© University of Kent - Contact | Feedback | Legal | FOI | Cookies
Publications by Prof Gareth Howells
Also view these in the Kent Academic Repository
Articles
Gu, X., Howells, G. and Yuan, H. (2024) 'A soft prototype-based autonomous fuzzy inference system for network intrusion detection', Information Sciences. Elsevier. doi: doi:10.1016/j.ins.2024.120964.
Abstract | View in KAR | View Full Text
Nowadays, cyber-attacks have become a common and persistent issue affecting various human activities in modern societies. Due to the continuously evolving landscape of cyber-attacks and the growing concerns around "black box" models, there has been a strong demand for novel explainable and interpretable intrusion detection systems with online learning abilities. In this paper, a novel soft prototype-based autonomous fuzzy inference system (SPAFIS) is proposed for network intrusion detection. SPAFIS learns from network traffic data streams online on a chunk-by-chunk basis and autonomously identifies a set of meaningful, human-interpretable soft prototypes to build an IF-THEN fuzzy rule base for classification. Thanks to the utilization of soft prototypes, SPAFIS can precisely capture the underlying data structure and local patterns, and perform internal reasoning and decision-making in a human-interpretable manner based on the ensemble properties and mutual distances of data. To maintain a healthy and compact knowledge base, a pruning scheme is further introduced to SPAFIS, allowing itself to periodically examine the learned solution and remove redundant soft prototypes from its knowledge base. Numerical examples on public network intrusion detection datasets demonstrated the efficacy of the proposed SPAFIS in both offline and online application scenarios, outperforming the state-of-the-art alternatives.
Dib, J., Sirlantzis, K. and Howells, G. (2023) 'An annotated water-filled, and dry potholes dataset for deep learning applications', Data in Brief. Elsevier. doi: 10.1016/j.dib.2023.109206.
Abstract | View in KAR | View Full Text
Potholes have long posed a challenging risk to automated systems due to their random and stochastic shapes and the reflectiveness of their surface when filled with water, whether it is "muddy" water or clear water. This has formed a significant limitation to autonomous assistive technologies such as Electric-Powered Wheelchairs (EPWs), mobility scooters, etc. due to the risk potholes pose on the user's well-being as it could cause severe falls and injuries as well as neck and back problems. Current research proved that Deep Leaning technologies are one of the most relevant solutions used to detect potholes due to the high accuracy of the detection. One of the main limitations to the datasets currently made available is the lack of photos describing water-filled, rabble-filled, and random coloured potholes. The purpose of our dataset is to provide the answer to this problem as it contains 713 high-quality photos representing 1152 manually-annotated potholes in different shapes, locations, colours, and conditions, all of which were manually-collected via a mobile phone and within different areas in the United Kingdom along with two additional benchmarking videos recorded via a dashcam.
Mohamed, E., Sirlantzis, K., Howells, G. and Hoque, S. (2022) 'Optimisation of Deep Learning Small-Object Detectors with Novel Explainable Verification', Sensors. MDPI, pp. 1-23. doi: 10.3390/s22155596.
Abstract | View in KAR | View Full Text
In this paper, we present a novel methodology based on machine learning for identifying the most appropriate from a set of available state-of-the-art object detectors for a given application. Our particular interest is to develop a road map for identifying verifiably optimal selections, especially for challenging applications such as detecting small objects in a mixed-size object dataset. State-of�the-art object detection systems often find the localisation of small-size objects challenging since most are usually trained on large-size objects. These contain abundant information as they occupy a large number of pixels relative to the total image size. This fact is normally exploited by the model during training and inference processes. To dissect and understand this process, our approach systematically examines detectors' performances using two very distinct deep convolutional networks. The first is the single-stage YOLO V3 and the second is the double-stage Faster R-CNN. Specifically, our proposed method explores and visually illustrates the impact of feature extraction layers, number of anchor boxes, data augmentation, etc., utilising ideas from the field of explainable Artificial Intelligence (XAI). Our results, for example, show that multi-head YOLO V3 detectors trained using augmented data produce better performance even with a fewer number of anchor boxes. Moreover, robustness regarding the detector's ability to explain how a specific decision was reached is investigated using different explanation techniques. Finally, two new visualisation techniques are proposed, WS-Grad and Concat-Grad, for identifying explanation cues of different detectors. These are applied to specific object detection tasks to illustrate their reliability and transparency with respect to the decision process. It is shown that the proposed techniques can result in high resolution and comprehensive heatmaps of the image areas, significantly affecting detector decisions as compared to the state-of-the-art techniques tested.
Mohamed, E., Sirlantzis, K. and Howells, G. (2022) 'A review of visualisation-as-explanation techniques for convolutional neural networks and their evaluation', Displays. Elsevier Science B.V. Available at: https://www.sciencedirect.com/science/article/pii/S014193822200066X.
Abstract | View in KAR | View Full Text
Visualisation techniques are powerful tools to understand the behaviour of Artificial Intelligence (AI) systems. They can be used to identify important features contributing to the network decisions, investigate biases in datasets, and find weaknesses in the system's structure (e.g., network architectures). Lawmakers and regulators may not allow the use of smart systems if these systems cannot explain the logic underlying a decision or action taken. These systems are required to offer a high level of 'transparency' to be approved for deployment. Model transparency is vital for safety-critical applications such as autonomous navigation and operation systems (e.g., autonomous trains or cars), where prediction errors may have serious implications. Thus, being highly accurate without explaining the basis of their performance is not enough to satisfy regulatory requirements. The lack of system interpretability is a major obstacle to the wider adoption of AI in safety-critical applications. Explainable Artificial Intelligence (XAI) techniques applied to intelligent systems to justify their decisions offers a possible solution. In this review, we present state-of-the-art explanation techniques in detail. We focus our presentation and critical discussion on visualisation methods for the most adopted architecture in use, the Convolutional Neural Networks (CNNs), applied to the domain of image classification. Further, we discuss the evaluation techniques for different explanation methods, which shows that some of the most visually appealing methods are unreliable and can be considered a simple feature or edge detector. In contrast, robust methods can give insights into the model behaviour, which helps to enhance the model performance and boost the confidence in the model's predictions. Besides, the applications of XAI techniques show their importance in many fields such as medicine and industry. We hope that this review proves a valuable contribution for researchers in the field of XAI.
Mohamed, E., Sirlantzis, K., Howells, G. and Dib, J. (2022) 'Investigation of Vibration and User Comfort for Powered Wheelchairs', IEEE Sensors Letters. IEEE. doi: 10.1109/LSENS.2022.3147740.
Abstract | View in KAR | View Full Text
Disabled users who use powered wheelchairs for mobility may suffer back and neck pain. Prolonged exposition to whole-body vibration due to different terrain surfaces may negatively impact the user's health and comfort. This study investigates the impact of whole-body vibration on powered wheelchair users following the ISO-2631 standard. The ISO-2631 standard defines the whole-body vibration limits and quantify its impact on the user's health and comfort. Four users with a range of different weights drive an Electrical Powered Wheelchair (EPW) on five different terrain surfaces. Results indicate that users' weights can impact vibration perception. Additionally, outdoor surfaces generally produce high vertical accelerations, which can negatively impact the user's health and comfort when the EPW is driven for a long period.
Mohamed, E., Sirlantzis, K. and Howells, G. (2022) 'A pixel-wise annotated dataset of small overlooked indoor objects for semantic segmentation applications', Data in Brief. Elsevier. doi: 10.1016/j.dib.2022.107791.
Abstract | View in KAR | View Full Text
The purpose of the dataset is to provide annotated images for pixel classification tasks with application to powered wheelchair users. As some of the widely available datasets contain only general objects, we introduced this dataset to cover the missing pieces, which can be considered as application-specific objects. However, these objects of interest are not only important for powered wheelchair users but also for indoor navigation and environmental understanding in general. For example, indoor assistive and service robots need to comprehend their surroundings to ease navigation and interaction with different size objects. The proposed dataset is recorded using a camera installed on a powered wheelchair. The camera is installed beneath the joystick so that it can have a clear vision with no obstructions from the user's body or legs. The powered wheelchair is then driven through the corridors of the indoor environment, and a one-minute video is recorded. The collected video is annotated on the pixel level for semantic segmentation (pixel classification) tasks. Pixels of different objects are annotated using MATLAB software. The dataset has various object sizes (small, medium, and large), which can explain the variation of the pixel's distribution in the dataset. Usually, Deep Convolutional Neural Networks (DCNNs) that perform well on large-size objects fail to produce accurate results on small-size objects. Whereas training a DCNN on a multi-size objects dataset can build more robust systems. Although the recorded objects are vital for many applications, we have included more images of different kinds of door handles with different angles, orientations, and illuminations as they are rare in the publicly available datasets. The proposed dataset has 1549 images and covers nine different classes. We used the dataset to train and test a semantic segmentation system that can aid and guide visually impaired users by providing visual cues.
Mohamed, E., Konstantin, S. and Howells, G. (2021) 'Indoor/Outdoor Semantic Segmentation Using Deep Learning for Visually Impaired Wheelchair Users', IEEE Access. IEEE. doi: 10.1109/ACCESS.2021.3123952.
Abstract | View in KAR | View Full Text
Electrical Powered Wheelchair (EPW) users may find navigation through indoor and outdoor environments a significant challenge due to their disabilities. Moreover, they may suffer from near-sightedness or cognitive problems that limit their driving experience. Developing a system that can help EPW users to navigate safely by providing visual feedback and further assistance when needed can have a significant impact on the user's wellbeing. This paper presents computer vision systems based on deep learning, with an architecture based on residual blocks that can semantically segment high-resolution images. The systems are modified versions of DeepLab version 3 plus that can process high-resolution input images. Besides, they can simultaneously process images from indoor and outdoor environments, which is challenging due to the difference in data distribution and context. The proposed systems replace the base network with a smaller one and modify the encoder-decoder architecture. Nevertheless, they produce high-quality outputs with fast inference speed compared to the systems with deeper base networks. Two datasets are used to train the semantic segmentation systems: an indoor application-based dataset that has been collected and annotated manually and an outdoor dataset to cover both environments. The user can toggle between the two individual systems depending on the situation. Moreover, we proposed shared systems that automatically use a specific semantic segmentation system depending on the pixels' confidence scores. The annotated output scene is presented to the EPW user, which can aid with the user's independent navigation. State-of-the-art semantic segmentation techniques are discussed and compared. Results show the ability of the proposed systems to detect objects with sharp edges and high accuracy for indoor and outdoor environments. The developed systems are deployed on a GPU based board and then integrated on an EPW for practical usage and evaluation.
Tahir, R., Tahir, S., McDonald-Maier, K. D., Howells, G. and Sajjad, A. (2021) 'A Novel ICMetric Public Key Framework for Secure Communication', Journal of Network and Computer Applications. Elsevier. doi: 10.1016/j.jnca.2021.103235.
Abstract | View in KAR | View Full Text
The Integrated Circuit Metric (ICMetric) technology is a novel trust basis that uses the system features to create an identication of a device. The ICMetric of the device is used for the provision of security services, thereby addressing the issue of trust associated with device identity. The ICMetric technology can be adapted to function with varying environments; however, the short length and low entropy of the ICMetric key pose a major threat to applications based on ICMetric. This paper proposes a secure compre-hensive ICMetric based architecture that facilitates asymmetric ICMetric applications for secure services in an end-to-end environment. This novel framework has been designed keeping in mind the construction principles of ICMetric thereby preventing threats that are prevalent in many security schemes. Finally, an empirical evaluation and feasibility has been presented by implementing the proposed framework and doing an extensive security analysis.
Khanna, P., Howells, G. and Lazaridis, P. (2021) 'Design and Implementation of Low‑Cost Real‑Time Energy Logger for Industrial and Home Applications', Wireless Personal Communications. Springer. doi: 10.1007/s11277-021-08350-1.
Abstract | View in KAR | View Full Text
With the significant increase in energy demands in the last decade, the issues of unnecessaryenergy usage have increased rapidly. Therefore, there is an immediate need to providea cheap and easily accessible monitoring tool for the energy consumed by an applianceused in homes and industries. Instead of monitoring the total power consumption of thehouses and/or industries, it is useful to monitor the power consumption of the individualappliance, which in turn, helps in saving the overall energy usage and thereby makes itcost-effective. This paper presents a cost-efficient design and implementation of a monitoringsystem that can precisely measure the current and voltage of each appliance. Thedesign provides tracking of device activity in a real-time environment for the industries andhelps in adopting to the green initiative. The design comprises of Arduino based microcontrollerand Raspberry Pi, that performs precise measurements of current and voltageof the device, followed by measuring the power consumed by the device. This paper presentstwo different system designs, one for the single-phase measurements and the otherfor the DC measurements. The single-phase measurement device comprises of 10-bit ADCwhereas, the 24 V DC measurement device comprises of a 12-bit ADC, which provideshigher measurement accuracy compared to other systems available in the market. Theimplemented design uses the EmonCMS web application to accumulate and envision themonitored data. It provides a flexible and user-friendly solution to monitor the measureddata easily on any android or iOS devices.
Yang, Y., Yan, X., Sirlantzis, K. and Howells, G. (2021) 'Regular form-based sliding mode control design on a two-wheeled inverted pendulum', International Journal of Modelling, Identification and Control. Inderscience, pp. 312-320. doi: 10.1504/IJMIC.2021.121846.
Abstract | View in KAR | View Full Text
In this paper, a Lagrangian-based dynamics is employed for a two-wheeled inverted pendulum with the consideration of unknown matched and unmatched uncertainties which are bounded by known nonlinear functions. The model is linearised and further transformed into a regular form to facilitate the analysis and design. A sliding surface is designed, and a set of conditions is developed such that the resulting sliding motion is uniformly ultimately bounded from a practical perspective. Further, a sliding mode control scheme is proposed such that the system is driven to the sliding surface in finite time and maintained on it thereafter. Finally, both simulation and experiment are presented using practical model parameters data to demonstrate the effectiveness and robustness of the regulation control.
Dib, J., Sirlantzis, K. and Howells, G. (2020) 'A Review on Negative Road Anomaly Detection Methods', IEEE Access. IEEE. doi: 10.1109/ACCESS.2020.2982220.
Abstract | View in KAR | View Full Text
The main limitation to obstacle avoidance nowadays has been negative road anomalies which is the term we used to refer to potholes and cracks due to their negative drop from the surface of the road. This has for long been a limitation because of the fact that they exist in different, random and stochastic shapes. Today's technology lacks the presence of sensors capable of detecting negative road anomalies efficiently as the latter surpasses the sensor's limitations rendering the sensing technique inaccurate. A significant amount of research has been focused on the detection of negative road anomalies due to the fact that this topic is becoming a hot research topic. In this paper, the existing techniques will be reviewed. Their limitations will be highlighted and they will be assessed via certain performance indicators and via some chosen criteria which will be introduced.
Gillham, M., Pepper, M., Kelly, S. and Howells, G. (2017) 'Stakeholder views addressing the development and uptake of powered wheelchair assistive technology', Disability and Rehabilitation: Assistive Technology. Taylor & Francis, pp. 146-160. doi: 10.1080/17483107.2017.1416186.
Abstract | View in KAR | View Full Text
Purpose: The objective of this research is to identify stakeholder views with regard to the development of effective powered wheelchair assistive technologies more suited to the user and carer needs, whilst also meeting the requirements for other stakeholders, such that developers can be better guided towards producing solutions which have a better chance of getting to the market place and hence to the end user. Method: A questionnaire was designed to collect the views of all stakeholders and circulated to a statistically representative number of them. The question rating data was then checked for correlation between groups, and within groups, to establish validity. Results: The 74 stakeholders across the eight classes who responded had a good correlation between each other, with a cross class 'Pearson's correlation' ranging between 0.7 and 0.95, and the 'Fleiss's Kappa reliability of agreement' within each class ranging between 0.07 and 0.36. Conclusions: This research has identified that all stakeholders should be involved in the development of the technology and that some may benefit in 'role-reversal' to help understand user problems and stakeholder concerns more clearly. Cost was a significant barrier to the uptake of appropriate technology, and training of users and carers was a major issue. Furthermore development should not increase user isolation and the impact on the user must be monitored for 'quality of life'. Technical support and training should be given to the user and their carers and equipment must be adaptive to meet the changing needs of the user.
Gillham, M., Pepper, M. G., Kelly, S. W. and Howells, G. (2017) 'Feature determination from powered wheelchair user joystick input characteristics for adapting driving assistance', Wellcome Open Research. F1000Research. doi: 10.12688/wellcomeopenres.12280.3.
Abstract | View in KAR | View Full Text
Background: Many powered wheelchair users find their medical condition and their ability to drive the wheelchair will change over time. In order to maintain their independent mobility, the powered chair will require adjustment over time to suit the user's needs, thus regular input from healthcare professionals is required. These limited resources can result in the user having to wait weeks for appointments, resulting in the user losing independent mobility, consequently affecting their quality of life and that of their family and carers. In order to provide an adaptive assistive driving system, a range of features need to be identified which are suitable for initial system setup and can automatically provide data for re-calibration over the long term. Methods: A questionnaire was designed to collect information from powered wheelchair users with regard to their symptoms and how they changed over time. Another group of volunteer participants were asked to drive a test platform and complete a course which represented manoeuvring in a very confined space as quickly as possible. Two of those participants were also monitored over a longer period in their normal home daily environment. Features, thought to be suitable, were examined using pattern recognition classifiers to determine their suitability for identifying the changing user input over time. Results: The results are not designed to provide absolute insight into the individual user behaviour, as no ground truth of their ability has been determined, they do nevertheless demonstrate the utility of the measured features to provide evidence of the users' changing ability over time whilst driving a powered wheelchair. Conclusions: Determining the driving features and adjustable elements provides the initial step towards developing an adaptable assistive technology for the user when the ground truths of the individual and their machine have been learned by a smart pattern recognition system
Hu, Y., Sirlantzis, K. and Howells, G. (2016) 'Optimal Generation of Iris Codes for Iris Recognition', IEEE Transactions on Information Forensics and Security. IEEE, pp. 157-171. doi: 10.1109/TIFS.2016.2606083.
Abstract | View in KAR | View Full Text
The calculation of binary iris codes from feature values (e.g. the result of Gabor transform) is a key step in iris recognition systems. Traditional binarization method based on the sign of feature values has achieved very promising performance. However, currently, little research focuses on a deeper insight into this binarization method to produce iris codes. In this paper, we illustrate the iris code calculation from the perspective of optimization. We demonstrate that the traditional iris code is the solution of an optimization problem which minimizes the distance between the feature values and iris codes. Furthermore, we show that more effective iris codes can be obtained by adding terms to the objective function of this optimization problem. We investigate two additional objective terms. The first objective term exploits the spatial relationships of the bits in different positions of an iris code. The second objective term mitigates the influence of less reliable bits in iris codes. The two objective terms can be applied to the optimization problem individually, or in a combined scheme. We conduct experiments on four benchmark datasets with varying image quality. The experimental results demonstrate that the iris code produced by solving the optimization problem with the two additional objective terms achieves a generally improved performance in comparison to the traditional iris code calculated by binarizing feature values based on their signs.
Hu, Y., Sirlantzis, K., Howells, G., Ragot, N. and Rodríguez, P. (2016) 'An online background subtraction algorithm deployed on a NAO humanoid robot based monitoring system', Robotics and Autonomous Systems. Elsevier, pp. 37-47. doi: 10.1016/j.robot.2016.08.013.
Abstract | View in KAR | View Full Text
In this paper, we design a fast background subtraction algorithm and deploy this algorithm on a monitoring system based on NAO humanoid robot. The proposed algorithm detects a contiguous foreground via a contiguously weighted linear regression (CWLR) model. It consists of a background model and a foreground model. The background model is a regression based low rank model. It seeks a low rank background subspace and represents the background as the linear combination of the basis spanning the subspace. The foreground model promotes the contiguity in the foreground detection. It encourages the foreground to be detected as whole regions rather than separated pixels. We formulate the background and foreground model into a contiguously weighted linear regression problem. This problem can be solved efficiently via an alternating optimization approach which includes continuous and discrete variables. Given an image sequence, we use the first few frames to incrementally initialize the background subspace, and we determine the background and foreground in the following frames in an online scheme using the proposed CWLR model, with the background subspace continuously updated using the detected background information. The proposed algorithm is implemented by Python on a NAO humanoid robot based monitoring system. This system consists of a control station and a Nao robot. The Nao robot acts as a mobile probe. It captures image sequence and sends it to the control station. The control station serves as a control terminal. It sends commands to control the behaviour of Nao robot, and it processes the image data sent by Nao. This system can be used for living environment monitoring and form the basis for many vision-based applications like fall detection and scene understanding. The experimental comparisons with most recent algorithms on both benchmark dataset and NAO captures demonstrate the high effectiveness of the proposed algorithm.
Hu, Y., Sirlantzis, K. and Howells, G. (2016) 'A novel iris weight map method for less constrained iris recognition based on bit stability and discriminability', Image and Vision Computing. Elsevier, pp. 168-180. doi: 10.1016/j.imavis.2016.05.003.
In this paper, we propose and investigate a novel iris weight map method for iris matching stage to improve less constrained iris recognition. The proposed iris weight map considers both intra-class bit stability and inter-class bit discriminability of iris codes. We model the intra-class bit stability in a stability map to improve the intra-class matching. The stability map assigns more weight to the bits that have values more consistent with their noiseless and stable estimates obtained using a low rank approximation from a set of noisy training images. Also, we express the inter-class bit discriminability in a discriminability map to enhance the inter-class separation. We calculate the discriminability map using a 1-to-N strategy, emphasizing the bits with more discriminative power in iris codes. The final iris weight map is the combination of the stability map and the discriminability map. We conduct experimental analysis on four publicly available datasets captured in varying less constrained conditions. The experimental results demonstrate that the proposed iris weight map achieves generally improved identification and verification performance compared to state-of-the-art methods.
Hu, Y., Sirlantzis, K. and Howells, G. (2016) 'Signal-Level Information Fusion for Less Constrained Iris Recognition using Sparse-Error Low Rank Matrix Factorization', IEEE Transactions on Information Forensics and Security. IEEE, pp. 1549-1564. doi: 10.1109/TIFS.2016.2541612.
Abstract | View in KAR | View Full Text
Iris recognition systems working in less constrained environments with the subject at-a-distance and on-the-move suffer from the noise and degradations in the iris captures. These noise and degradations significantly deteriorate iris recognition performance. In this paper, we propose a novel signal-level information fusion method to mitigate the influence of noise and degradations for less constrained iris recognition systems. The proposed method is based on low rank approximation (LRA). Given multiple noisy captures of the same eye, we assume that: 1) the potential noiseless images lie in a low rank subspace and 2) the noise is spatially sparse. Based on these assumptions, we seek an LRA of noisy captures to separate the noiseless images and noise for information fusion. Specifically, we propose a sparse-error low rank matrix factorization model to perform LRA, decomposing the noisy captures into a low rank component and a sparse error component. The low rank component estimates the potential noiseless images, while the error component models the noise. Then, the low rank and error components are utilized to perform signal-level fusion separately, producing two individually fused images. Finally, we combine the two fused images at the code level to produce one iris code as the final fusion result. Experiments on benchmark data sets demonstrate that the proposed signal-level fusion method is able to achieve a generally improved iris recognition performance in less constrained environment, in comparison with the existing iris recognition algorithms, especially for the iris captures with heavy noise and low quality.
Gillham, M. and Howells, G. (2015) 'A Dynamic Localized Adjustable Force Field Method for Real-time Assistive Non-holonomic Mobile Robotics', International Journal of Advanced Robotic Systems. INTECH, p. 1. doi: 10.5772/61190.
Abstract | View in KAR | View Full Text
Providing an assistive navigation system that augments rather than usurps user control of a powered wheelchair represents a significant technical challenge. This paper evaluates an assistive collision avoidance method for a powered wheelchair that allows the user to navigate safely whilst maintaining their overall governance of the platform motion. The paper shows that by shaping, switching and adjusting localized potential fields we are able to negotiate different obstacles by generating a more intuitively natural trajectory, one that does not deviate significantly from the operator in the loop desired-trajectory. It can also be seen that this method does not suffer from the local minima problem, or narrow corridor and proximity oscillation, which are common problems that occur when using potential fields. Furthermore this localized method enables the robotic platform to pass very close to obstacles, such as when negotiating a narrow passage or doorway.
Ye, B., Howells, G., Haciosman, M. and Wang, F. Z. (2015) 'Multi-dimensional key generation of ICMetrics for cloud computing', Journal of Cloud Computing. doi: 10.1186/s13677-015-0044-6.
Abstract | View in KAR | View Full Text
Despite the rapid expansion and uptake of cloud based services, lack of trust in the provenance of such services represents a significant inhibiting factor in the further expansion of such service. This paper explores an approach to assure trust and provenance in cloud based services via the generation of digital signatures using properties or features derived from their own construction and software behaviour. The resulting system removes the need for a server to store a private key in a typical Public/Private-Key Infrastructure for data sources. Rather, keys are generated at run-time by features obtained as service execution proceeds. In this paper we investigate several potential software features for suitability during the employment of a cloud service identification system. The generation of stable and unique digital identity from features in Cloud computing is challenging because of the unstable operation environments that implies the features employed are likely to vary under normal operating conditions. To address this, we introduce a multi-dimensional key generation technology which maps from multi-dimensional feature space directly to a key space. Subsequently, a smooth entropy algorithm is developed to evaluate the entropy of key space.
Hu, Y., Sirlantzis, K. and Howells, G. (2015) 'Iris liveness detection using regional features', Pattern Recognition Letters. Elsevier. doi: 10.1016/j.patrec.2015.10.010.
In this paper, we exploit regional features for iris liveness detection. Regional features are designed based on the relationship of the features in neighbouring regions. They essentially capture the feature distribution among neighbouring regions. We construct the regional features via two models: spatial pyramid and relational measure which seek the feature distributions in regions with varying size and shape respectively. The spatial pyramid model extracts features from coarse to fine grid regions, and, it models a local to global feature distribution. The local distribution captures the local feature variations while the global distribution includes the information that is more robust to translational transform. The relational measure is based on a feature-level convolution operation defined in this paper. By varying the shape of the convolution kernel, we are able to obtain the feature distribution in regions with different shapes. To combine the feature distribution information in regions with varying size and shape, we fuse the results based on the two models at the score level. Experimental results on benchmark datasets demonstrate that the proposed method achieves an improved performance compared to state-of-the-art features.
Zhai, X., Appiah, K., Ehsan, S., Howells, G., Hu, H., Gu, D. and McDonald-Maier, K. (2015) 'Exploring ICMetrics to detect abnormal program behaviour on embedded devices', Journal of Systems Architecture. Elsevier, pp. 567-575. doi: 10.1016/j.sysarc.2015.07.007.
Execution of unknown or malicious software on an embedded system may trigger harmful system behaviour targeted at stealing sensitive data and/or causing damage to the system. It is thus considered a potential and significant threat to the security of embedded systems. Generally, the resource constrained nature of commercial off-the-shelf (COTS) embedded devices, such as embedded medical equipment, does not allow computationally expensive protection solutions to be deployed on these devices, rendering them vulnerable. A Self-Organising Map (SOM) based and Fuzzy C-means based approaches are proposed in this paper for detecting abnormal program behaviour to boost embedded system security. The presented technique extracts features derived from processor's Program Counter (PC) and Cycles per Instruction (CPI), and then utilises the features to identify abnormal behaviour using the SOM. Results achieved in our experiment show that the proposed SOM based and Fuzzy C-means based methods can identify unknown program behaviours not included in the training set with 90.9% and 98.7% accuracy.
Hu, Y., Sirlantzis, K. and Howells, G. (2015) 'Improving colour iris segmentation using a model selection technique', Pattern Recognition Letters. Elsevier Science BV, PO Box 211, 1000 AE Amsterdam, Netherlands, pp. 24-32. doi: doi:10.1016/j.patrec.2014.12.012.
In this paper, we propose a novel method to improve the reliability and accuracy of colour iris segmentation for captures both from static and mobile devices. Our method is a fusion strategy based on selection among the segmentation outcomes of different segmentation methods or models. First, we present and analyse an iris segmentation framework which uses three different models to show that improvements can be obtained by selection among the outcomes generated by the three models. Then, we introduce a model selection method which defines the optimal segmentation based on a ring-shaped region around the outer segmentation boundary identified by each model. We use the histogram of oriented gradients (HOG) as features extracted from the ring-shaped region, and train a SVM-based classifier which provides the selection decision. Experiments on colour iris datasets, captured by mobile devices and static camera, show that the proposed method achieves an improved performance compared to the individual iris segmentation models and existing algorithms.
Zhai, X., Appiah, K., Ehsan, S., Howells, G., Hu, H., Gu, D. and McDonald-Maier, K. D. (2015) 'A Method for Detecting Abnormal Program Behavior on Embedded Devices', IEEE Transactions on Information Forensics and Security. IEEE, pp. 1692-1704. doi: doi:10.1109/TIFS.2015.2422674.
Abstract | View in KAR | View Full Text
A potential threat to embedded systems is the execution of unknown or malicious software capable of triggering harmful system behavior, aimed at theft of sensitive data or causing damage to the system. Commercial off-the-shelf embedded devices, such as embedded medical equipment, are more vulnerable as these type of products cannot be amended conventionally or have limited resources to implement protection mechanisms. In this paper, we present a self-organizing map (SOM)-based approach to enhance embedded system security by detecting abnormal program behavior. The proposed method extracts features derived from processor's program counter and cycles per instruction, and then utilises the features to identify abnormal behavior using the SOM. Results achieved in our experiment show that the proposed method can identify unknown program behaviors not included in the training set with over 98.4% accuracy.
Gillham, M., Howells, G., Spurgeon, S. K. and McElroy, B. (2013) 'Floor Covering and Surface Identification for Assistive Mobile Robotic Real-Time Room Localization Application', Sensors. MDPI, pp. 17501-17515. doi: 10.3390/s131217501.
Abstract | View in KAR | View Full Text
Assistive robotic applications require systems capable of interaction in the human world, a workspace which is highly dynamic and not always predictable. Mobile assistive devices face the additional and complex problem of when and if intervention should occur; therefore before any trajectory assistance is given, the robotic device must know where it is in real-time, without unnecessary disruption or delay to the user requirements. In this paper, we demonstrate a novel robust method for determining room identification from floor features in a real-time computational frame for autonomous and assistive robotics in the human environment. We utilize two inexpensive sensors: an optical mouse sensor for straightforward and rapid, texture or pattern sampling, and a four color photodiode light sensor for fast color determination. We show how data relating floor texture and color obtained from typical dynamic human environments, using these two sensors, compares favorably with data obtained from a standard webcam. We show that suitable data can be extracted from these two sensors at a rate 16 times faster than a standard webcam, and that these data are in a form which can be rapidly processed using readily available classification techniques, suitable for real-time system application. We achieved a 95% correct classification accuracy identifying 133 rooms' flooring from 35 classes, suitable for fast coarse global room localization application, boundary crossing detection, and additionally some degree of surface type identification.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2013) 'A Colour Iris Recognition System Employing Multiple Classifier Techniques', ELCVIA Electronic Letters on Computer Vision and Image Analysis. CVC Press, pp. 54-65. doi: 10.5565/rev/elcvia.520.
The randomness of iris texture has allowed researchers to develop biometric systems with almost flawless accuracies. However, a common drawback of the majority of existing iris recognition systems is the constrained environment in which the user is enroled and recognized. The iris recognition systems typically require a high quality iris image captured under near infrared illumination. A desirable property of an iris recognition system is to be able to operate on colour images, whilst maintaining a high accuracy. In the present work we propose an iris recognition methodology which is designed to cope with noisy colour iris images. There are two main contributions of this paper: first, we adapt standard iris features proposed in literature for near infrared images by applying a feature selection method on features extracted from various colour channels; second, we introduce a Multiple Classifier System architecture to enhance the recognition accuracy of the biometric system. With a feature size of only 360 real valued components, the proposed iris recognition system performs with a high accuracy on UBIRISv1 dataset, in both identification and verfication scenarios.
Radu, P., Sirlantzis, K., Howells, G., Deravi, F. and Hoque, S. (2013) 'A review of information fusion techniques employed in iris recognition systems', International Journal of Advanced Intelligence Paradigms. InderScience Publishers, pp. 211-240. doi: 10.1504/IJAIP.2012.052067.
Iris recognition has shown to be one of the most reliable biometric authentication methods. The majority of iris recognition systems which have been developed require a constrained environment to enrol and recognise the user. If the user is not cooperative or the capture environment changes then the accuracy of the iris recognition system may decrease significantly. To minimise the effect of such limitations, possible solutions include the use of multiple channels of information such as using both eyes or extracting more iris feature types and subsequently employing an efficient fusion method. In this paper, we present a review of iris recognition systems using information from multiple sources that are fused in different ways or at different levels. A categorisation of the iris recognition systems incorporating multiple classifier systems is also presented. As a new desirable dimension of a biometric system, besides those proposed in the literature, the mobility of such a system is introduced in this work. The review charts the path towards greater flexibility and robustness of iris recognition systems through the use of information fusion techniques and points towards further developments in the future leading to mobile and ubiquitous deployment of such systems.
Sheng, W., Howells, G., Fairhurst, M., Deravi, F. and Chen, S. (2012) 'Reliable and Secure Encryption Key Generation from Fingerprints', Information Management & Computer Security. Emerald Group Publishing Limited, pp. 207-221. doi: 10.1108/09685221211247307.
Purpose ? Biometric authentication, which requires storage of biometric templates and/or encryption keys, raises a matter of serious concern, since the compromise of templates or keys necessarily compromises the information secured by those keys. To address such concerns, efforts based on dynamic key generation directly from the biometrics have recently emerged. However, previous methods often have quite unacceptable authentication performance and/or small key spaces and therefore are not viable in practice. The purpose of this paper is to propose a novel method which can reliably generate long keys while requires storage of neither biometric templates nor encryption keys. Design/methodology/approach ? This proposition is achieved by devising the use of fingerprint orientation fields for key generation. Additionally, the keys produced are not permanently linked to the orientation fields, hence, allowing them to be replaced in the event of key compromise. Findings ? The evaluation demonstrates that the proposed method for dynamic key generation can offer both good reliability and security in practice, and outperforms other related methods. Originality/value ? In this paper, the authors propose a novel method which can reliably generate long keys while requires storage of neither biometric templates nor encryption keys. This is achieved by devising the use of fingerprint orientation fields for key generation. Additionally, the keys produced are not permanently linked to the orientation fields, hence, allowing them to be replaced in the event of key compromise.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2011) 'Information Fusion for Unconstrained Iris Recognition', International Journal of Hybrid Information Technology. SERSC, pp. 1-12.
The majority of the iris recognition algorithms available in the literature were developed to operate on near infrared images. A desirable feature of iris recognition systems with reduced constraints such as potential operability on commonly available hardware is to work with images acquired under visible wavelength. Unlike in near infrared images, in colour iris images the pigment melanin present in the iris tissue causes the appearance of reflections, which are one of the major noise factors present in colour iris images. In this paper we present an iris recognition system which is able to cope with noisy colour iris images by employing score level fusion between different channels of the iris image. The robustness of the proposed approach is tested on three colour iris images datasets, ranging from images captured with professional cameras in both constrained environment and less cooperative scenario, and finally to iris images acquired with a mobile phone.
McElroy, B. and Howells, G. (2011) 'Automated Adaptation of Input and Output Data for a Weightless Artificial Neural Network', International Journal of Database Theory and Application. SERSC, pp. 49-58.
The ability to adapt automated guided vehicles for employment to a range of practical situations can significantly enhance their usability in hazardous situations where security is a major concern and it is inadvisable for humans to enter. Robot guidance is still a very challenging issue computationally in both the academic and industrial worlds. Whilst considerable progress has been made in robotics in the last few decades, many still experience difficulties in the recognition of dynamically changing situations such as our daily environments. With so many different scenarios it is difficult to find one system that can effectively deal with both the expected and unexpected issues that may arise. This paper examines the possibility of manipulating the potential inputs and outputs to a system to tailor a better solution to the current problem. Weightless neural networks will be used as a classification tool to determine the direction of a robot in an open loop simulation.
McConnon, G., Deravi, F., Hoque, S., Sirlantzis, K. and Howells, G. (2011) 'An Investigation of Quality Aspects of Noisy Colour Images for Iris Recognition', International Journal of Signal Processing, Image Processing and Pattern Recognition. SERSC, pp. 165-178. Available at: http://www.sersc.org/journals/IJSIP/vol4_no3.php.
The UBIRIS.v2 dataset is a set of noisy colour iris images designed to simulate visible wavelength iris acquisition at-a-distance and on-the-move. This paper presents an examination of some of the characteristics that can impact the performance of iris recognition in the UBIRIS.v2 dataset. This dataset consists of iris images in the visible wavelength and was designed to be noisy. The quality and characteristics of these images are surveyed by examining seven different channels of information extracted from them: red, green, blue, intensity, value, lightness, and luminance. We present new quality metrics to assess the image characteristics with regard to focus, entropy, reflections, pupil constriction and pupillary boundary contrast. The results clearly suggest the existence of different characteristics for these channels and could be exploited for use in the design and evaluation of iris recognition systems.
Kovalchuk, Y., McDonald-Maier, K. D. and Howells, G. (2011) 'Overview of ICmetrics Technology – Security Infrastructure for Autonomous and Intelligent Healthcare System', International Journal of u- and e-Service, Science and Technology. SERSC, pp. 49-60.
Recent developments in bio-, nano-, and digital technology have changed the way modern healthcare systems operate. The provision of healthcare servicing remotely and exploitation of monitoring and assistive technology within and outside medical institutions mean that medical staff and patients constantly interact with various electronic devices. It also means that sensitive patient data are stored on and being transmitted between these devices. To ensure safe and secure use of medical equipment, as well as authorised access to data, appropriate encryption and debugging infrastructure should be integrated into the modern healthcare system. This paper introduces a novel concept, ICmetrics, that can serve as a basis for developing such infrastructure. More specifically, the ICmetric technology is based on the idea of generating encryption keys directly from the characteristics of electronic systems' behaviour on both hard- and software levels. This may include features extracted from electronic circuits, sensors, machine-machine and machine-human interfaces, as well communication peripherals. While the proposed technology has a number of advantages over the existing security systems, it also poses interesting research challenges. These challenges along with the proposed solutions are discussed in the paper.
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2011) 'An advanced combination strategy for multi-classifiers employed in large multi-class problem domains', Journal of Applied Soft Computing. Elsevier, pp. 2151-2163. doi: 10.1016/j.asoc.2010.07.014.
Traditional artificial neural architectures possess limited ability to address the scale problem exhibited by a large number of distinct pattern classes and limited training data. To address these problems, this paper explores a novel advanced encoding scheme, which reduces both memory demand and execution time, and provides improved performance. The novel advanced encoding scheme known as the engine encoding, have been implemented in a multi-classifier, which combines the scaled probabilities, configuration information, and the discriminating abilities of the associated component classifiers. The problems of overloading and saturation experienced by traditional networks are solved by training the base classifiers on differing sub-sets of the required pattern classes and allowing the combiner classifier to derive a solution. Current Multi-classifier Systems are easily biased when trained on one class more often than another class, when patterns representing a class are very large compared to the rest, or when the multi-classifier depends on a certain fixed order of arrangement of pattern classes. A unique statistical arrangement method is hereby presented which aims to solve the bias problem. This statistical arrangement method also enhances independence of component classifiers. The system is demonstrated on the exemplar of fingerprint identification and utilizes a Weightless Neural System called the Enhanced Probabilistic Convergent Neural Network (EPCN) in a Multi-classifier System.
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2010) 'A Novel Weightless Artificial Neural Based Multi-Classifier for Complex Classifications', Neural Process Letters. Springer, pp. 25-44. doi: 10.1007/s11063-009-9125-1.
Artificial neural systems in general and weightless systems in particular have traditionally struggled in performance terms when confronted with problem domains such as possessing a large number of independent pattern classes and pattern classes with non-standard distributions. A multi-classifier is proposed which explores problem domains with a large number of independent pattern classes typically found in forensic and security databases. Specifically, the multi-classifier system is demonstrated on the exemplar of fingerprint identification problem typical to forensic, biometric, and security. Furthermore, the multi-classifier is able to provide a reasonable solution to benchmark problems from medicinal and physical (science) fields, which are determining the health, state of thyroid glands and determining whether or not there is a structure in the ionosphere, respectively.
Sheng, W., Howells, G., Fairhurst, M., Deravi, F. and Harmer, K. (2009) 'Consensus Fingerprint Matching with Genetically Optimised Approach', Pattern Recognition. Elsevier Science, pp. 1399-1407. doi: 10.1016/j.patcog.2008.11.038.
Fingerprint matching has been approached using various criteria based on different extracted features. However, robust and accurate fingerprint matching is still a challenging problem. In this paper, we propose an improved integrated method which operates by first suggesting a consensus matching function which combined different matching criteria based on heterogeneous features. We then devise a genetically guided approach to optimise the consensus matching function for simultaneous fingerprint alignment and verification. Since different features usually offer complementary information about the matching task, the consensus function is expected to improve the reliability of fingerprint matching. A related motivation for proposing such a function is to build a robust criterion that can perform well over a variety of different fingerprint matching instances. Additionally, by employing the global search functionality of a genetic algorithm along with a local matching operation for population initialisation, we aim to identify the optimal or near optimal global alignment between two fingerprints. The proposed algorithm is evaluated by means of a series of experiments conducted on public domain collections of fingerprint images and compared with previous work. Experimental results show that the consensus function can lead to a substantial improvement in performance while the local matching operation helps to identify promising initial alignment configurations, thereby speeding up the verification process. The resulting algorithm is more accurate than several other proposed methods which been implemented for comparison.
Wood, S. K., Akehurst, D. H., Uzenkov, O., Howells, G. and McDonald-Maier, K. D. (2008) 'A Model Driven Development Approach to Mapping UML State Diagrams to Synthesizable VHDL', IEEE Transactions on Computers. IEEE Computer Society, pp. 1357-1371. doi: 10.1109/TC.2008.123.
With the continuing rise in the complexity of embedded systems, there is an emerging need for a higher level modeling environment that facilitates efficient handling of this complexity. The aim here is to produce such a high-level environment using Model-Driven Development ( MDD) techniques that map a high-level abstract description of an electronic embedded system into its low-level implementation details. The Unified Modeling Language (UML) is a high-level graphical- based language that is broad enough in scope to model embedded systems hardware circuits. The authors have developed a framework for deriving Very High Speed Integrated Circuit Hardware Description Language ( VHDL) code from UML state diagrams and defined a set of rules that enable automated generation of synthesizable VHDL code from UML specifications using MDD techniques. By adopting the techniques and tools described in this paper, the design and implementation of complex state-based systems is greatly simplified.
Sheng, W., Howells, G., Fairhurst, M. and Deravi, F. (2008) 'Template-Free Biometric-Key Generation by Means of Fuzzy Genetic Clustering', IEEE Transactions on Information Forensics and Security, pp. 183-191. doi: 10.1109/TIFS.2008.922056.
Biometric authentication is increasingly gaining popularity in a wide range of applications. However, the storage of the biometric templates and/or encryption keys that are necessary for such applications is a matter of serious concern, as the compromise of templates or keys necessarily compromises the information secured by those keys. In this paper, we propose a novel method, which requires storage of neither biometric templates nor encryption keys, by directly generating the keys from statistical features of biometric data. An outline of the process is as follows: given biometric samples, a set of statistical features is first extracted from each sample. On each feature subset or single feature, we model the intra and interuser variation by clustering the data into natural clusters using a fuzzy genetic clustering algorithm. Based on the modelling results, we subsequently quantify the consistency of each feature subset or single feature for each user. By selecting the most consistent feature subsets and/or single features for each user individually, we generate the key reliably without compromising its relative security. The proposed method is evaluated on handwritten signature data and compared with related methods, and the results are very promising.
Statheros, T., Howells, G. and McDonald-Maier, K. D. (2008) 'Autonomous Ship Collision Avoidance Navigation Concepts, Technologies and Techniques', Journal of Navigation, pp. 129-142. doi: 10.1017/S037346330700447X.
This study provides both a spherical understanding about autonomous ship navigation for collision avoidance (CA) and a theoretical background of the reviewed work. Additionally, the human cognitive abilities and the collision avoidance regulations (COLREGs) for ship navigation are examined together with water based collision avoidance algorithms. The requirements for autonomous ship navigation are addressed in conjunction with the factors influencing ship collision avoidance. Humans are able to appreciate these factors and also perform ship navigation at a satisfactory level, but their critical decisions are highly subjective and can lead to error and potentially, to ship collision. The research for autonomous ship navigation may be grouped into the classical and soft computing based categories. Classical techniques are based on mathematical models and algorithms while soft-computing techniques are based on Artificial Intelligence (AI). The areas of AI for autonomous ship collision avoidance are examined in this paper are evolutionary algorithms, fuzzy logic, expert systems, and neural networks (NN), as well as a combination of them (hybrid system).
Akehurst, D. H., Howells, G., Scheidgen, M. and McDonald-Maier, K. D. (2008) 'C# 3.0 Makes OCL Redundant!', Electronic Communications of the EASST. Technische Universität Berlin, pp. 1-8. doi: 10.14279/tuj.eceasst.9.103.
Other than its "platform independence" the major advantages of OCL over traditional Object Oriented programming languages has been the declarative nature of the language, its powerful navigation facility via the iteration operations, and the availability of tuples as a first class concept. The recent offering from Microsoft of the "Orcas" version of Visual Studio with C# 3.0 and the Linq library provides functionality almost identical to that of OCL. This paper examines and evaluates the controversial thesis that, as a result of C# 3.0, OCL is essentially redundant, having been superseded by the incorporation of its advantageous features into a mainstream programming language.
Akehurst, D. H., Howells, G. and Zschaler, S. (2008) 'OCL: Modularising the Language', Electronic Communications of the EASST. Technische Universität Berlin, pp. 1-20. doi: 10.14279/tuj.eceasst.9.100.95.
The Object Constraint Language (OCL) was originally designed as an 'add-on' to the Unified Modelling Language (UML) in order to facilitate writing textual constraints complementing the graphical specifications. Since its original standardisation many extensions have been added to the language and many more have been proposed. The original structure of the OCL definition has not been formed, however, with a view of extensibility. Still, OCL can be redesigned in such a manner that it becomes easy to extend the language. In this paper we present a modular redefinition of OCL and illustrate how it supports extension. This new approach to the design of OCL enables you to consistently extend or customise OCL to your own needs.
Sheng, W., Howells, G., Fairhurst, M. and Deravi, F. (2007) 'A memetic fingerprint matching algorithm', IEEE Transactions on Information Forensics and Security. Institute Electrical Electronics Engineers, pp. 402-412. doi: 10.1109/TIFS.2007.902681.
Abstract | View in KAR | View Full Text
Minutiae point pattern matching is the most common approach for fingerprint verification. Although many minutiae point pattern matching algorithms have been proposed, reliable automatic fingerprint verification remains as a challenging problem, both with respect to recovering the optimal alignment and the construction of an adequate matching function. In this paper, we develop a memetic fingerprint matching algorithm (MFMA) which aims to identify the optimal or near optimal global matching, between two minutiae sets. Within the MFMA, we first introduce an efficient matching operation to produce an initial population of local alignment configurations by examining local features of minutiae. Then, we devise a hybrid evolutionary procedure by combining the use of the global search functionality of a genetic algorithm with a local improvement operator to search for the optimal or near optimal global alignment. Finally, we define a reliable matching function for fitness computation. The proposed algorithm was evaluated by means of a series of experiments conducted on the FVC2002 database and compared with previous work. Experimental results confirm that the MFMA is an effective and practical matching algorithm for fingerprint verification. The algorithm is faster and more accurate than a traditional genetic-algorithm-based method. It is also more accurate than a number of other methods implemented for comparison, though our method generally requires more computational time in performing fingerprint matching.
Statheros, T., Howells, G. and McDonald-Maier, K. D. (2007) 'Trajectory equilibrium state detection and avoidance algorithm for multi-autonomous potential field mobile robots', Electronics Letters. Institute of Engineering Technology, pp. 799-801. doi: 10.1049/el:20071197.
An exceptionally efficient algorithm for local multi-mobile robot autonomous navigation is presented. The algorithm guides each robot independently although the algorithmic principle is identical for each robot. This approach is a combination of a novel rule-based mathematical algorithm and the virtual force field (VFF) navigational method. The need for the combinational algorithm is due to VFF's inability to guide efficiently multi-autonomous robots in the same environment owing to a trajectory equilibrium state (TES). TES is a new state that dramatically degrades performance of the VFF and is firstly identified and defined within this study. Test results of the novel algorithm yield near-optimum trajectories for the mobile robots.
Akehurst, D. H., Howells, G. and McDonald-Maier, K. D. (2006) 'Implementing Associations: UML 2.0 to Java 5', Journal of Software and Systems Modeling. Springer-Verlag, pp. 3-35. doi: 10.1007/s10270-006-0020-1.
Abstract | View in KAR | View Full Text
A significant current software engineering problem is the conceptual mismatch between the abstract concept of an association as found in modelling languages such as UML and the lower level expressive facilities available in object-oriented languages such as Java. This paper introduces some code generation patterns that aid the production of Java based implementations from UML models. The work is motivated by a project to construct model driven development tools in support of the construction of embedded systems. This involves the specification and implementation of a number of meta-models (or models of languages). Many current UML oriented tools provide code generation facilities, in particular the generation of object-oriented code from class diagrams. However, many of the more complex aspects of class diagrams, such as qualified associations are not supported. In addition, several concepts introduced in UML version 2.0 are also not supported. The aim of the work presented in this paper is to develop a number of code generation patterns that allow us to support the automatic generation of Java code from UML class diagrams that support these new and complex association concepts. These patterns significantly improve the code generation abilities of UML tools, providing a useful automation facility that bridges the gap between the concept of an association and lower level object-oriented programming languages.
Hoque, S., Fairhurst, M., Howells, G. and Deravi, F. (2005) 'Feasibility of Generating Biometric Encryption Keys', Electronics Letters, pp. 309-311. doi: doi:10.1049/el:20057524.
Canuto, A., Fairhurst, M. and Howells, G. (2003) 'Fuzzy Connectives as a Combination Tool in a Hybrid Multi-Neural System', International Journal of Neural Systems. World Scientific Publishing Company, pp. 67-76. doi: 10.1142/s0129065703001455.
The set of fuzzy connectives can be seen as an important combination tool, such as in combining the antecedent sets of the rules, in multi-criteria decision making and in combining the outputs of neural classifiers in a multi-neural system. This papers investigates the performance of some fuzzy combination schemes applied to a multi hybrid neural system which is composed of neural and fuzzy neural networks. An empirical evaluation in a handwritten numeral recognition task is used to investigate the performance of the presented fuzzy methods with some existing combination methods. [ABSTRACT FROM AUTHOR]
Rahman, A. F. R., Howells, G. and Fairhurst, M. (2001) 'A Multiexpert Framework for Character Recognition: A Novel Application of Clifford Networks', IEEE Transactions on Neural Networks, pp. 101-112. doi: 10.1109/72.896799.
Canuto, A., Fairhurst, M. and Howells, G. (2001) 'Improving Artmap Learning through Variable Vigilance', International Journal of Neural Systems. World Scientific Publishing Company, pp. 509-522. doi: 10.1016/s0129-0657(01)00093-x.
Canuto, A., Howells, G. and Fairhurst, M. (2000) 'An investigation of the effects of variable vigilance within the RePART neuro-fuzzy network', Journal of Intelligent & Robotic Systems. Kluwer Academic Publ, pp. 317-334. doi: 10.1023/A:1008159908688.
RePART is a variation of fuzzy ARTMAP to which a reward/punishment concept has been added. Previously, an improvement in performance of RePART had been noted compared with other ARTMAP-based models, such as fuzzy ARTMAP and ARTMAP-IC. In this paper, a wider investigation of RePART performance is described, in which RePART is analysed in relation to a multi-layer perceptron and a RAM-based network in a handwritten numeral recognition task. In the RePART network, a variable vigilance parameter is proposed in order to smooth the poor-generalisation problem of RePART. Firstly, the same vigilance is associated within every neuron general variable vigilance. Secondly, an individual variable vigilance for each neuron - which takes into account its average and Frequency of activation - is used. In a handwritten numeral recognition task using individual variable vigilance, RePART performance improved and demonstrated a performance comparable with alternative architectures such as fuzzy multi-layer perceptron and Radial RAM.
Howells, G., Fairhurst, M. and Rahman, F. (2000) 'An exploration of a new paradigm for weightless RAM-based neural networks', Connection Science. Carfax Publishing, pp. 65-90. doi: 10.1080/095400900116203.
This paper introduces a novel networking strategy for RAM-based neurons which significantly improves the training and recognition performance of such networks whilst maintaining the generalization capabilities achieved in previous network configurations. A number of different architectures are introduced, each using the same underlying principles. Initially, features which are common to all architectures are described, illustrating the basis of the underlying paradigm. Three architectures are then introduced illustrating different techniques of employing the paradigm to meet differing performance specifications. The architectures are described in terms of the structure of the neurons they employ. Details of the various training and recognition algorithms employed by the architectures are supplied in order to present a complete description of the operation of this class of artificial neural network.
Canuto, A., Howells, G. and Fairhurst, M. (2000) 'The use of confidence measures to enhance combination strategies in multi-network neuro-fuzzy systems', Connection Science. Tayor & Francis ltd, pp. 315-331. doi: 10.1080/09540090010014089.
It is well known that substantial improvements can be obtained in difficult pattern recognition problems by combining or integrating the outputs of multiple neural classifiers. This paper analyses the performance of some combination schemes applied to a multi-hybrid neural system which is composed of neural and fuzzy neural networks. Essentially, the combination methods employ different ways to extract valuable information from the output of the experts through the use of confidence (weights) measures of the ensemble members to each class. An empirical evaluation in a handwritten numeral. recognition task is used to investigate the performance of the presented methods in comparison with some existing combination methods.
Canuto, A., Howells, G. and Fairhurst, M. (1999) 'RePART: A modified fuzzy ARTMAP for pattern recognition', Computational Intelligence. Berlin: Wiley Periodicals, pp. 159-168. doi: 10.1007/3-540-48774-3_19.
Fuzzy ARTMAP has been proposed as a neural network architecture for supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors [12]. In this paper, RePART, a proposal for a variant of Fuzzy ARTMAP is analysed. As in ARTMAP-IC, this variant uses distributed code processing and instance counting in order to calculate the set of neurons used to predict untrained data. However, it additionally uses a reward/punishment process and takes into account every neuron in the calculation process..
Howells, G., Fairhurst, M. and Bisset, D. (1995) 'BCN - A Novel Network Architecture for ram-Based Neurons', Pattern Recognition Letters. Elsevier Science Bv, pp. 297-303. doi: 10.1016/0167-8655(94)00098-N.
A new architecture for networks of RAM-based Boolean neurons is presented which, whilst retaining learning and generalisation properties possessed by existing network architectures, allows for arbitrary target patterns for pattern classes with strong convergence properties. The network architecture provides the basis for a pattern recognition system capable of application in a practical environment.
Book sections
Mohamed, E., Sirlantzis, K. and Howells, G. (2019) 'Application of Transfer Learning for Object Detection on Manually Collected Data', in Intelligent Systems and Applications volume 1. Intelligent Systems Conference (IntelliSys) 2019, Springer, pp. 913-931. doi: 10.1007/978-3-030-29516-5_69.
This paper investigates the usage of pre-trained deep learning neural networks for object detection on a manually collected dataset for real-life indoor objects. Availability of object-specific datasets is a great challenge and the unavoidable task of collecting, processing and annotating ground truth data is laborious and time-consuming. In this paper, two famous models (AlexNet and Vgg16) have been evaluated as feature extractors in a Faster R-CNN network. Network models have been trained end-to-end on the collected dataset. The study highlights the poor performance of state of art systems when dealing with small size objects. Modifying the detector design by redesigning systems' anchor boxes might help to tackle this problem. Detector results on the proposed dataset have been collected and compared. In addition, limitations and future work have been discussed.
Yang, Y., Yan, X., Sirlantzis, K. and Howells, G. (2019) 'Application of Sliding Mode Trajectory Tracking Control Design for Two-Wheeled Mobile Robots', in 2019 NASA/ESA Conference on Adaptive Hardware and Systems (AHS). 2019 NASA/ESA Conference on Adaptive Hardware and Systems, IEEE. doi: 10.1109/AHS.2019.00012.
Abstract | View in KAR | View Full Text
A trajectory tracking controller is proposed to drive the wheeled mobile robot (WMR) to follow a predefined trajectory robustly within a finite time under the presence of uncertainties. The two-wheeled mobile robot and tracking error system are modelled by kinematic equations, the stability and reachability of the sliding mode controller are analysed based on the system models. A two-wheeled mobile robot is built by using the STM32F407 (ARM Cortex-M4 microcontroller) board and a MATLAB GUI, and a cooperative real-time operating system are implemented by using C programming language in order to provide convenient system configuration and improve the overall tracking performance. It is demonstrated that the line and circular trajectories are well tracked in simulation and experiment.
Howells, G. and Gillham, M. (2017) 'Attitude Control of Small Probes for De-orbit, Descent and Surface Impact on Airless Bodies Using a Single PWM Thruster', in 2017 6th International Conference on Space Mission Challenges for Information Technology (SMC-IT). 6th International conference on Space Mission Challenges for Information Technology, IEEE. doi: 10.1109/SMC-IT.2017.16.
Abstract | View in KAR | View Full Text
A single thruster attitude and de-orbital control method is proposed, capable of delivering a small spin stabilized probe with payload to the surface of an airless body such as the Moon. Nutation removal, attitude control and fast large angle maneuvers have been demonstrated and shown to be effective using a commercially available single standard cold gas pulse width modulated controlled thruster model. Maximum final impact angle due to drift and residual velocities was found to be less than 5 degrees and the maximum angle of attack to be 4 deg. The conventional 3-axis control would require as many as twelve thrusters requiring a more substantial structure with complex pipework, and a more sophisticated controller. The single thruster concept minimises the mass requirement and thus cost of the mission, making the concept of small networked surface probes for extended science missions more viable. Experiments based on computer simulation have shown that strict design and mission profile requirements can be fulfilled using the single thruster control method.
Hu, Y., Sirlantzis, K. and Howells, G. (2016) 'A study on iris textural correlation using steering kernels', in 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS). 8th IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS 2016), IEEE. doi: 10.1109/BTAS.2016.7791160.
Abstract | View in KAR | View Full Text
Research on iris recognition have observed that iris texture has inherent radial correlation. However, currently, there lacks a deeper insight into iris textural correlation. Few research focus on a quantitative and comprehensive analysis on this correlation. In this paper, we perform a quantitative analysis on iris textural correlation. We employ steering kernels to model the textural correlation in images. We conduct experiments on three benchmark datasets covering iris captures with varying quality. We find that the local textural correlation varies due to local characteristics in iris images, while the general trend of textural correlation goes along the radial direction. Moreover, we demonstrate that the information on iris textural correlation can be utilized to improve iris recognition. We employ this information to produce iris codes. We show that the iris code with the information on textural correlation achieves an improved performance compared to traditional iris codes.
Ye, B. and Howells, G. (2016) 'Integrating Multi-Modal Cloud Features within a Multi-Dimensional Encryption Space', in 2015 Sixth International Conference on Emerging Security Technologies (EST). Sixth International Conference on Emerging Security Technologies, IEEE. doi: 10.1109/EST.2015.12.
The problem of combining multi-modal features which extract from characteristics of given Cloud Computing Servers in the pattern recognition system is well known difficult. This paper addresses a novel efficient technique for normalizing sets of features which are highly multi-modal in nature, so as to allow them to be incorporated from a multi-dimensional feature distribution space. The intend system identify the modes of each distribution and for removing any possible correlation between the feature data to allow to be used in an encryption key generation system.
Gillham, M., Howells, G. and Kelly, S. (2016) 'Assistive trajectories for human-in-the-loop mobile robotic platforms', in 2015 Sixth International Conference on Emerging Security Technologies (EST). Sixth International Conference on Emerging Security Technologies, IEEE. doi: 10.1109/EST.2015.19.
Abstract | View in KAR | View Full Text
Autonomous and semi-autonomous smoothly interruptible trajectories are developed which are highly suitable for application in tele-operated mobile robots, operator on-board military mobile ground platforms, and other mobility assistance platforms. These trajectories will allow a navigational system to provide assistance to the operator in the loop, for purpose built robots or remotely operated platforms. This will allow the platform to function well beyond the line-of-sight of the operator, enabling remote operation inside a building, surveillance, or advanced observations whilst keeping the operator in a safe location. In addition, on-board operators can be assisted to navigate without collision when distracted, or under-fire, or when physically disabled by injury.
Zhai, X., Appiah, K., Ehsan, S., Cheung, W. M., Howells, G., Hu, H., Gu, D. and McDonald-Maier, K. D. (2014) 'Detecting Compromised Programs for Embedded System Applications: 27th International Conference, Lübeck, Germany, February 25-28, 2014. Proceedings', in Architecture of Computing Systems – ARCS 2014 27th International Conference. Architecture of Computing Systems, ARCS 2014, Cham, Switzerland: Springer, pp. 221-232. doi: 10.1007/978-3-319-04891-8_19.
This paper proposes an approach for detecting compromised programs by analysing suitable features from an embedded system. Features used in this paper are the performance variance and actual program counter values of the embedded processor extracted during program execution. "Cycles per Instruction" is used as pre-processing block before the features are classified using a Self-Organizing Map. Experimental results demonstrate the validity of the proposed approach on detecting some common changes such as deletion, insertion and substitution of programs. Overall, correct detection rate for our system is above 90.9% for tested programs.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2013) 'A Multi-algorithmic Colour Iris Recognition System', in Soft Computing Applications Proceedings of the 5th International Workshop Soft Computing Applications (SOFA). Proceedings of the 5th International Workshop Soft Computing Applications (SOFA), Berlin, Germany: Springer, pp. 45-56. doi: 10.1007/978-3-642-33941-7_7.
The reported accuracies of iris recognition systems are generally higher on near infrared images than on colour RGB images. To increase a colour iris recognition system's performance, a possible solution is a multialgorithmic approach with an appropriate fusion mechanism. In the present work, this approach is investigated by fusing three algorithms at the score level to enhance the performance of a colour iris recognition system. The contribution of this paper consists of proposing 2 novel feature extraction methods for colour iris images, one based on a 3-bit encoder of the 8 neighborhood and the other one based on gray level co-occurrence matrix. The third algorithm employed uses the classical Gabor filters and phase encoding for feature extraction. A weighted average is used as a matching score fusion. The efficiency of the proposed iris recognition system is demonstrated on UBIRISv1 dataset.
Tahir, R., Hu, H., Gu, D., McDonald-Maier, K. and Howells, G. (2012) 'A Scheme for the Generation of Strong Cryptographic Key Pairs based on ICMetrics', in 2012 International Conference for Internet Technology and Secured Transactions. The Seventh International Conference for Internet Technology and Secured Transactions (ICITST), IEEE.
This paper presents a scheme for the generation of strong high entropy keys based on ICMetrics. ICMetrics generates the security attributes of the sensor node based on measurable hardware and software characteristics of the integrated circuit. This work is based on key derivation functions to derive cryptographic key pairs from ICMetrics values. The proposed ICMetrics based key derivation function makes use of ICMetrics basis numbers and authentication tokens from the trusted third party to generate high entropy public/private key pairs. The proposed approach makes use of key stretching using SHA-2 and performs multiple iterations of the proposed key derivation function to generate strong high entropy keys of sufficient length, so as to prevent exhaustive search attacks. The novelty of this work lies in the fact that the entire key generation scheme has been designed keeping in mind the construction principles of ICMetrics, which does not store keys but computes these for every session based on ICMetrics value, therefore use of a random value anywhere in the protocol will compromise the purpose of ICMetrics. The proposed scheme generates high entropy key pairs while concealing the original ICMetrics data, such that it is impossible to recover the ICMetrics basis data in the system.
McElroy, B., Gillham, M., Howells, G., Spurgeon, S., Kelly, S., Batchelor, J. and Pepper, M. (2012) 'Highly efficient Localisation utilising Weightless neural systems', in ESANN 2012 The 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Proceedings. 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN, ESANN, pp. 543-548. Available at: https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2012-138.pdf.
Abstract | View in KAR | View Full Text
Efficient localisation is a highly desirable property for an autonomous navigation system. Weightless neural networks offer a real-time approach to robotics applications by reducing hardware and software requirements for pattern recognition techniques. Such networks offer the potential for objects, structures, routes and locations to be easily identified and maps constructed from fused limited sensor data as information becomes available. We show that in the absence of concise and complex information, localisation can be obtained using simple algorithms from data with inherent uncertainties using a combination of Genetic Algorithm techniques applied to a Weightless Neural Architecture.
Aldosary, S. and Howells, G. (2012) 'A Robust Multimodal Biometric Security System Using the Polynomial Curve Technique within Shamir's Secret Sharing Algorithm', in 2012 Third International Conference on Emerging Security Technologies. Third International Conference on Emerging Security Technologies (EST), 2012, IEEE, pp. 66-69. doi: 10.1109/EST.2012.9.
This paper investigates the application of secret sharing technology to allow an encryption key to be derived from multimodal biometric samples. Within the proposed scheme, individual points on a parabolic curve are indirectly derived from individual biometric samples taken from an individual, and Shamir's Secret Sharing algorithm is applied in order to derive the required key. The proposal is robust, in that a pre-defined subset of modalities is required in order to derive the key, rendering the system able to accommodate exception handling for given modalities. The current paper reports preliminary work on how secret sharing techniques may be employed to integrate arbitrary points that may be derived from the actual biometric data.
Harmer, K. and Howells, G. (2012) 'Direct Template-Free Encryption Key Generation from Palm-Veins', in 2012 Third International Conference on Emerging Security Technologies. Third International Conference on Emerging Security Technologies (EST), 2012, IEEE, pp. 70-73. doi: 10.1109/EST.2012.20.
In this paper, an investigation into the feasibility of applying the palm-vein biometric modality within a template-free key generation framework was conducted. In partnership with iCognize GmbH, experiments were conducted on both the raw images and the encoded biometric templates. Although feature analysis suggested difficulties may ensue due to the significant overlapping between genuine and impostor distributions, it was found that the framework still performed well for dataset of 20 subjects. The experiments resulted in both the key reproducibility and key uniqueness rates achieving 100% with considerable effective key lengths. These results are highly encouraging and demonstrate that stable keys can be achieved from poorly separable features.
Kovalchuk, Y., Hu, H., Gu, D., McDonald-Maier, K. D., Newman, D., Kelly, S. and Howells, G. (2012) 'Investigation of Properties of ICmetrics Features', in 2012 Third International Conference on Emerging Security Technologies. 2012 Third International Conference on Emerging Security Technologies, IEEE, pp. 115-120. doi: 10.1109/EST.2012.22.
The ICmetrics technology is concerned with identifying acceptable features in an electronic system's operation for encryption purposes. Ideally, the nature of the features should be identical for all of the systems considered, while the values of these features should allow for unique identification of each of the systems. This paper looks at the properties of the Program Counter of a processor core as a potential ICmetrics feature, and explores how the number of its samples being inputted into the ICmetrics system affects stability of the system's performance.
McConnon, G., Deravi, F., Hoque, S., Sirlantzis, K. and Howells, G. (2012) 'Impact of common ophthalmic disorders on iris segmentation', in 2012 5th IAPR International Conference on Biometrics (ICB). Biometrics (ICB), 2012 5th IAPR International Conference, IEEE, pp. 277-282. doi: 10.1109/ICB.2012.6199820.
As iris recognition moves from constrained indoor and near-infrared systems towards unconstrained on-the-move and at-a-distance systems, possibly using visible light illumination, interest in measurement of the fidelity of the acquired images and their impact on recognition performance has grown. However, the impact of the subject's physiological characteristics on the nature of the acquired images has received little attention. In this paper we catalog a selection of the most common ophthalmic disorders and investigate some of their characteristics including their prevalence and possible impact on recognition performance. The paper also includes an experimental exploration of the effect of such conditions on segmentation of the iris image.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2012) 'Image Enhancement vs Feature Fusion in Colour Iris Recognition', in 2012 Third International Conference on Emerging Security Technologies. Emerging Security Technologies (EST), 2012 Third International Conference, IEEE, pp. 53-57. doi: 10.1109/EST.2012.33.
In iris recognition, most of the research was conducted on operation under near infrared illumination. For an iris recognition system to be deployed on common hardware devices, such as laptops or mobile phones, its ability of working with visible spectrum iris images is necessary. Two of the main possible approaches to cope with noisy images in a colour iris recognition system are either to apply image enhancement techniques or to extract multiple types of features and subsequently to employ an efficient fusion mechanism. The contribution of the present paper consists of comparing which of the two above mentioned approaches is best in both identification and verification scenarios of a colour iris recognition system. The efficiency of the two approaches is demonstrated on UBIRISv1 dataset
Kovalchuk, Y., Hu, H., Gu, D., McDonald-Maier, K. D. and Howells, G. (2012) 'ICmetrics for Low Resource Embedded Systems', in 2012 Third International Conference on Emerging Security Technologies. 2012 Third International Conference on Emerging Security Technologies, IEEE, pp. 121-126. doi: 10.1109/EST.2012.23.
The ICmetrics technology is based on extracting features from digital devices' operation that may be integrated together to generate unique identifiers for each of the devices or create unique profiles that describe the devices' actual behaviour. Any changes in these identifiers (profiles) during consequent devices' operation would signal about a possible safety or security breach within the electronic system. This paper explores the program counter (PC) of a processor core as a potential source for ICmetrics features and discusses several methods of feature values acquisition with the aim to achieve a maximum level of information gain with a minimal impact on a system's performance. The main finding of this study is that while isolated PC values may not always allow to generate a stable identifier (profile) for a device that would distinguish the device from the rest in the considered set, the PC sequences and frequencies in the execution flow may serve as suitable ICmetrics features, which has yet to be tested in complex scenarios.
Gillham, M., McElroy, B., Howells, G., Kelly, S. W., Spurgeon, S. K. and Pepper, M. G. (2012) 'Weightless Neural System Employing Simple Sensor Data for Efficient Real-Time Round-Corner, Junction and Doorway Detection for Autonomous System Path Planning in Smart Robotic Assisted Healthcare Wheelchairs', in 2012 Third International Conference on Emerging Security Technologies. Emerging Security Technologies (EST), 2012 Third International Conference, IEEE, pp. 161-164. doi: 10.1109/EST.2012.21.
Abstract | View in KAR | View Full Text
Human assistive devices need to be effective with real-time assistance in real world situations: powered wheelchair users require reassuring robust support, especially in the area of collision avoidance. However, it is important that the intelligent system does not take away control from the user. The patient must be allowed to provide the intelligence in the system and the assistive technology must be engineered to be sufficiently smart to recognize and accommodate this. Robotic assistance employed in the healthcare arena must therefore emphasize positive support rather than adopting an intrusive role. Weightless Neural Networks are an excellent pattern recognition tool for real-time applications. This paper introduces a technique for look-ahead identification of open doorways and junctions. Simple sensor data in real-time is used to detect open doors with inherent data uncertainties using a technique applied to a Weightless Neural Network Architecture.
McElroy, B., Gillham, M., Howells, G., Kelly, S. W., Spurgeon, S. K. and Pepper, M. G. (2012) 'Real-time sensor data for efficient localisation employing a weightless neural system', in 2012 1st International Conference on Systems and Computer Science (ICSCS). Systems and Computer Science (ICSCS), 2012 1st International Conference on, IEEE, pp. 1-5. doi: 10.1109/IConSCS.2012.6502448.
Abstract | View in KAR | View Full Text
Mobile robotic localisation obtained from simple sensor data potentially offers real-time real-world integration. Computationally highly efficient Weightless Neural Networks, when used for location determination, further enhances performance potential. This paper introduces techniques for the identification of rooms or locations in the absence of complex and succinct information. Using simple floor colour and texture, and room geometrics from ranging data, although inherent uncertainties exist, these limited simple fused real-time sensor data can be easily resolved into a room identification criterion using architectures generated by a Genetic Algorithm technique applied to a Weightless Neural Network Architecture.
Howells, G. and Sirlantzis, K. (2010) 'A Proposal for Integrating Formal Logic and Artificial Neural Systems: A Practical Exploration', in Ao, S.-I. and Gelman, L. (eds) Electronic Engineering and Computing Technology. Netherlands: Springer, pp. 297-308. doi: http://doi.dx.org/10.1007/978-90-481-8776-8_26.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2010) 'On Combining Information from Both Eyes to Cope with Motion Blur in Iris Recognition', in 4th International Workshop on Soft Computing Applications. 4th International Workshop on Soft Computing, IEEE, pp. 175-181. doi: 10.1109/SOFA.2010.5565604.
Iris Recognition has emerged as one of the best biometric authentication techniques in recent years. However, a significant drawback of this biometric modality is the constrained environment in which the user is enrolled and recognized. It typically requires the user to be very cooperative for good quality images to be captured. If this limitation could be effectively addressed, it would be possible to employ iris recognition in environments where images incorporating increased noise and distortions were present whilst maintaining high recognition accuracy. In the present paper, we explore how the effect of image distortions caused by motion blur may be significantly reduced by using iris information from both eyes of the user.
Sudhakaran, S., Cheung, W. M., McDonald-Maier, K. D. and Howells, G. (2010) 'UML based hierarchical state diagram approach for protocol designs', in 2010 2nd Computer Science and Electronic Engineering Conference (CEEC). Computer Science and Electronic Engineering Conference (CEEC), 2010, IEEE, pp. 1-6. doi: 10.1109/CEEC.2010.5606496.
The increasing complexity in the design of protocol based sequential digital systems such as USB3.0 and PCI express (PCIe), is leading to an increased time to market constraint. This paper introduces a UML based visual design approach to address this increased complexity in the design of IP as well as System-on-Chips (SoC). A hardware development method for USB3.0 device using the Unified Modeling Language is explored. It focuses on the conversion of UML structure diagrams and hierarchical state machines into synthesizable hardware description language. A Model Driven Development (MDD) method using UML state diagrams and hierarchical design breakdown approach is used for the development the synthesizable HDL for USB3.0 device IP with more than 20 sequential states
Atah, J. A. and Howells, G. (2009) 'Key Generation in a Voice Based Template Free Biometric Security System', in Fierrez, J., Ortega-Garcia, J., Esposito, A., Drygajlo, A., and Faundez-Zanuy, M. (eds) Biometric ID Management and Multimodal Communication: Joint COST 2101 and 2102 International Conference, BioID MultiComm 2009, Madrid, Spain. Berlin: Springer Verlag, pp. 170-177. doi: 10.1007/978-3-642-04391-8_22.
Howells, G., Selim, H., Fairhurst, M., Deravi, F. and Hoque, S. (2008) 'A Securable Autonomous Generalised Document Model (SAGENT)', in Stoica, A., Arslan, T., Howard, D., Higuchi, T., and El-Rayis, A. O. (eds) 2008 Bio-inspired, Learning and Intelligent Systems for Security. 2008 ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2008), IEEE, pp. 136-141. doi: 10.1109/BLISS.2008.10.
A generalised modelling system for handling multimedia documents is introduced capable of allowing documents authored in differing formats to be efficiently manipulated, compared and analysed. The model represents a document as a secure autonomous object possessing the ability to represent and modify its own meta data whilst not compromising the ideals of maintaining the autonomy of individual document components. The paper presents the model by means of a case study of the existing prototype implementation followed by the detailed presentation of the implementation of the model using Object-Oriented technology showing how the model is able to address the key issues of security, generality and autonomy.
Papoutsis, E., Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2008) 'Effects of Feature Trimming on Encryption Key Stability for an ICmetric System', in Stoica, A., Arslan, T., Howard, D., Higuchi, T., and El-Rayis, A. O. (eds) 2008 Bio-inspired, Learning and Intelligent Systems for Security. 2008 ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2008), IEEE, pp. 87-91. doi: 10.1109/BLISS.2008.19.
The stable reproduction of an encryption key under potentially varying operating conditions is a fundamental requirement of any encryption key generating system. This paper examines aspects of the generation of encryption keys based on measurable features derived from characteristics of investigated electronic system with a view to determining whether such encryption key generation is sufficiently stable. Specifically, it addresses the effect on encryption key stability of removing unstable contributions to the key generation process, a technique known as feature trimming.
Hopkins, A. B., McDonald-Maier, K. D., Papoutsis, E. and Howells, G. (2008) 'Adaptive Online Profiling Hardware for ICmetrics Based Security', in Keymeulen, D., Arslan, T., Seuss, M., Stoica, A., Erdogan, A. T., and Merodio, D. (eds) 2008 NASA/ESA Conference on Adaptive Hardware and Systems. Third NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2008), IEEE, pp. 498-504. doi: 10.1109/AHS.2008.8.
Monitoring circuitry is presented that extracts properties and features from a complex system based on a System-on-Chip based device to support ICmetrics, a novel security concept that aims to uniquely identify and secure an embedded system based on its own behavioural identity. The circuits utilise a novel approach to profiling the instruction fetches and data accesses associated with each of the system's component software tasks so that a representation of their address distributions can be generated online when required. By using profiling circuits with adaptive allocation of counters and by exploiting existing debugging infrastructure circuits, the overall resource requirement is kept sufficiently low for real-world applications. Experimental results are provided to illustrate the nature of features that can be obtained.
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2008) 'An FPGA Based Adaptive Weightless Neural Network Hardware', in Keymeulen, D., Arslan, T., Seuss, M., Stoica, A., Erdogan, A. T., and Merodio, D. (eds) 2008 NASA/ESA Conference on Adaptive Hardware and Systems. Third NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2008), IEEE, pp. 220-227. doi: 10.1109/AHS.2008.19.
Abstract | View in KAR | View Full Text
This paper explores the significant practical difficulties inherent in mapping large artificial neural structures onto digital hardware. Specifically, a class of weightless neural architecture called the Enhanced Probabilistic Convergent Network is examined due to the inherent simplicity of the control algorithms associated with the architecture. The advantages for such an approach follow from the observation that, for many situations for which an intelligent machine requires very fast, unmanned, and uninterrupted responses, a PC-based system is unsuitable especially in electronically harsh and isolated conditions, The target architecture for the design is an FPGA, the Virtex-II pro which is statically and dynamically reconfigurable, enhancing its suitability for an adaptive weightless neural networks. This hardware is tested on a benchmark of unconstrained handwritten numbers from the National Institute of Standards and Technology (NIST), USA.
Wood, S. K., Akehurst, D. H., Howells, G. and McDonald-Maier, K. D. (2008) 'Array OL Descriptions of Repetitive Structures in VHDL', in Schieferdecker, I. and Hartman, A. (eds) Model Driven Architecure, Foundations and Applications - Proceedings. Springer, pp. 137-152.
With the continuing advances in semiconductor technology driving the rise in complexity of electronic embedded systems, there is a demand for the development of high level modelling environments for computer-aided design. The modelling of highly repetitive structures in graphical form poses a particular challenge if a hierarchical approach is not adopted. This paper proposes a mechanism for describing such component structures in a compact form based upon extensions of the Array Oriented Language (Array-OL). An example is given as to how the structure described is subsequently mapped into VHDL code.
Papoutsis, E., Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2008) 'Investigation of Sample Sizes and Correlation in Multi-Cluster Feature Distributions for an Efficient Encryption System', in Keymeulen, D., Arslan, T., Seuss, M., Stoica, A., Erdogan, A. T., and Merodio, D. (eds) 2008 NASA/ESA Conference on Adaptive Hardware and Systems. Third NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2008), IEEE, pp. 409-415. doi: 10.1109/AHS.2008.32.
This paper investigates some practical aspects of the employment of measurable features derived from characteristics of given integrated electronic circuits for the generation of encryption keys pertaining to the circuits, a technique termed ICmetrics. Specifically the paper addresses difficulties introduced by features exhibiting highly diverse distributions, potentially containing many distinct clusters associated with each of the given circuits. For such feature distributions, it is crucial to detect the precise number of clusters associated with each given circuit and the paper discusses the consequentially crucial importance of selecting the appropriate number of samples in order to correctly detect and identify the number of clusters. Moreover, the phenomenon of correlation in multi-cluster features is analyzed and methods of how to successively detect it are presented.
Harmer, K., Howells, G., Sheng, W., Fairhurst, M. and Deravi, F. (2008) 'A Peak-Trough Detection Algorithm based on Momentum', in Li, D. and Deng, G. (eds) 2008 Congress on Image and Signal Processing. 2008 International Congress on Image and Signal Processing (CISP2008), IEEE, pp. 454-458. doi: 10.1109/CISP.2008.704.
This paper presents a simple, yet novel, approach to peak-trough detection using a rudimentary model of Newtonian mechanics. Based on the line-searching technique also employed in artificial neural network technology to determine global minima, the momentum is used to find both peaks and troughs of a signal. This algorithm provides a fast alternative to the traditional techniques, which uses contextual information in order to determine prominent peaks and troughs without requiring smoothing or thresholding.
Bordbar, B., Howells, G., Evans, M. J. and Staikopoulos, A. (2007) 'Model Transformation from OWL-S to BPEL via SiTra', in Akehurst, D. H., Vogel, R., and Paige, R. F. (eds) Model Driven Architecture- Foundations and Applications Third European Conference. Third European Conference on Model Driven Architecture: Foundations and Applications (ECMDA), Berlin, Germany: Springer, pp. 43-58. doi: 10.1007/978-3-540-72901-3.
Although there are a large number of academic and industrial model transformation frameworks available, allowing specification, implementation, maintenance and documentation of model transformations which provide a rich set of functionalities, such tools are inherently complex. In particular, for a newcomer to the field of model transformation and for researchers who are only interested in experimentation and creation of prototypes, the steep learning curve is a significant hurdle. There is thus a clear scope for the creation of model transformation frameworks that are both easy to use and able to conduct complex transformations. Simple Transformer (SiTra) is a model transformation framework, which was originally designed to be a "way in" for the experienced programmer, to start using the concepts of model transformation, and for academic researchers to experiment with the creation of prototypes of implementation of their transformations. The underlying idea of SiTra is to put less focus on the specification language, maintenance and documentation aspects of transformation, by focusing on the implementation of transformations. SiTra makes use of Java for the specification of transformations. This alleviates the need to learn a new specification language or get to grips with a new tool and development environment. SiTra is equipped with a strong transformation engine to execute the transformation behind the scenes. This paper reports on a case study involving transformations from Ontology Web Language-Service (OWL-S) to Business Process Execution Language (BPEL), demonstrating that SiTra can also be used to handle complex and large transformations.
Harmer, K., Howells, G., Sheng, W., Fairhurst, M. and Deravi, F. (2007) 'A Computationally Efficient Fingerprint Segmentation Algorithm using Digital Closed Curves', in Proceedings of the 2007 International Conference on Image Processing, Computer Vision, & Pattern Recognition. 2007 International Conference on Image Processing, Computer Vision and Pattern Recognition (IPCV'07), part of 2007 World Congress in Computer Science, CSREA.
Arslan, T., Haridas, N., Yang, E., Erdogan, A. T., Barton, N., Walton, A. J., Thompson, J. S., Stoica, A., Vladimirova, T., McDonald-Maier, K. D. and others. (2006) 'ESPACENET: A Framework of Evolvable and Reconfigurable Sensor Networks for Aerospace-Based Monitoring and Diagnostics', in First NASA/ESA Conference on Adaptive Hardware and Systems (AHS'06). First NASA/ESA Conference on Adaptive Hardware and Systems, IEEE, pp. 323-329. doi: 10.1109/AHS.2006.34.
There is an increasing need to develop flexible, reconfigurable, and intelligent multi-spacecraft sensing networks for aerospace-based monitoring and diagnostics. Technical advancements in ad hoe networking, MEMS devices, low-power electronics, adaptive and reconfigurable hardware, microspacecraft, and micro-sensors have enabled the design and development of such highly integrated space wireless sensor networks. This paper proposes the framework for an Evolvable Sensor Network Architecture, investigated as part of the ESPACENET project, collocated at the University of Edinburgh, Essex, Kent and Surrey. The aim is to design a flexible and intelligent embedded network of reconfigurable piconodes optimised by a hierarchical multi-objective algorithm. Although the project is targeted at aerospace applications, the same intelligent network can be used for many earth bound applications such as environmental and medical diagnostics.
Howells, G., Papoutsis, E. and McDonald-Maier, K. D. (2006) 'Novel Techniques for Ensuring Secure Communications for Distributed Low Power Devices', in First NASA/ESA Conference on Adaptive Hardware and Systems (AHS'06). First NASA/ESA Conference on Adaptive Hardware and Systems, IEEE, pp. 343-347. doi: 10.1109/AHS.2006.52.
This paper explores effective algorithms for managing the distributed processing and secure data transfer environment present within the network of satellite nodes using advanced mathematical techniques based on encryption methods. Security is enhanced via encryption techniques based on keys, which are based on unique properties of the individual nodes within the network. This will serve both to encrypt data within the network as well as to validate the initiator node of a message.
Howells, W., Selim, H., Hoque, S., Fairhurst, M. and Deravi, F. (2001) 'The Autonomous Document Object (ADO) Model', in Proceedings of Sixth International Conference on Document Analysis and Recognition. Int Conf on Document Analysis and Rec. (ICDAR2001), IEEE, pp. 977-981. doi: 10.1109/ICDAR.2001.953931.
Abstract: A novel strategy for the representation and manipulation of multimedia documents is introduced. The model allows such documents to be treated as autonomous entities capable of representing and modifying their own internal structures. The model is sufficiently flexible as to allow any given arbitrary document format and any programming language to be incorporated within its implementation.
Canuto, A., Howells, G. and Fairhurst, M. (1999) 'Fuzzy multi-layer perceptron for binary pattern recognition', in Seventh International Conference on Image Processing And Its Applications, 1999. 7th IEE Conference on Image Processing and its Applications (IPA99), IEEE, pp. 260-264. doi: 10.1049/cp:19990323.
This paper presents a modified fuzzy Multilayer Perceptron model which uses, as a basis, the implementation developed in (Pal and Mitra, (9)). The proposed model uses different parameters in the calculation of a fuzzy desired output vector to (Pal and Mitra (9)) as well as adding an ambiguity parameter to the updating equation in order to take into account the degree of ambiguity of an input pattern during the learning phase.
Sirlantzis, K., Howells, G. and Paschalakis, S. (1999) 'A functional neural network prototype for multidimensional data analysis', in Seventh International Conference on Image Processing And Its Applications, 1999. 7th IEE Conference on Image Processing and its Applications (IPA99), IEEE, pp. 98-102. doi: 10.1049/cp:19990289.
Artificial neural networks present a powerful tool to analyse complex systems. They have been long used to tackle the difficulties of image analysis and interpretation with applications ranging from character recognition (Howells et al. 1996) to colour image processing (Howells et al. 1997). This paper presents a novel approach which exploits the generality of expressions available in the area of constructive type theory and its potential for the production of guaranteed bug free, provably correct software to develop a working neural network prototype. To illustrate the possible applications of our work we present results from two examples arising from co-operation with the Dover Harbour Board.
Howells, G., Bisset, D. and Fairhurst, M. (1998) 'A New Paradigm for RAM-based Neural Networks', in Austin, J. (ed.) RAM-based Neural Networks. World Scientific. doi: 10.1142/9789812816849_0013.
Howells, G., Bisset, D. and Fairhurst, M. (1998) 'A Framework for Reasoning about RAM-based Neural Networks for Image Analysis Applications', in Austin, J. (ed.) RAM-based Neural Networks. World Scientific. doi: 10.1142/9789812816849_0007.
Howells, G., Allgrove, C. and Fairhurst, M. (1997) 'Binary Image Enhancement by Segmentation Analysis', in 1997 Sixth International Conference on Image Processing and Its Applications. Sixth IEE International Conference on Image Processing and its Applications (IPA), IEEE. doi: 10.1049/cp:19970995.
This paper addresses the problem of the enhancement of images of handwritten bank cheques in order to facilitate their automatic processing by machine. The paper focuses on the detection and removal of additional image noise introduced to the original image through overprinting of paying-in confirmation stamps commonly placed on the cheque by banks within the United Kingdom. The removal of such stamp imprints is essential if satisfactory performance in legal and courtesy amount recognition is to be achieved by the subsequent handwritten character recognition software.
Howells, G., Fairhurst, M. and Bisset, D. (1996) 'Novel RAM-based neural networks for object recognition', in Solomon, S. S., Batchelor, B. G., and Waltz, F. M. (eds) Machine Vision Applications, Architectures, and Systems Integration V. Conference on Machine Vision Applications, Architectures, and Systems Integration V, SPIE, pp. 50-57. doi: 10.1117/12.257276.
This paper introduces a novel networking strategy for RAM-based Neurons which significantly improves the training and recognition performance of such networks whilst maintaining the generalisation capabilities achieved in previous network configurations. A number of different architectures are introduced each using the same underlying principles. Initially, features which are common to all architectures are described illustrating the basis of the underlying paradigm. Three architectures are then introduced illustrating different techniques for employing the paradigm to meet differing performance specifications. The architectures are described in terms of the structure of the neurons they employ. Greater detail of the various training and recognition algorithms employed by the architectures may be found in the referenced papers.
Howells, G., Fairhurst, M. and Bisset, D. (1995) 'GCN: The Generalised Convergent Network', in Fifth International Conference on Image Processing and its Applications, 1995. Fifth IEE International Conference on Image Processing and its Applications, IEEE. doi: 10.1049/cp:19950735.
A new architecture for networks of RAM-based Boolean neurons is presented which, whilst retaining learning and generalisation properties possessed by existing network architectures, allows for a regular treatment of specialisation and generalisation with strong convergence properties. The network architecture provides the basis for a pattern recognition system capable of application in a practical environment.
Hanna, K. and Howells, G. (1994) 'Parallel Theorem Proving', in Runciman, C. and Wakeling, D. (eds) Applications of Functional Programming. UCL Press, pp. 221-235.
Hanna, K. and Howells, G. (1994) 'The Veritas Proof Assistant', in Runciman, C. and Wakeling, D. (eds) Applications of Functional Programming. UCL Press, pp. 125-204.
Hanna, K., Daeche, N. and Howells, G. (1992) 'Implementation of the Veritas Design Logic', in International Conference On Theorem Provers in Circuit Design : Theory, Practice And Experience. International Conference On Theorem Provers in Circuit Design : Theory, Practice And Experience, Nijmegen, Netherlands: Elsevier Science, pp. 77-94. Available at: https://dl.acm.org/citation.cfm?id=672785.
Veritas is a design logic that provides dependent types and subtypes. It is implemented within the functional programming language Haskell. Interesting aspects of this implementation, in particular those relating to dependent types, to the representation of terms and signatures, to syntactic variants (controlled by attributes) and to a concrete notation for derivations are discussed.
Conference or workshop items
Mohamed, E., Sirlantzis, K. and Howells, G. (2022) 'Real-time Powered Wheelchair Assistive Navigation System Based on Intelligent Semantic Segmentation for Visually Impaired Users', in. 2022 IEEE 5th International Conference on Image Processing Applications and Systems, IEEE. doi: 10.1109/ipas55744.2022.10053051.
People with movement disabilities may find powered wheelchair driving a challenging task due to their comorbidities. Certain visually impaired persons with mobility disabilities are not prescribed a powered wheelchair because of their sight condition. However, powered wheelchairs are essential to the majority of these disabled users for commuting and social interaction. It is vital for their independence and wellbeing. In this paper, we propose to use a semantic segmentation (SS) system based on deep learning algorithms to provide environmental cues and information to visually impaired wheelchair users to aid with the navigation process. The system classifies the objects of the indoor environment and presents the annotated output on a display customised to the user's condition. The user can select a target object, for which the system can display the estimated distance from the current position of the wheelchair. The system runs in real-time, using a depth camera installed on the wheelchair, and it displays the scene in front of the wheelchair with every pixel annotated with distinguishable colour to represent the different components of the environment along with the distance to the target object. Our system has been designed, implemented and deployed on a real powered wheelchair for practical evaluation. The proposed system helped the users to estimate more accurately the distance to the target objects with a relative error of 19.8% and 18.4% for the conditions of a) semi-neglect and b) short-sightedness, respectively, compared to errors of 47.8% and 5.6% without the SS system. In our experiments, healthy participants were put in simulated conditions representing the above visual impairments using instruments commonly used in medical research for this purpose. Finally, our system helps to visualise, on the display, hidden areas of the environment and blind spots that visually impaired users would not be able to see without it.
Dib, J., Sirlantzis, K. and Howells, G. (2022) 'Application of Deep Learning Techniques in Negative Road Anomalies Detection', in. 14th International Joint Conference on Computational Intelligence - ROBOVIS, pp. 475-482. doi: 10.5220/0011336000003332.
Abstract | View in KAR | View Full Text
Negative Road Anomalies (Potholes, cracks, and other road anomalies) have long posed a risk for drivers driving on the road. In this paper, we apply deep learning techniques to implement a YOLO-based (You Only Look Once) network in order to detect and identify potholes in real-time providing a fast and accurate detection and sufficient time for proper safe navigation and avoidance of potholes. This system can be used in conjunction with any existing system and can be mounted to moving platforms such as autonomous vehicles. Our results show that the system is able to reach real-time processing (29.34 frames per second) with a high level of accuracy (mAP of 82.05%) and detection accuracy of 89.75% when mounted onto an Electric-Powered Wheelchair (EPW).
Mohamed, E., Sirlantzis, K. and Howells, G. (2022) 'Analysing the Impact of Vibrations on Smart Wheelchair Systems and Users', in. ICPRAI 2022 - 3rd International Conference on Pattern Recognition and Artificial Intelligence. doi: 10.1007/978-3-031-09037-0_3.
Abstract | View in KAR | View Full Text
Mechanical vibrations due to uneven terrains can significantly impact the accuracy of computer vision systems installed on any moving vehicle. In this study, we investigate the impact of mechanical vibrations induced using artificial bumps in a controlled environment on the performance of smart computer vision systems installed on an Electrical powered Wheelchair (EPW). Besides, the impact of the vibrations on the user's health and comfort is quantified using the vertical acceleration of an Inertial Measurement Unit (IMU) sensor according to the ISO standard 2631. The proposed smart computer vision system is a semantic segmentation based on deep learning for pixels classification that provides environmental cues for visually impaired users to facilitate safe and independent navigation. In addition, it provides the EPW user with the estimated distance to objects of interest. Results show that a high level of vibrations can negatively impact the performance of the computer vision system installed on powered wheelchairs. Also, high levels of whole-body vibrations negatively impact the user's health and comfort.
Yadav, S., Khanna, P. and Howells, G. (2022) 'Device Identification Using Discrete Wavelet Transform', in. 7th International Conference on Engineering and Emerging Technologies (ICEET), IEEE. doi: 10.1109/ICEET53442.2021.9659553.
Abstract | View in KAR | View Full Text
This paper investigates the effectiveness of employing measured hardware features mapped into the frequency domain for devices identification. The technique is to utilize Discrete Wavelet Transform (DWT) coefficients as distinguishing features. The DWT coefficients address the degree of relationship between the investigated features and the wavelet function at different occurrences of time. Therefore, DWT coefficients carry useful temporal information about the transient activity of the investigated wavelet features. We study the impacts of utilizing different wavelet functions (Coiflets, Haar and Symlets) on the performance of the device identification system. This system yields 92.5 % of accuracy using Sym6 wavelet. A comparison is made of the accuracy of wavelet features and raw features with standard classifiers.
Mohamed, E., Sirlantzis, K. and Howells, G. (2021) 'Incorporation Of Rejection Criterion - A Novel Technique For Evaluating Semantic Segmentation Systems', in. 2021 14th International Conference on Human System Interaction (HSI), IEEE. doi: 10.1109/HSI52170.2021.9538787.
Abstract | View in KAR | View Full Text
Semantic segmentation `SS' evaluation metrics are great tools to assess systems' performance in terms of pixels' accuracy and the alignment of segments. Standard metrics ignore pixels' confidence scores which can carry useful information. Pixels' scores represent the level of confidence of the system for assigning class labels to image pixels. However, it has not been utilised by any evaluating metric for semantic segmentation systems. We propose to incorporate pixels' confidence scores with existing metrics to gain better insights into systems' behaviours. Results show the usefulness of the introduced approach to utilise the pixels' scores in the evaluation process. Besides, using pixels' scores thresholding can help to enhance the system performance on a specific task or objects of a particular size.
Yadav, S., Khanna, P. and Howells, G. (2021) 'Robust Device Authentication Using Non-Standard Classification Features', in. International Conference for Internet Technology and Secured Transactions, pp. 136-142. doi: 10.20533/ICITST.2021.0014.
Abstract | View in KAR | View Full Text
This paper investigates the use of novel hardware features derived from the physical and behavioral characteristics of electronic devices to identify such devices uniquely. Importantly, the features examined exhibit non-standard and multimodal distributions which present a significant challenge to model and characterize. Specifically, the potency of four data classification methods is compared whilst employing such characteristics, proposed model Multivariate Gaussian Distribution (MVGD -address multimodality), Logistic Regression (LogR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM). Performance is measured based on its accuracy, precision, recall and f measure. The experimental results reveal that by addressing multimodal features with proposed model Multivariate Gaussian Distribution classifier, the overall performance is better than the other classifiers.
Khanna, P. and Howells, G. (2021) 'Using Dynamic Operational features to Identify Embedded Devices', in. 2021 XXXIVth General Assembly and Scientific Symposium of the International Union of Radio Science (URSI GASS), IEEE. doi: 10.23919/URSIGASS51995.2021.9560513.
Abstract | View in KAR | View Full Text
This paper investigates the use of system memory featuresas the characteristics of simpler embedded devices. TheICmetrics technology is based on the hardware andsoftware features of the systems in order to generate theunique identifiers. Usually memory features are consideredvery volatile as they are considered very unstable usually.But, in this case the memory features are very crucial asthey tell us more about the system function. Hence, thesefeatures were used for analysis and a multivariate gaussianmodel was created and validated by comparing testingsample against the training data with 98% accuracyamongst 6 devices. This confirms the usefulness of thesystem memory features in adding a layer of security to thedevices.
Yang, Y., Yan, X., Sirlantzis, K. and Howells, G. (2021) 'Static Output Feedback Control of a Two-wheeled Inverted Pendulum Using Sliding Mode Technique', in. International Conference on Robotics and Control Systems.
This paper presents a static output feedback sliding mode control method to regulate a two-wheeled inverted pendulum system with considerations of matched and unmatched uncertainties. A sliding surface is designed and the associated sliding motion stability is analysed based on the reduced-order dynamics. A static output sliding mode control law is synthesised to drive the system to the sliding surface and maintain a sliding motion afterwards. The nonlinear bounds on the uncertainties are employed in the stability analysis and control design to improve the robustness. The simulation results demonstrate the effectiveness of the proposed control.
Khanna, P. and Howells, G. (2020) 'A novel cost-effective Pressure Sensor based Smart Car park system', in. XXXIII General Assembly and Scientific Symposium (GASS) of the International Union of Radio Science, IEEE. doi: 10.23919/URSIGASS49373.2020.9232146.
Abstract | View in KAR | View Full Text
With the increase in number of people using vehicles for transportation since last decade, traffic congestion is a major problem that requires to be solved effectively. Smart car park system is considered as one of the strategic solutions to this problem, which involves use of sensors to collect data. This paper proposes a novel low-cost smart car monitoring system to detect number of incoming and outgoing cars in and/or out of the car park using pressure sensors. This system also provides the data for the number of spaces available in the car park. Additionally, the paper also demonstrates the algorithm used to process the data obtained by the sensors to use it as a useful information.
Yanushkevich, S., Stoica, A., Shmerko, V., Howells, G., Crockett, K. and Guest, R. (2020) 'Cognitive Identity Management: Synthetic Data, Risk and Trust', in. 2020 International Joint Conference on Neural Networks (IJCNN), IEEE. doi: 10.1109/IJCNN48605.2020.9207385.
Abstract | View in KAR | View Full Text
Synthetic, or artificial data is used in security applications such as protection of sensitive information, prediction of rare events, and training neural networks. Risk and trust are assessed specifically for a given kind of synthetic data and particular application. In this paper, we consider a more complicated scenario, – biometric-enabled cognitive cognitive biometric-enabled identity management, in which multiple kinds of synthetic data are used in addition to authentic data. For example, authentic biometric traits can be used to train the intelligent tools to identify humans, while synthetic, algorithmically generated data can be used to expand the training set or to model extreme situations. This paper is dedicated to understanding the potential impact of synthetic data on the cognitive checkpoint performance, and risk and trust prediction.
Yanushkevich, S., Howells, G., Crockett, K., O'Shea, J., Oliveira, H., Guest, R. and Shmerko, V. (2020) 'Cognitive Identity Management: Risks, Trust and Decisions using Heterogeneous Sources', in. The First IEEE International Conference on Cognitive Machine Intelligence, IEEE. doi: 10.1109/CogMI48466.2019.00014.
Abstract | View in KAR | View Full Text
This work advocates for cognitive biometric-enabled systems that integrate identity management, risk assessment and trust assessment. The cognitive identity management process is viewed as a multi-state dynamical system, and probabilistic reasoning is used for modeling of this process. This paper describes an approach to design a platform for risk and trust modeling and evaluation in the cognitive identity management built upon processing heterogeneous data including biometrics, other sensory data and digital ID. The core of an approach is the perception-action cycle of each system state. Inference engine is a causal network that uses various uncertainty metrics and reasoning mechanisms including Dempster-Shafer and Dezert- Smarandache beliefs.
Arouna, S., Champagnat, R., Coustaty, M., Falquet, G., Ghadfi, S., Ghamri-Doudane, Y., Gomez-Kramer, P., Howells, G., McDonald-Maier, K. D., Murphy, J. and others. (2019) 'Security and Privacy for the Internet of Things: An Overview of the Project', in. IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2019), IEEE. doi: 10.1109/SMC.2019.8914221.
Abstract | View in KAR | View Full Text
As the adoption of digital technologies expands, it becomes vital to build trust and confidence in the integrity of such technology. The SPIRIT project investigates the proof of concept of employing novel secure and privacy-ensuring techniques in services set-up in the Internet of Things (IoT) environment, aiming to increase the trust of users in IoTbased systems. The proposed system integrates three highly novel technology concepts developed by the consortium partners. Specifically, a technology, termed ICMetrics, for deriving encryption keys directly from the operating characteristics of digital devices; secondly, a technology based on a contentbased signature of user data in order to ensure the integrity of sent data upon arrival; a third technology, termed semantic firewall, which is able to allow or deny the transmission of data derived from an IoT device according to the information contained within the data and the information gathered about the requester.
Oprea, P., Sirlantzis, K., Chatzidimitriadis, S., Doumas, O. and Howells, G. (2019) 'Artificial intelligence for safe assisted driving based on user head movements in robotic wheelchairs', in. 15th Conference on Global Challenges in Assistive Technology: Research, Policy & Practice, IOS Press. Available at: https://aaate2019.eu/aaate-2019-proceedings/.
Abstract | View in KAR | View Full Text
Wheelchairs users don't always have the ability to control a powered wheelchair using a normal joystick due to factors that restrict the use of their arms and hands. For a certain number of these individuals, which still retain mobility of their head, alternative methods have been devised, such as chin-joysticks, head switches or sip-and-puff control. Such solutions can be bulky, cumbersome, unintuitive or simply uncomfortable and taxing for the user. This work presents an alternative head-based drive-control system for wheelchair users.
Mohamed, E., Dib, J., Sirlantzis, K. and Howells, G. (2019) 'Integrating ride dynamics measurements and user comfort assessment to smart robotic wheelchairs', in. 15th Conference on Global Challenges in Assistive Technology: Research, Policy & Practice, IOS Press. Available at: https://aaate2019.eu/aaate-2019-proceedings/.
Abstract | View in KAR | View Full Text
Individuals relying on wheelchairs for mobility are subject to the risk of injury due to their exposure to whole-body vibrations for long periods of time as per ISO 2631-1. Our study evaluates the feasibility of integrating ride dynamics measurements (i.e. vertical accelerations) as expressions of user travel comfort assessment to smart robotic wheelchairs. This will also help to mitigate the injury risk caused by the continuous exposure to vibrations using real time electronic measurement systems in order to ensure that the wheelchair's movement dynamics (acceleration and speed) and the user's comfort is adapted to the surrounding environment, specifically the type of ground surface type, as per the ISO standard mentioned previously.
Murphy, J., Howells, G. and McDonald-Maier, K. D. (2019) 'A Machine Learning Method For Sensor Authentication Using Hidden Markov Models', in. Eighth IEEE International Conference on Emerging Security Technologies, IEEE. doi: 10.1109/EST.2019.8806200.
Abstract | View in KAR | View Full Text
A machine learning method for sensor based authentication is presented. It exploits hidden markov models to generate stable and synthetic probability density functions from variant sensor data. The principle, and novelty, of the new method are presented in detail together with a statistical evaluation. The results show a marked improvement in stability through the use of hidden markov models.
Yadav, S. and Howells, G. (2019) 'Secure device identification using multidimensional mapping', in. Eighth IEEE International Conference on Emerging Security Technologies, New York, NY, USA: IEEE. doi: 10.1109/EST.2019.8806218.
Abstract | View in KAR | View Full Text
In this paper we investigate several potential hardware features from multiple devices for suitability during the employment of a device identification. The generation of stable and unique digital identity from features is challenging in device identification because of the unstable operation environments that implies the features employed are likely to vary under normal operating conditions. To address this, we introduce a novel multi-dimensional key generation technology which maps from multi-dimensional feature space directly to a key space. Furthermore, normalized distributions of features give the necessary data to model the characteristics, from which we derive intra-sample device feature distributions, and correlate the distinct features to generate a secure key to identify the device. Furthermore, to evaluate our experiment, we considerably carried out measurement using the mathematical & statistical modelling.
Baba, S. D., Yadav, S. and Howells, G. (2019) 'SortAlgo-Metrics: Identification of Cloud-Based Server Via a Simple Algorithmic Analysis', in. Eighth IEEE International Conference on Emerging Security Technologies, New York, NY, USA: IEEE. doi: 10.1109/EST.2019.8806214.
Abstract | View in KAR | View Full Text
This paper introduces a novel technique to detect spoof or fake software systems via the generation of a unique digital signature based on a direct analysis of the construction of the system. Specifically, we model a novel mechanism referred to as SortAlgo-Metrics analysis to identify cloud-based servers. Experimentally, we deployed four cloud-based servers to run four sorting algorithms in order to extract features that are employed to perform statistical analysis upon with the aim to obtain their metrics which has further underpin the investigation of their behaviours. The model has been validated by comparing training data and unknown data, and the result has shown server 2-4 have a strong identification with 96% probability, while server 1 with 55%, it is surmised that is could be as the result of insufficient sample data. However, if such a simple model can produce a result with this high probability, this shows that with more complex features and sufficient data pulled from cloud-based servers, SortAlgo-Metrics model could generate a higher degree of basis numbers for ICMetrics technology entropy key generation and other complex systems.
Khalid, A., Saha, S., Bhatt, B., Gu, D., Howells, G. and McDonald-Maier, K. D. (2019) 'FLAG: A Framework for FPGA Based Load Generator in Profinet Communication', in. International Conference on Industry 4.0 and Artificial Intelligence Technologies. Available at: https://inait-conf.org/.
Like other automated system technologies, PROFINET, a real-time Industrial Ethernet Standard has shown increasing level of integration into the present IT Infrastructure. Such vast use of PROFINET can expose the controllers and I/O devices to operate in critical failures when traffic goes unexpectedly higher than normal. Rigorous testing of the running devices then becomes essential and therefore, in this paper, we prototype and design an FPGA based load Generating solution called "FLAG (FPGA based LoAd Generator) for PROFINET based traffic at the desired load configurations such as, bits per second, the number and size of the packets with their Ethertypes and MAC addresses. We have employed, a Zynq-7000 FPGA as our implementation platform for the proposed FLAG framework. The system can easily be deployed and accessed via the web or command line interface for successful load generation. Extensive experiments have been conducted to verify the effectiveness of our proposed solution and the results confirm that the proposed framework is capable to generate precise load at Fast/Gigabit line rate with a defined number of packets.
Murphy, J., Howells, G. and McDonald-Maier, K. D. (2018) 'On Quaternary 1-of-4 ID Generator Circuits', in. IEEE EST 2018, IEEE. doi: 10.1109/AHS.2018.8541477.
Abstract | View in KAR | View Full Text
A quaternary 1-of-4 ID generator circuit is presented. It exploits the properties of quaternary metastability to provide stable n-bit IDs tolerant to the effects of nanoscale process scaling and temperature variations, which is achieved by increasing the margin between threshold voltage and metastability voltage via quaternary metastability. A 128-bit ID generator hardware implementation and electrical evaluation yields an average of 26.6% uniqueness of ID bits and 100% stability rate over a 10?C to 40?C temperature range.
Murphy, J., Howells, G. and McDonald-Maier, K. D. (2017) 'Multi-factor Authentication using Accelerometers for the Internet-of-Things', in. Seventh IEEE International Conference on Emerging Security Technologies, IEEE, pp. 103-107. doi: 10.1109/EST.2017.8090407.
Abstract | View in KAR | View Full Text
Embedded and mobile devices forming part of the Internet-of-Things (IoT) need new authentication technologies and techniques. This requirement is due to the increase in effort and time attackers will use to compromise a device, often remote, based on the possibility of a significant monetary return. This paper proposes exploiting a device's accelerometers in-built functionality to implement multi-factor authentication. An experimental embedded system designed to emulate a typical mobile device is used to implement the ideas and investigated as proof-of-concept.
Stoica, A., Iwashita, Y., Assad, C., Ryoo, M. and Howells, G. (2017) 'A Holistic Approach to Interpreting Human States in Smart Environments Providing High Quality of Life', in. Seventh IEEE International Conference on Emerging Security Technologies. doi: 10.1109/EST.2017.8090412.
Abstract | View in KAR | View Full Text
We formulate a concept of a future smart environment for high quality of life (SEQUAL) that would empower humans to compensate for physical and cognitive disabilities associated with sickness and aging. In SEQUAL the assessment of the state of 'well-being' - from behaviors and biological signals - is holistic, meaning that the estimation of individual's health, emotional condition, activity and wishes, are from the beginning determined in relation to each other and in (individual's own) context, with superior results compared to when estimated independent from each other, as in common practice. Similarly, the prediction of a person's future condition, intentions, future needs, and actions/treatment/interventions are determined holistically. SEQUAL includes robots, mobility systems and assistive devices for physical intervention, as well as remote professional caregivers, family and friends, to provide intelligent assistance and support network, aiming for higher quality of life for both patient and caregiver.
Canoz, V., Gillham, M., Oprea, P., Chaumont, P., Bodin, A., Laux, P., Lebigre, M., Howells, G. and Sirlantzis, K. (2017) 'Embedded hardware for closing the gap between research and industry in the assistive powered wheelchair market', in. IEEE/SICE International Symposium on System Integration (SII 2016), IEEE. doi: 10.1109/SII.2016.7843983.
Abstract | View in KAR | View Full Text
Literature is abound with smart wheelchair platforms of various developments, yet to date there has been little technology find its way to the market place. Many trials and much research has taken place over the last few decades however the end user has benefited precious little. There exists two fundamental difficulties when developing a smart powered wheelchair assistive system, the first is need for the system to be fully compatible with all of the manufacturers, and the second is to produce a technology and business model which is marketable and therefore desirable to the manufacturers. However this requires the researchers to have access to hardware which can be used to develop practical systems which integrate and communicate seamlessly with current manufacturer's wheelchair systems. We present our powered wheelchair system which integrates with 95% of the powered wheelchair controller market; our system allows researchers to access the low level embedded system with more powerful computational devices running sophisticated software enabling rapid development of algorithms and techniques. When they have been evaluated they can be easily ported to the embedded processor for real-time evaluation and clinical trial.
Gillham, M., Howells, G., Pepper, M. G. and Kelly, S. W. (2016) 'Developing Effective Intelligent Assistance for the Powered Wheelchair User', in. Technology for Independence Conference (T4i). doi: 10.15131/shef.data.4256522.
Abstract | View in KAR | View Full Text
This research is working towards developing a pre-production prototype system which can provide a low-cost real-time adjustable and adaptable driving assistance system for powered wheelchair users. Currently we are seeking to obtain information from user joystick input and their driving quality to identify symptoms and make adjustments to the driving assistance system.
Sobhy, M., Batchelor, J. C. and Howells, G. (2016) 'Identification of Transmitting Antennas in Secure Internet of Things Networks', in. Loughborough Antennas and Propagation Conference LAPC16, Loughborough, pp. 1-3. doi: 10.1109/lapc.2016.7807517.
Abstract | View in KAR | View Full Text
Bluetooth and WIFI channels are open to public users and have few security procedures. One security aspect is for a receiver to be able to verify the identity of the transmitter. This paper describes methods of identifying transmitters by the properties of their antennas.
Hu, Y., Sirlantzis, K. and Howells, G. (2015) 'Exploiting stable and discriminative iris weight map for iris recognition under less constrained environment', in. 7th IEEE International Conference on Biometrics: Theory, Applications and Systems. doi: 10.1109/btas.2015.7358759.
Hu, Y., Sirlantzis, K., Howells, G., Nicolas, R. and Rodriguez, P. (2015) 'An online background subtraction algorithm using contiguously weighted linear regression', in. EUSIPCO 2015 - European Signal Processing Conference. Available at: http://www.eusipco2015.org/.
Catley, E., Sirlantzis, K., Howells, G. and Kelly, S. W. (2014) 'Preliminary investigations into human fall verification in static images using the NAO humanoid robot', in. CareTECH.
Hu, Y., Sirlantzis, K. and Howells, G. (2014) 'A Robust Algorithm for Colour Iris Segmentation Based on 1-norm Regression', in. International Joint Conference on Biometrics. doi: 10.1109/btas.2014.6996233.
Catley, E., Sirlantzis, K., Kelly, S. W. and Howells, G. (2014) 'Non-overlapping dual camera fall detection using the NAO humanoid robot', in. 5th International Conference on Emerging Security Technologies, pp. 67-70. doi: 10.1109/est.2014.13.
Abstract | View in KAR | View Full Text
With an aging population and a greater desire for independence, the dangers of falling incidents in the elderly have become particularly pronounced. In light of this, several technologies have been developed with the aim of preventing or monitoring falls. Failing to strike the balance between several factors including reliability, complexity and invasion of privacy has seen prohibitive in the uptake of these systems. Some systems rely on cameras being mounted in all rooms of a user's home while others require being worn 24 hours a day. This paper explores a system using a humanoid NAO robot with dual vertically mounted cameras to perform the task of fall detection.
Haciosman, M., Ye, B. and Howells, G. (2014) 'Protecting and identifiying smartphone apps using ICmetrics', in. 5th International Conference on Emerging Security Technologies. doi: 10.1109/est.2014.28.
Ye, B., Haciosman, M. and Howells, G. (2014) 'Analysis of ICmetrics features requirments in Cloud environment', in. 10th Annual International Conference on Grid and Cloud Computing and Applications.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2013) 'Optimizing 2D Gabor Filters for Iris Recognition', in. 4th International Conference on Emerging Security Technologies (EST 2013), IEEE, pp. 47-50. doi: 10.1109/EST.2013.15.
The randomness and richness present in the iris texture make the 2D Gabor filter bank analysis a suitable technique to be used for iris recognition systems. To accurately characterize complex texture structures using 2D Gabor filters it is necessary to use multiple sets of parameters of this type of filters. This paper proposes a technique of optimizing multiple sets of 2D Gabor filter parameters to gradually enhance the accuracy of an iris recognition system. The proposed methodology is suitable to be applied on both near infrared and visible spectrum iris images. To illustrate the efficiency of the filter bank design technique, UBIRISv1 database was used for benchmarking
Zhai, X., Appiah, K., Ehsan, S., Hu, H., Gu, D., McDonald-Maier, K. D., Cheung, W. M. and Howells, G. (2013) 'Application of ICmetrics for Embedded System Security', in. 4th International Conference on Emerging Security Technologies, IEEE, pp. 89-92. doi: 10.1109/EST.2013.21.
Integrated Circuit Metrics (ICmetrics) technology is concerned with the extraction of measurable features of an embedded system, capable of uniquely identifying the system's behaviour. Any changes in these identifiers (profiles) during consequent devices' operation would signal about a possible safety or security breach within the electronic system. This paper explores the combination of program counter (PC) and Cycles per Instructions (CPI) of a processor core as a potential ICmetrics source for embedded system security. The use of this combination exhibits that while isolated PC values may not always generate a stable identifier (profile) for a device that would distinguish the device from the rest in a considered set, the PC and CPI sequences and frequencies in the execution flow may serve as suitable ICmetrics features.
Zhai, X., Appiah, K., Ehsan, S., Cheung, W. M., Hu, H., Gu, D., McDonald-Maier, K. D. and Howells, G. (2013) 'A Self-Organising Map Based Algorithm for Analysis of ICmetrics Features', in. 4th International Conference on Emerging Security Technologies (EST 2013), IEEE, pp. 93-97. doi: 10.1109/EST.2013.22.
ICmetrics is a new approach that exploits the characteristic and behaviour of an embedded system to obtain a collection of properties and features, which aims to uniquely identify and secure an embedded system based on its own behavioural identity. In this paper, an algorithm based on a self-organising map (SOM) neural network is proposed to extract and analyse the features derived from a processor's performance profile (i.e. average cycles per instruction (CPI)), where the extracted features are used to help finding the main behaviours of the system. The proposed algorithm has been tested with different programs selected from the MiBench benchmark suite, and the results achieved show that it can successfully segment each program into different main phases based on the unique extracted features, which confirms its utility for the ICmetrics technology.
Appiah, K., Zhai, X., Ehsan, S., Cheung, W. M., Hu, H., Gu, D., McDonald-Maier, K. D. and Howells, G. (2013) 'Program Counter as an Integrated Circuit Metrics for Secured Program Identification', in. 4th International Conference on Emerging Security Technologies (EST 2013), IEEE, pp. 98-101. doi: 10.1109/EST.2013.23.
Integrated Circuit Metrics is mainly concerned with the extraction of measurable properties or features of a given hardware device, capable of uniquely identifying the system's behaviour. This paper presents features that can be extracted from software executing on a device and identify the very software in execution. The main contribution of this paper is in two folds. The ability to extract features whiles the software is in execution as well as correctly identifying the software to divulge any tampering or malicious exploitation. Our aim is to use program counter values generated during program execution to train a k-means algorithm optimized for vector quantization, and later use the system to associate program counter values with an application.
Ye, B., Howells, G. and Haciosman, M. (2013) 'Investigation of Properties of ICmetric in Cloud', in. 4th International Conference on Emerging Security Technologies (EST 2013), IEEE, pp. 107-108. doi: 10.1109/EST.2013.36.
This paper investigates some practical aspects of the employment of measurable features derived from characteristics of given Cloud computing servers for the generation of encryption keys pertaining to the servers, a technique termed ICmetric. The ICmetric technology requires identifying the suitable features in a distributed environment for encryption purpose. Ideally, the nature of the features should be identical for all of the systems considered, while the values of these features should allow for unique identification of each of the system servers. This paper looks at the properties of the server behaviors as a potential ICmetric feature, and explores how the number of its samples being inputted into the ICmetric system affects stability of the system's performance.
Ragot, N., Bouzbouz, F., Khemmar, R., Ertaud, J.-Y., Kokosy, A.-M., Labbani-Igbida, O., Sajous, P., Niyonsaba, E., Reguer, D., Hu, H. and others. (2013) 'Enhancing the Autonomy of Disabled Persons: Assistive Technologies Directed by User Feedback', in. 4th International Conference on Emerging Security Technologies (EST 2013), IEEE, pp. 71-74. doi: 10.1109/EST.2013.20.
Europe faces a major and growing healthcare problem due to increase in population, increasing longevity and an aging population with disability. Such dependent, elderly, disabled and vulnerable persons, are concerned since they wish to live at home as long as possible. This aspiration is also shared by national policies and communities across EU. To ensure the optimum care of dependent people, innovative solutions are encouraged to maintain independent life style. This paper outlines two projects, SYSIASS and COALAS, which aim to develop a set of technology based solutions to meet the needs and empower these people by enhancing mobility and communication.
Tahir, R., Hu, H., Gu, D., McDonald-Maier, K. D. and Howells, G. (2013) 'Resilience against Brute Force and Rainbow Table Attacks using Strong ICMetrics Session Key Pairs', in. IEEE. doi: 10.1109/ICCSPA.2013.6487307.
Cryptography has become an essential for providing security in embedded system applications. The employed cryptographic primitives should provide strong protection such that the security of the system is not compromised at any point in the lifecycle of a secure operation. This particularly includes the secure generation and maintenance of cryptographic keys. In general this assumption is difficult to accomplish, since there are attacks that come under this umbrella ranging from brute force attacks on the key to capturing the node to extract the key. In this paper we investigate and analyze ICMetrics and its counterpart scheme referred to as the scheme for the generation of strong high entropy ICMetrics session key pairs. ICMetrics is a key technology that computes the secret key based on hardware/ software properties of a device, thereby providing resilience against node capture attacks, while high entropy key pair generation scheme is employed to strengthen the generated ICMetrics basis number, so as to safeguard the generated strong key pairs from brute force and rainbow table attacks.
Tahir, R., Hu, H., Gu, D., McDonald-Maier, K. D. and Howells, G. (2013) 'A Scheme for the Generation of Strong ICMetrics based Session Key Pairs for Secure Embedded System Applications', in. The First International Conference on Communications, Signal Processing and their applications, IEEE. doi: 10.1109/WAINA.2013.143.
This paper presents a scheme for the generation of strong session based ICMetrics key pairs for security critical embedded system applications. ICMetrics generates the security attributes of the sensor node based on measurable hardware and software characteristics of the integrated circuit. In the proposed scheme a random session ID is assigned by a trusted party to each participating network entity, which remains valid for a communication session. Our work is based on the design of a key derivation function that uses an ICMetrics secret key and a session token assigned by the trusted party to derive strong cryptographic key pairs for each entity. These session tokens also serve the purpose of identification/authentication between the trusted parties and the respective nodes in each network. The main strength of our proposed scheme rests on the randomness feature incorporated via the random session ID's, which makes the generated strong private/public key pair highly resistant against exhaustive search and rainbow table attacks. Our proposed approach makes use of key stretching using random session tokens via SHA-2 and performs multiple iterations of the proposed key derivation function to generate strong high entropy session key pairs of sufficient length. The randomness of the assigned ID's and the session based communication hinders the attacker's ability to launch various sorts of cryptanalytic attacks, thereby making the generated keys very high in entropy. The randomness feature has also been very carefully tuned according to the construction principles of ICMetrics, so that it doesn't affect the original ICMetrics data. The second part of the proposed scheme generates a corresponding public session key by computing the Hermite Normal Form of the high entropy private session key.
Gillham, M., Howells, G., Spurgeon, S. K., Kelly, S. W. and Pepper, M. G. (2013) 'Real-time Doorway Detection and Alignment Determination for Improved Trajectory Generation in Assistive Mobile Robotic Wheelchairs', in. Emerging Security Technologies (EST), 2013 Fourth International Conference on, pp. 62-65.
Abstract | View in KAR | View Full Text
Powered wheelchair users may find operation in enclosed environments such as buildings difficult; a fundamental problem exists: wheelchairs are not much narrower than the doorway they wish to pass through. The ability to detect and pass through doorways represents a major current challenge for automated guided wheelchairs. We utilize a simple doorway pattern recognition technique for fast processing in a real-time system for robotic wheelchair users. We are able to show a 96% detection and identification of 5 individual doorways and an 86% recognition rate of 22 separate approach angles and translations. We conclude that pattern recognition using features obtained from simple constrained infrared ranging sensor data binning can be utilized for fast identification of doorways, and important coarse position and approach angle determination, suitable for real-time trajectory adjustment, representing a significant enhancement in this area.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2013) 'A Novel Iris Clustering Approach Using LAB Color Features', in. 4th IEEE International Symposium on Electrical And Electronics Engineering (ISEEE 2013), IEEE, pp. 1-4. doi: 10.1109/ISEEE.2013.6674362.
Interesting results of color clustering for the iris images in the UBIRISv1 database are presented. The iris colors are characterized by feature vectors with 80 components corresponding to histogram bins computed in the CIELAB color space. The feature extraction is applied to the first session eye images after undergoing an iris segmentation process. An agglomerative hierarchical algorithm is used to organize 1.205 segmented iris images in 8 clusters based on their color content.
Kovalchuk, Y., Howells, G., Hu, H., Gu, D. and McDonald-Maier, K. D. (2012) 'A practical proposal for ensuring the provenance of hardware devices and their safe operation', in. The 7th International IET System Safety Conference, incorporating the Cyber Security Conference, IEEE. doi: 10.1049/cp.2012.1500.
This paper presents a novel technique, termed ICmetrics (Integrated Circuit metrics), that can be used for the purposes of generating encryption keys, electronic signatures, detecting attempts of frauds, or preventing malfunction of hardware components and systems. The ICmetrics technology is based on employment of measurable features derived from characteristics of a given electronic device in order to generate an identifier that uniquely determines or describes the device. Any changes in the identifier during consequent device's operation would signal about a possible safety or security breach within the electronic system. After a detailed overview of the ICmetrics technology and comparing it to the alternative techniques commonly used for securing electronic systems, the paper discusses challenges of developing the technology and brings an example to demonstrate how these issues are being addressed.
Kokosy, A.-M., Floquet, T., Howells, G., Hu, H., Pepper, M. G., Sakel, M. and Donze, C. (2012) 'SYSIASS – an intelligent powered wheelchair', in. First International Conference on Systems and computer Science.
This paper explains the motivations and the goals of the SYSIASS project. This project has three major ambitions: to design intelligent devices for both the assisted navigation of the powered wheelchairs and the secure communication of the data and to design multi-modality human machine interaction. Moreover, the challenge of the project is to take the needs of the users and the constraints that it implies into account at each stage of the project development. The devices developed during the project will be evaluated by the users through the clinical trials.
Cheung, W. M., Abdullah, S., McDonald-Maier, K. D. and Howells, G. (2012) 'Model Driven Development Approach for Effective SOA Communication Performance Analysis', in. UK Electronics Forum.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2012) 'A Visible Light Iris Recognition System using Colour Information', in. 9th IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA 2012), Acta Press. doi: 10.2316/P.2012.778-019.
The iris has been shown to be a highly reliable biometric modality with almost perfect authentication accuracy. However, a classical iris recognition system operates under near infrared illumination, which is a major constraint for a range of applications. In this paper, we propose an iris recognition system which is able to cope with noisy colour iris images by employing image processing techniques together with a Multiple Classifier System to fuse the information from various colour channels. There are two main contributions in the present work: first, we adapt standard iris features, proposed in the literature for near infrared images, to match the characteristics of colour iris images; second, we introduce a robust fusion mechanism to combine the features from various colour channels. With a feature size of only 360 real numbers, the efficiency of the proposed biometric system is demonstrated on the UBIRISv1 dataset for both identification and verification scenarios.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2011) 'A Versatile Iris Segmentation Algorithm', in. 2011 BIOSIG Conference on Biometrics and Security.
Sudhakaran, S., Chung, W., McDonald-Maier, K. D. and Howells, G. (2011) 'Application of UML Diagrams in the Design and Verification of Digital Systems', in. UK Electronics Forum 2011.
McElroy, B. and Howells, G. (2011) 'Improved Adaptive Meta-Network Design Employing Genetic Algorithm Techniques', in. 8th International Conference on Informatics in Control, Automation and Robotics.
McElroy, B. and Howells, G. (2011) 'Neural Network Tuning using Genetic Algorithms for Robot Obstacle Avoidance', in. 14th IASTED International Conference on Artificial Intelligence and Soft Computing.
Radu, P., Sirlantzis, K., Howells, G., Deravi, F. and Hoque, S. (2011) 'Information Fusion for Unconstrained Iris Recognition', in. International Conference on Emerging Security Technologies (EST 2011).
Sudhakaran, S., Chung, W., Howells, G. and McDonald-Maier, K. D. (2010) 'UML Hierarchical State Diagram Approach for Protocol Designs with USB3.0 as an Example', in. 2nd Computer Science and Electronic Engineering Conference (CEEC).
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2010) 'Are Two Eyes Better Than One?', in. International Conference on Emerging Security Technologies (EST 2010).
Sirlantzis, K., Howells, G., Deravi, F., Hoque, S., Radu, P., McConnon, G., Savatier, X., Ertaud, J.-Y., Ragot, N., Dupuis, Y. and others. (2010) 'Nomad Biometric Authentificatin (NOBA): Towards Mobile and Ubiquitous Person Identification', in. International Conference on Emergy Security Technologies (EST 2010).
McElroy, B. and Howells, G. (2010) 'Evaluating the Application of Simple Weightless Networks to Complex Patterns', in. International Conference on Emerging Security Technologies (EST 2010). doi: 10.1109/est.2010.15.
Radu, P., Sirlantzis, K., Howells, G., Hoque, S. and Deravi, F. (2010) 'Can Dual Iris Help with Motion Blur?', in. 4th IEEE Int. Workshop on Soft Computing Applications (SOFA2010).
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2010) 'Model Learning from Weights by the Adaptive Enhanced Probabilistic Convergent Network', in. 18th European Symposium on Artificial Neural Networks (ESANN).
McConnon, G., Deravi, F., Hoque, S., Howells, G. and Sirlantzis, K. (2010) 'A Novel Interactive Biometric Passport Photograph Alignment System', in. 18th European Symposium on Artificial Neural Networks (ESANN).
Chung, W., Howells, G., McDonald-Maier, K. D., Hopkins, A. B., Arslan, T. and Derrick, J. (2010) 'Novel Model Driven Design and Validation Techniques for Adaptive Cruise Control', in. 1st Workshop on Model Based Engineering for Embedded Systems Design.
McConnon, G., Deravi, F., Hoque, S., Sirlantzis, K. and Howells, G. (2010) 'A Survey of Point-Source Specular Reflections in Noisy Iris Images', in. Emerging Security Technologies (EST), 2010 International Conference, pp. 13-17. doi: doi:10.1109/EST.2010.33.
This paper presents an examination of a selection of images taken from the UBIRIS.v2 dataset to explore the characteristics of point-source reflections present in the images. These reflections were some of the most commonly found sources of noise in iris images acquired under visual wavelength light and clearly impact the accuracy of iris recognition systems. The spatial and intensity distributions of these reflections is studied and results are presented that can be used to model their behaviour. This information can be helpful for developing more accurate iris synthesis techniques and for the study of iris image focus assessment as well as developing better matching algorithms for iris recognition.
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2009) 'An Identification System for Fingerprints utilising Enhanced Probabilistic Convergent Network', in. Fourth NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2009).
Wood, S. K., Akehurst, D. H., Howells, G. and McDonald-Maier, K. D. (2009) 'Verification of Generated VHDL Systems', in. Fifth UK Embedded Forum.
Papoutsis, E., Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2009) 'Ensuring Secure Healthcare Communications via ICmetric based Encryption on Unseen Devices', in. 2009 ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2009).
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2009) 'A Fingerprint Identification System Using Adaptive FPGA - Based Enhanced Probabilistic Convergent Network', in. Fourth NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2009).
Papoutsis, E., Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2009) 'Integrating Feature Values for Key Generation in an ICmetric System', in. Fourth NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2009). doi: 10.1109/ahs.2009.30.
Howells, G., Bordbar, B. and Akehurst, D. H. (2009) 'Model Transformation using Adaptive Systems', in. Fourth International Conference on Software and Data Technologies (ICSOFT 2009), INSTICC Press, pp. 133-138.
Howells, G. and Sirlantzis, K. (2009) 'A Framework for the Merger and Practical Exploitation of Formal Logic and Artificial Neural Networks', in Ao, S. L., Gelman, L., Hukins, D. W., Hunter, A., and Korsunsky, A. (eds). World Congress on Engineering, International Association for Engineers, pp. 19-24.
The assimilation of formal logic into the domain of Software Engineering offers the possibility of enormous benefits in terms of software reliability and verifiability. To date, however, the integration of such techniques has proved difficult since they involve a significantly increased burden on the programmer in meeting the demands of the formal mechanisms being employed. The current paper investigates the advantages which may be gained by the software development process with the introduction of Artificial Neural Network technology into a formal software development system. Essentially, the adaptive artificial neural network model is employed to refine an existing formal software model in order to produce increasingly better approximations to a given solution. Each approximation is itself a valid formal system whose precise behaviour may be formally determined. The paper introduces a framework by which a programmer may define a system possessing the abstract structure of a traditional neural network but whose internal structures are taken from the formal mathematical domain of Constructive Type Theory. The system will then refine itself to produce successive approximations to a desired goal based on data presented to it. An example is presented addressing a problem domain which has previously proved difficult to model. Although the example presented is necessarily limited, it does provide an insight into the potential advantages of merging formal logic with artificial neural systems.
Statheros, T., Howells, G., Lorrentz, P. and McDonald-Maier, K. D. (2009) 'A Novel Potential Field Algorithm and an Intelligent Multi-Classifier for the Automated Control and Guidance System (ACOS)', in Filipe, J., Andrade-Cetto, J., and Ferrier, J.-L. (eds). Sixth International Conference on Informatics in Control, Automation and Robotics (ICINCO 2009), INSTICC Press, pp. 337-342.
Atah, J. A. and Howells, G. (2009) 'Integrating Revocable Biometrics within a Voice Based Template-Free Biometric Security System', in. 2009 International Conference on Image Processing, Computer Vision and Pattern Recognition (IPCV 2009), part of World Congress in Computer Science, Computer Engineering and Applied Computing.
Atah, J. A. and Howells, G. (2009) 'Mapping of Information in Voice Features for Use in an Efficient Template-Free Biometric Security System', in. International Conference on Information Security and Privacy (ISP-09).
Atah, J. A. and Howells, G. (2009) 'Analysis of Binary Information in a Voice Based Template-Free Biometric Security System', in. ADIS Multi-Conference on Computer Science and Information Systems (MCCSIS 2009).
Sirlantzis, K., Howells, G. and Gherman, B. (2009) 'Novel Modular Weightless Neural Architectures for Biometrics-Based Recognition', in. 17th European Symposium on Artificial Neural Networks (ESANN 2009).
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2009) 'FPGA-Based Enhanced Probabilistic Convergent Weightless Network for Human Iris Recognition', in. 17th European Conference on Artificial Neutal Networks (ESANN 2009).
Howells, G., Batchelor, J. C., Spurgeon, S. K., McDonald-Maier, K. D. and Hopkins, A. B. (2009) 'Novel Secure Communications Technologies Supporting Remote Healthcare', in. IET Conference on Assisted Living. doi: 10.1049/ic.2009.0044.
Howells, G. and Sirlantzis, K. (2008) 'Improving Robotic System Robustness via a Generalised Formal Artificial Neural System', in. 2008 ECSIS Symposium on Learning and Adaptive Behaviour in Robotic Systems (LAB-RS 2008), IEEE Computer Society, pp. 23-28. doi: 10.1109/lab-rs.2008.12.
A major concern for robotic guidance systems is that a temporary or permanent failure of a given sensor within the system will erroneously trigger a potential system failure state. This paper introduces a generalised artificial neural system which is capable of addressing such problems by means of the inclusion of a weight value able to incorporate a distinct failure value. This will serve to significantly improve the performance and reliability of the guidance system
Hoque, S., Fairhurst, M. and Howells, G. (2008) 'Evaluating Biometric Encryption Key Generation using Handwritten Signatures', in. 2008 ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2008), IEEE Computer Socieity, pp. 17-22. doi: 10.1109/bliss.2008.8.
In traditional cryptosystems, user authentication is based on the possession of secret keys/tokens. Such keys can be forgotten, lost, stolen, or may be illegally shared, but an ability to relate a ctyptographic key to biometric data can enhance the trustworthiness of a system. In this paper, we demonstrate how biometric keys can be generated directly from live biometrics, under certain conditions, by partitioning feature space into subspaces and partitioning these into cells, where each cell subspace contributes to the overall key generated. We evaluate the proposed scheme on real biometric data, representing both genuine samples and attempted imitations. Experimental results then demonstrate the extent to which the proposed technique can be implemented reliably in possible practical scenarios
Harmer, K., Howells, G., Sheng, W., Fairhurst, M. and Deravi, F. (2008) 'Fuzzy Vault Fingerprint Smartcard Implementation using an Orientation-Based Feature Vector', in. 2008 ECSIS Symposium on Bio-inspired, Learning and Intelligent Systems for Security (BLISS 2008#). doi: 10.1109/bliss.2008.20.
Hopkins, A. B., Sartain, P., McDonald-Maier, K. D. and Howells, G. (2008) 'Towards Embedded Artificial Intelligence Based Security for Computer Systems', in. 2008 ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2008). doi: 10.1109/bliss.2008.13.
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2008) 'An Analysis of Hardware Configurations for an Adaptive Weightless Neural Network', in Ao, S., Gelman, L., Hukins, D. W., Hunter, A., and Korsunsky, A. (eds). World Congress on Engineering 2008, INT ASSOC ENGINEERS-IAENG, UNIT1, 1-F, 37-39 HUNG TO ROAD, KWUN TONG, HONG KONG, 00000, PEOPLES R CHINA: IAE, pp. 66-71.
This paper examines the potential offered by adaptive hardware configurations of a class of weightless neural architecture called the Enhanced Probabilistic Convergent Network targeted on a Virtex-II pro FPGA which is re configurable. The reconfiguration and adaptive capability of the Enhanced Probabilistic Convergent Network is a highly adaptive architecture offering a very fast, automated uninterrupted responses in potentially electronically harsh and isolated conditions. The hardware architecture is tested on a benchmark of unconstrained handwritten numerals from the Centre of Excellence for Document Analysis and Recognition.
Akehurst, D. H., Howells, G., Boardbar, B. and McDonald-Maier, K. D. (2008) 'Maths vs (Meta) Modelling: Are we Reinventing the Wheel?', in. Third International Conference on Software and Data Technologies (ICSOFT).
Atah, J. A. and Howells, G. (2008) 'Score Normalisation of Voice Features for Template-Free Biometric Encryption', in. International Conference on Artificial Intelligence and Pattern Recognition (AIPR-08), part of 2008 MultiConference (MULTICONF-08) in Computer Science.
Sartain, P., Hopkins, A. B., McDonald-Maier, K. D. and Howells, G. (2008) 'A Framework for Self-Diagnosis and Condition Monitoring of Embedded Hardware using a SOM-Based Classifier', in. Third NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2008).
This paper presents a system level framework for System-on-Chip (SoC) based embedded devices that may include adaptive and reconfigurable elements. Cut-rent development support and debugging solutions are highly dependant On off-line post-mortem style inspection, and even those that utilise tracing for real-time and schedule-critical systems rely v on external development tools and environments. This new framework introduces an AI-lead infrastructure that A as the potential to reduce much of the development effort while complementing existing debugging circuits. Specifically this paper investigates how to use a Kohonen self-organising-map (SOM) as a classifier, and shows a preliminary investigation into how to determine the quality of a map after training. This classifier is a first step in diagnosing failure, degradation and anomalies (i.e. provides condition monitoring) in an embedded system from a system level point of view, and in the larger task of self-diagnosis of an embedded system.
Sheng, W., Harmer, K., Howells, G., Fairhurst, M. and Deravi, F. (2008) 'A Genetic Algorithm for Fingerprint Matching based on an Integrated Measure', in. IEEE Congress on Evolutionary Computation (IEEE CEC 2008), part of 2008 IEEE World Congress on Computational Intelligence (WCCI 2008). doi: 10.1109/cec.2008.4630907.
In this paper, we develop a fingerprint matching method which operates by first introducing an integrated measure, which combines two different matching criteria based on heterogeneous features. We then devise a genetically guided algorithm to optimise the integrated measure for simultaneous fingerprint alignment and verification. The proposed method is evaluated through experiments conducted on two public domain collections of fingerprint images and compared with related work, with very encouraging results
Akehurst, D. H., Zschaler, S. and Howells, G. (2008) 'OCL: Modularising the Language', in Margaria, T., Padberg, J., and Taentzer, G. (eds). Workshop on Ocl4All: Modelling Systems with OCL, part of 10th International Conference on Model Driven Engineering Languages and Systems (MODELS/UML), Berlin, Germany: Technische Universität Berlin, pp. 176-181.
The Object Constraint Language (OCL) was originally designed as an 'add-on' to the Unified Modelling Language (UML) in order to facilitate writing textual constraints complementing the graphical specifications. Since its original standardisation many extensions have been added to the language and many more have been proposed. The original structure of the OCL definition has not been formed, however, with a view of extensibility. Still, OCL can be redesigned in such a manner that it becomes easy to extend the language. In this paper we present a modular redefinition of OCL and illustrate how it supports extension. This new approach to the design of OCL enables you to consistently extend or customise OCL to your own needs.
Wood, S. K., Akehurst, D. H., Howells, G. and McDonald-Maier, K. D. (2007) 'Mapping the Design of Repetitive Structures onto VHDL', in. International Workshop on MODEASY, in conjunction with Forum on Specificatin and Design Languages (FDL 07).
Akehurst, D. H., Wood, S. K., Howells, G. and McDonald-Maier, K. D. (2007) 'Towards a Twofold Approach to the Verification of Generated VHDL Systems', in. International Workshop on MODEASY, in conjunction with Forum on Specificatin and Design Languages (FDL 07).
The rise of Model Driven Development, Domain Specific Languages and Generative Programming as new techniques for systems and software engineering means that the actual code that is compiled and executed is no longer written by a human, it is generated by a tool. To give confidence that the desired system has been generated, it is necessary to provide a successful means to verify the generated code. This paper proposes a twofold approach to verification, drawing on techniques from both the testing and formal approaches to verification. The concepts are discussed in the context of generating VHDL code from a UML State Machine.
Hopkins, A. B., McDonald-Maier, K. D., Papoutsis, E. and Howells, G. (2007) 'Ensuring Data Integrity via ICmetrics based Security Infrastructure', in. NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2007). doi: 10.1109/ahs.2007.48.
Sheng, W., Harmer, K., Howells, G., Fairhurst, M. and Deravi, F. (2007) 'Fingerprint Matching with an Evolutionary Approach', in. Second International Conference on Biometrics (ICB 2007).
Papoutsis, E., Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2007) 'Integrating Multi-Modal Circuit Features within an Efficient Encryption System', in. Third International Symposium on Information Assurance and Security (IAS 2007). doi: 10.1109/isias.2007.4299755.
Papoutsis, E., Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2007) 'Key Generation for Secure Inter-Satellite Communication', in. NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2007). doi: 10.1109/AHS.2007.67.
This paper addresses issues relating to the generation of secure encryption keys for use in inter-satellite communications operating in a low power environment. It introduces techniques which possess the potential to generate encryption keys based on properties or features directly associated with the actual satellites and thus removing the necessity for key storage. This research investigates constraints associated with ensuring secure inter-satellite communications for satellite constellations. The need for data sent to and from satellites to be secure and verified is substantial. Security can be improved by using encryption techniques based on keys, which are based on unique properties of the individual nodes within the satellite network. This will serve both to minimize the need for key sharing as well as to validate the initiator node of a message.
Howells, G., McDonald-Maier, K. D., Binzegger, T. and Young, M. (2007) 'MAVIS: A Secure Formal Computational Paradigm based on the Mammalian Visual System', in. ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2007). doi: 10.1109/bliss.2007.13.
Howells, G., Papoutsis, E., Hopkins, A. B. and McDonald-Maier, K. D. (2007) 'Normalizing Discrete Circuit Features with Statistically Independent Values for Incorporation within a Highly Secure Encryption System', in. NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2007). doi: 10.1109/AHS.2007.78.
Protecting hardware devices from unwanted software attacks is a current area of major security concern. Coupled with the need to secure and verify data sent to and from such devices, the need to supply systems capable of uniquely identifying and securing hardware devices is considerable and imminent. This paper introduces techniques which possess the potential to generate unique identifying codes for given hardware devices based on measurable quantities or features associated with the given hardware and software configurations executing upon it. The techniques are investigated by considering abstract properties in order to validate primarily the feature normalization techniques employed prior to the code generation phase which allows features with highly variable distributions, and whose component values are independent of each other, to be employed within the code generation system.
Howells, G., Howlett, R. and McDonald-Maier, K. D. (2007) 'TRICODA: Complex Data Analysis and Condition Monitoring based on Neural Network Models', in. NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2007). doi: 10.1109/AHS.2007.107.
The increasing availability of advanced computer equipment and sensory systems often results in large volumes of data, with subsequent difficulties in efficient analysis and real-time processing. The Tricoda initiative focuses on tools and techniques to aid in the automated analysis of large, complex systems and the data sets they generate. A novel general-purpose modelling system is employed based on the combination of a number of artificial intelligence based and conventional techniques, all integrated with a novel formal framework based on Constructive Type Theory. The tool is evaluated for the solution of a data analysis and condition monitoring case study focusing on an automotive application, specifically the automotive sector for engine control.
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2007) 'Design and Analysis of a Novel Weightless Artificial Neural Based Multi-Classifier', in. International Conference of Computational Intelligence and Intelligent Systems (ICCIIS 2007), part of World Conference on Engineering 2007 (WCE 2007).
Sirlantzis, K., Howells, G., Lloyd-Jones, T. J. and Fairhurst, M. (2007) 'A Multi-Classifier Approach to Modelling Human and Automatic Visual Cognition', in. ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2007). doi: 10.1109/bliss.2007.12.
Harmer, K., Howells, G., Sheng, W., Fairhurst, M. and Deravi, F. (2007) 'A Novel Level-Independent Fingerprint Segmentation Algorithm based on Fourier Energy', in. 2007 International Conference on Image Processing, Computer Vision and Pattern Recognition (IPCV'07), part of 2007 World Congress in Computer Science.
Sartain, P., Hopkins, A. B., McDonald-Maier, K. D. and Howells, G. (2007) 'A System Level Framework for Monitoring and Self Diagnosis in ESPACENET', in. NASA/ESA Conference on Adaptive Hardware and Systems (AHS-2007). doi: 10.1109/ahs.2007.18.
Akehurst, D. H., Howells, G., Scheidgen, M. and McDonald-Maier, K. D. (2007) 'C# 3.0 makes OCL Redundant', in. Workshop on Ocl4All: Modelling Systems with OCL, part of 10th International Conference on Model Driven Engineering Languages and Systems (MODELS/UML).
Hopkins, A. B., Howells, G., McDonald-Maier, K. D., Erdogan, A. T. and Arslan, T. (2007) 'I2S3 The Integrated Intelligent Secure Sensor Systems Project', in. ECSIS Symposium on Bio-Inspired, Learning and Intelligent Systems for Security (BLISS 2007). doi: 10.1109/bliss.2007.8.
Lorrentz, P., Howells, G. and McDonald-Maier, K. D. (2006) 'Enhanced PCN: The Probabilistic Convergent Network', in. Sixth International Conference on Recent Advances in Soft Computing (RASC).
Nnolim, U., Khola, S., Howells, G. and McDonald-Maier, K. D. (2006) 'A VHDL based Implementation of Generalized Convergent Network using Field Programmable Gate Array', in. International Conference on Recent Advances in Soft Computing, RASC 2006, IEE, ENNS, EUSPLAT, IAPR.
Howells, G., Khola, S., Statheros, T. and McDonald-Maier, K. D. (2006) 'An Intelligent Fast-Learning Multi-Classifier System based on Weightless Artificial Neural Architectures', in. Sixth International Conference on Recent Advances in Soft Computing (RASC).
Statheros, T., Defoort, M., Khola, S., McDonald-Maier, K. D., Howells, G., Kokosy, A.-M., Palos, J., Perruquetti, W., Floquet, T. and Boulinguez, D. (2006) 'Automated Control and Guidance System (ACOS): An Overview', in. Sixth International Conference on Recent Advances in Soft Computing (RASC).
Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2006) 'Ensuring Data Integrity and Hardware Identity using ICmetrics', in. ECSIS Symposium on Intelligent Systems for Defense and ecurity (ISDS), part of 4th European Conference on Intelligent Systems and Technologies.
Arslan, T., Haridas, N., Yang, E., Erdogan, A. T., Barton, N., Walton, A. J., Thompson, J. S., Stoica, A., Vladimirova, T., McDonald-Maier, K. D. and others. (2006) 'ESPACENET: A Joint Project for Evolvable and Reconfigurable Sensor Networks for Application to Aerospace-Based Monitoring and Diagnosis', in. Sixth International Conference on Recent Advances in Soft Computing (RASC).
Howells, G., Fairhurst, M. and Deravi, F. (2006) 'Improved Data Security using Template-Free Biometric based Encryption', in. ECSIS Symposium on Intelligent Systems for Defense and ecurity (ISDS), part of 4th European Conference on Intelligent Systems and Technologies.
Vladimirova, T., Wu, X., Bridges, C., Arslan, T., Haridas, N., Yang, E., Erdogan, A. T., Barton, N., Walton, A. J., Thompson, J. S. and others. (2006) 'Intelligent and Distributed Reconfigurable System-on-Chip Sensor Networks for Space Applications - An Introduction to ESPACENET', in. 9TH Annual International Military and Aerospace Programmable Logic Device (MAPLD) Conference.
Hopkins, A. B., McDonald-Maier, K. D. and Howells, G. (2006) 'Online Monitoring for Application Debugigng and Integrity Checking', in. ECSIS Symposium on Intelligent Systems for Defense and ecurity (ISDS), part of 4th European Conference on Intelligent Systems and Technologies.
Akehurst, D. H., Boardbar, B., Evans, M. J., Howells, G. and McDonald-Maier, K. D. (2006) 'SiTra: Simple Transformations in Java', in. ACM/IEEE 9TH International Conference on Model Driven Engineering Languages and Systems (formerly the UML series of conferences), Springer-Verlag, pp. 351-364. doi: 10.1007/11880240_25.
A number of different Model Transformation Frameworks (MTF) are being developed, each of them requiring a user to learn a different language and each possessing its own specific language peculiarities, even if they are based on the QVT standard. To write even a simple transformation, these MTFs require a large amount of learning time. We describe in this paper a minimal, Java based, library that can be used to support the implementation of many practical transformations. Use of this library enables simple transformations to be implemented simply, whilst still providing some support for more complex transformations.
Akehurst, D. H., Howells, G. and McDonald-Maier, K. D. (2006) 'UML/OCL: Detaching the Standard Library', in. Workshop on OCL for (meta-)models in Multiple Application Domains, part of 9th International Conference on Model Driven Engineering Languages and Systems (MODELS/UNL).
The Object Constraint Language (or variations of it) is increasingly being used as a text based navigation or expression language over Object-based modelling languages other than the original target of UML. The recent increase of Domain Specific Languages has in particular contributed to this process. As a consequence, it is useful to investigate the lengths to which an OCL like expression language can be made independent of the specifics of the underlying modelling language, concepts and implementation. This paper looks at the issue from the perspective of detaching the OCL specification from the standard library of types that is currently built into its definition.
Fairhurst, M., Hoque, S., Howells, G. and Deravi, F. (2005) 'Evaluating Biometric Encryption Key Generation', in. Proceedings of Third Cost 275 Workshop, Biometrics on the Internet - http://www.fub.it/cost275, pp. 93-96.
In traditional cryptosystems, user authentication is based on possession of secret keys/tokens. Such keys can be forgotten, lost, stolen, or may be illegally shared, but an ability to relate a cryptographic key to biometric data can enhance the trustworthiness of a system. This paper presents a new approach to generating encryption keys directly from biometrics.
Akehurst, D. H., Howells, G. and McDonald-Maier, K. D. (2005) 'Kent Model Transformation Language', in. Proc. Model Transformations in Practice Workshop, part of MoDELS 2005.
The Kent Model Transformation Language is the third generation of model transformation approaches developed at the University of Kent. In this paper we show a grammar for the language and illustrate its differences to the predecessors. The major difference of the latest approach is the inclusion of a Model Driven Development Environment for manipulating models and transformers as first class entities.
Howells, G., Selim, H., Fairhurst, M., Deravi, F. and Hoque, S. (2005) 'SAGENT: A Model for Exploiting Biometric-Based Security for Distributed Multimedia Documents', in. Proceedings of Third Cost 275 Workshop, Biometrics on the Internet - http://www.fub.it/cost275.
Issues concerning the security of heterogeneous documents in a distributed environment are addressed by introducing a novel document model capable of incorporating any desired, and in particular biometrically based, security techniques within existing documents without compromising the original document structure.
Akehurst, D. H., Howells, G. and McDonald-Maier, K. D. (2005) 'Supporting OCL as Part of a Family of Languages', in. Proceedings of the MoDELS'05 Conference Workshop on Tool Support for OCL and Related Formalisms - Needs and Trends, LTL-REPORT-2--5-001, pp. 30-37.
With the continued interest in Model Driven techniques for software development more and more uses are found for query or expression languages that navigate and manipulate object-oriented models. The Object Constraint Language is one of the most frequently used languages; however, its original intended use as a constraint expression language has been succeeded by its frequently proposed use as a basis for a more general model query language, model transformation language and potential action language. We see a future where OCL forms a basis for a family of languages related in particular to Model Driven Development techniques; as a consequence we require an appropriate tool suite to aid in the development of such language families. This paper proposes some important aspects of such a tool suit.
Farhan-Khola, S., Sirlantzis, K., Howells, G., McDonald-Maier, K. D. and Statheros, T. (2004) 'An Analysis of the Performance of the Genetic Feature Selection Algorithm', in. 5th International Conference on Recent Advances in Soft Computing (RASC04).
Canuto, A., Fairhurst, M. and Howells, G. (2003) 'Enhancing Multi-Neural Systems through the use of Hybrid Structures', in. International Joint Conference on Neural Networks, IEEE. doi: 10.1109/IJCNN.2003.1223364.
This paper investigates the performance of multi-neural systems, focusing on the benefits that can be gained when integrating different types of neural experts (hybrid multi-neural system). An empirical evaluation shows that the integration of different types of neural networks leads to an improvement in performance in a practical classification task for a range of combination methods.
Canuto, A., Howells, G. and Fairhurst, M. (2000) 'Network Combination Strategies for a Hybrid Neuro-Fuzzy Multi-Expert System', in. 8th International Conference on Information Processing and Management of Uncertants in Knowledge Based Systems.
Canuto, A., Howells, G. and Fairhurst, M. (1999) 'A Comparative Performance Evaluation of the RePart Neuro-Fuzzy Network', in. Sixth UK Workshop on Fuzzy Systems.
Rahman, A. F. R., Howells, G. and Fairhurst, M. (1999) 'Clifford Network: A Novel Application in Character Recognition', in. International Conference on Advances in Intelligent Data Analysis (AIDA).
Howells, G., Rahman, A. F. R., Fairhurst, M. and Bisset, D. (1997) 'Clifford Networks: Novel Neural Architectures for Multi-Dimensional Data', in. Sixth IEE International Conference on Image Processing and its Applications (IPA). doi: 10.1049/cp:19970979.
Howells, G., Fairhurst, M. and Bisset, D. (1996) 'Novel Neural Architectures for Recognition of Handwritten Characters', in. IEE Workshop on Handwriting Analysis and Recognition. doi: 10.1049/ic:19960925.
This paper presents an overview of novel networking strategies for neural networks which significantly improves the training and recognition performance of such networks whilst maintaining the generalisation capabilities achieved by existing architectures. A number of different architectures are introduced based on two major principles. The first of these employs RAM-based neurons arranged in multilayer clusters and the second involves modifying the existing weight structure of a back-propagation network to utilise weights taken from a given domain of Clifford algebra. The architectures are described in terms of the structure of the neurons they employ.
Howells, G., Fairhurst, M. and Bisset, D. (1995) 'PCN: The Probabilistic Convergence Network', in. 1995 IEEE International Conference on Neural Networks (ICNN 95), IEEE, pp. 1211-1214.
Howells, G., Fairhurst, M. and Bisset, D. (1994) 'BCN - an Architecture for Weightless Ram-Base Neural Networks', in. 1994 IEEE International Conference on Neural Networks (ICNN 94) - 1st IEEE World Congress on Computational Intelligence, I E E E, pp. 1386-1390.
Howells, G. (1989) 'The Functional Data Model and Functional Programming', in. Workshop on Handling Large Knowledge Bases Declaratively.
Canuto, A., Fairhurst, M. and Howells, G. 'An Investigation of Fuzzy Combiners applied to a Hybrid Multi-Neural System', in. VII Brazilian Symposium on Neural Networks (SBRN'02).
Garhan-Khola, S. and Howells, G. 'Design of a Genetic Feature Selection Algorithm for Neuron Input Mapping in N-Tuple Based Classifiers', in. International Conference on Machine Learning: Models, Technologies and Applications (MLMTA).
Hoque, S., Selim, H., Howells, G., Fairhurst, M. and Deravi, F. 'SAGENT: A Novel Technique for Document Modeling for Secure Access and Distribution', in. 7th International Conference on Document Analysis and Recognition ICDAR'03, Edinburgh, Vol II, Proceedings, pp. 1257-1261.
Patents
Howells, G., Hopkins, A. B. and McDonald-Maier, K. D. (2007) 'A Device to Generate a Machine Specific Identification Key'. doi: PCT/GB2007/002916.
An integrated circuit assembly having monitoring circuitry for observing the internal signals of the system so that its properties are captured. The system properties are manipulated so that they can be used as a pseudo random number and or as the basis number for an encryption key. The monitoring circuitry having: manipulation circuitry to transform monitored data and combine it with previously manipulated values; and registers to store previously manipulated values; and counters to count events; and condition detection circuitry for detecting when a signal is at a specific value or range of values. Optionally the monitoring circuitry which has the functionality for capturing system properties may be combined with other monitoring circuitry, which has the functionality required by a debug support circuit.; The monitoring circuitry avoids replication of resources by sharing parts of specific monitoring circuits like counters.
Howells, G., Fairhurst, M. and Deravi, F. (2006) 'A Method and Apparatus for the Generation of Code from Pattern Features'. doi: 1111.
Howells, G., Fairhurst, M. and Deravi, F. (2006) 'Method for the Direct Generation of Encryption Keys from Biometric Data Samples'. doi: UK Patent Application GB 06 13482.9.
Others
Akehurst, D. H., Uzenkov, O., Howells, G., McDonald-Maier, K. D. and Bordbar, B. (2007) 'Compiling UML State Diagrams into WHDL: An Experiment in using Model Driven Development', Forum on Specification and Design Languages (FDL 07). Forum on Specification and Design Languages (FDL 07), CiteSeer.
Embedded systems are becoming more and more complex. This complexity means that developers require increasing support and new techniques to aid them in developing complex systems. The use of high level graphical languages can significantly aid in managing the complex design of a system. However, it is still necessary to convert the high level design into low level code for the purpose of implementation. In this paper, we discuss the results of experimenting with the use of Model Driven Development (MDD) Techniques as a means of compiling UML State Diagrams into synthesisable VHDL code. These results show that although MDD provides a potentially useful technique, there are aspects where we still need significant improvement in the MDD tools and techniques in order to make this an easily useable approach to the task.
Edited books
Howells, G. and Sirlantzis, K. (2010) Proceedings of the 2010 International Conference on Emerging Security Technologies (EST 2010) - Robots and Security (ROBOSEC 2010) - Learning and Adaptive Behavior in Robotic Systems (LAB-RS 2010), 2010 International Conference on Emerging Security Technologies. Edited by G. Howells, K. Sirlantzis, A. Stoica, T. Huntsberger, and T. Arslan. Washington, USA: IEEE Conference Publishing Services (CPS), pp. C1-C1. doi: doi:10.1109/EST.2010.42.
Edited journals
Howells, G. (2008) 'International Workshop: ModEasy '07: Model Driven Design for Automotive Safety Embedded Systems'. Edited by J.-L. Dekeyser, A. Menhaj-Rivenq, K. D. McDonald-Maier, and G. Howells. Shaker Verlag.