[show abstract][hide abstract] ABSTRACT: Europe faces a major and growing healthcare prob-lem 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.
Fourth International conference on Emerging Security Technology, Cambridge; 09/2013
[show abstract][hide abstract] ABSTRACT: A vision system that can assess its own performance and take appropriate actions online to maximize its effectiveness would be a step towards achieving the long-cherished goal of imitating humans. This paper proposes a method for performing an online performance analysis of local feature detectors, the primary stage of many practical vision systems. It advocates the spatial distribution of local image features as a good performance indicator and presents a metric that can be calculated rapidly, concurs with human visual assessments and is complementary to existing offline measures such as repeatability. The metric is shown to provide a measure of complementarity for combinations of detectors, correctly reflecting the underlying principles of individual detectors. Qualitative results on well-established datasets for several state-of-the-art detectors are presented based on the proposed measure. Using a hypothesis testing approach and a newly-acquired, larger image database, statistically-significant performance differences are identified. Different detector pairs and triplets are examined quantitatively and the results provide a useful guideline for combining detectors in applications that require a reasonable spatial distribution of image features. A principled framework for combining feature detectors in these applications is also presented. Timing results reveal the potential of the metric for online applications.
[show abstract][hide abstract] ABSTRACT: The ICmetrics technology is concerned with identifying acceptable features in an electronic system’s operation for encryption purposes. 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 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.
[show abstract][hide abstract] ABSTRACT: Speeded-Up Robust Features is a feature extraction algorithm designed for real-time execution, although this is rarely achievable on low-power hardware such as that in mobile robots. One way to reduce the computation is to discard some of the scale-space octaves, and previous research has simply discarded the higher octaves. This paper shows that this approach is not always the most sensible and presents an algorithm for choosing which octaves to discard based on the properties of the imagery. Results obtained with this best octaves algorithm show that it is able to achieve a significant reduction in computation without compromising matching performance.
[show abstract][hide abstract] ABSTRACT: Repeatability is widely used as an indicator of the performance of an image feature detector but, although useful, it does
not convey all the information that is required to describe performance. This paper explores the spatial distribution of interest
points as an alternative indicator of performance, presenting a metric that is shown to concur with visual assessments. This
metric is then extended to provide a measure of complementarity for pairs of detectors. Several state-of-the-art detectors
are assessed, both individually and in combination. It is found that Scale Invariant Feature Operator (SFOP) is dominant,
both when used alone and in combination with other detectors.
Image Analysis and Recognition - 8th International Conference, ICIAR 2011, Burnaby, BC, Canada, June 22-24, 2011. Proceedings, Part I; 01/2011
[show abstract][hide abstract] ABSTRACT: 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.
[show abstract][hide abstract] ABSTRACT: The most frequently employed measure for performance characterisation of local feature detectors is repeatability, but it has been observed that this does not necessarily mirror actual performance. Presented are improved repeatability formulations which correlate much better with the true performance of feature detectors. Comparative results for several state-of-the-art feature detectors are presented using these measures; it is found that Hessian-based detectors are generally superior at identifying features when images are subject to various geometric and photometric transformations.
[show abstract][hide abstract] ABSTRACT: 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.
[show abstract][hide abstract] ABSTRACT: Current weightless classifiers require historical data to model a system and make prediction about a system successfully. Historical data either is not always available or does not take a recent system modification into consideration. For this reason an adaptive filter is designed, which when employed with a weightless classifier enables system model, difficult to characterise system model, and system output prediction, successfully.
ESANN 2010, 18th European Symposium on Artificial Neural Networks, Bruges, Belgium, April 28-30, 2010, Proceedings; 01/2010
[show abstract][hide abstract] ABSTRACT: Performance comparison among various architectures is generally attained by using standard benchmark tools. This paper presents
JetBench, an Open Source OpenMP based multicore benchmark application that could be used to analyse real time performance
of a specific target platform. The application is designed to be platform independent by avoiding target specific libraries
and hardware counters and timers. JetBench uses jet engine parameters and thermodynamic equations presented in the NASA’s
EngineSim program, and emulates a real-time jet engine performance calculator. The user is allowed to determine a flight profile
with timing constraints, and adjust the number of threads. This paper discusses the structure of the application, thread distribution
and its scalability on a custom symmetric multicore platform based on a cycle accurate full system simulator.
Architecture of Computing Systems - ARCS 2010, 23rd International Conference, Hannover, Germany, February 22-25, 2010. Proceedings; 01/2010
[show abstract][hide abstract] ABSTRACT: Recent developments in reconfigurable multiprocessor system on chip (MPSoC) have offered system designers a great amount of flexibility to exploit task concurrency with higher throughput and less energy consumption. This paper presents a novel fuzzy logic reconfiguration engine (FLRE) for coarse grain MPSoC reconfiguration that facilitates to identify an optimum balance between power and performance of the system. The FLRE is composed on two levels of abstraction layers. The system selects an optimal configuration of Level 1 / Level 2 cache size and Associativity, processor operating frequency and voltage, the number of cores based on miss rate, and energy and throughput information of the system both at core and SoC level. An 8-core symmetric chip multiprocessor has been used to evaluate the proposed scheme. The results show an overall decrease of energy consumption with not more than 30% decrease in the throughput.
CISIS 2010, The Fourth International Conference on Complex, Intelligent and Software Intensive Systems, Krakow, Poland, 15-18 February 2010; 01/2010
[show abstract][hide abstract] ABSTRACT: With the increase of processor-memory performance gap, it has become important to gauge the performance of cache architectures so as to evaluate their impact on energy requirement and throughput of the system. Multilevel caches are found to be increasingly prevalent in the high-end processors. Additionally, the recent drive towards multicore systems has necessitated the use of multilevel cache hierarchies for shared memory architectures. This paper presents simplified and accurate mathematical models to estimate the energy consumption and the impact on throughput for multilevel caches for single core systems.
Proceedings of the 12th UKSim, International Conference on Computer Modelling and Simulation, Cambridge, UK, 24-26 March 2010; 01/2010
[show abstract][hide abstract] ABSTRACT: Embedded systems architectures have traditionally often been investigated and designed in order to achieve a greater throughput combined with minimum energy consumption. With the advent of reconfigurable architectures it is now possible to support algorithms to find optimal solutions for an improved energy and throughput balance. As a result of ongoing research several online and offline techniques and algorithm have been proposed for hardware adaptation. This paper presents a novel coarse-grained reconfigurable symmetric chip multiprocessor (SCMP) architecture managed by a fuzzy logic engine that balances performance and energy consumption. The architecture incorporates reconfigurable level 1 (L1) caches, power gated cores and adaptive on-chip network routers to allow minimizing leakage energy effects for inactive components. A coarse grained architecture was selected as to be a focus for this study as it typically allows for fast reconfiguration as compared to the finegrained architectures, thus making it more feasible to be used for runtime adaption schemes. The presented architecture is analyzed using a set of OpenMP based parallel benchmarks and the results show significant improvements in performance while maintaining minimum energy consumption.
[show abstract][hide abstract] ABSTRACT: A workable technique for the stable reproduction of an encryption key from measurable characteristics of integrated circuits which have not previously been enrolled or introduced to the system is presented. Such a system offers great potential within practical scenarios where rapid integration of new devices is necessary such as may be found within the healthcare environment.
Bio-inspired Learning and Intelligent Systems for Security, 2009. BLISS '09. Symposium on; 09/2009
[show abstract][hide abstract] ABSTRACT: This paper investigates the practicalities of combining values derived from measurable features of given integrated electronic circuits in order to derive a robust encryption key, a technique termed ICmetrics. Specifically the paper explores options for the precise techniques required to combine the derived feature values in order to ensure key stability. Key stability is an essential component of any encryption system but this must be combined with a guarantee of key diversity between devices.
[show abstract][hide abstract] ABSTRACT: In this paper, non deterministic Direct Reinforcement Learning (RL) for controlling the transmission times and power of a Wireless Sensor Network (WSN) node is presented. RL allows for truly autonomous optimal behaviour of agents by requiring no models or supervision to learn. Optimal actions are learnt by repeated interactions with the environment. Performance results are presented for Monte Carlo, TD0 and TDlambda. The resultant optimal learned policies are shown to out perform static power control in a stochastic environment.
[show abstract][hide abstract] ABSTRACT: The ultimate research goal for unmanned aerial vehicles (UAVs) is to facilitate autonomy of operation. Research in the last decade has highlighted the potential of vision sensing in this regard. Although vital for accomplishment of missions assigned to any type of unmanned aerial vehicles, vision sensing is more critical for small aerial vehicles due to lack of high precision inertial sensors. In addition, uncertainty of GPS signal in indoor and urban environments calls for more reliance on vision sensing for such small vehicles. With off-line processing does not offer an attractive option in terms of autonomy, these vehicles have been challenging platforms to implement vision processing on-board due to their strict payload capacity and power budget. The strict constraints drive the need for new vision processing architectures for small unmanned aerial vehicles. Recent research has shown encouraging results with FPGA based hardware architectures. This paper reviews the bottle necks involved in implementing vision processing on-board,advocates the potential of hardware based solutions to tackle strict constraints of small unmanned aerial vehicles and finally analyzes feasibility of ASICs, Structured ASICs and FPGAs for use on future systems.
[show abstract][hide abstract] ABSTRACT: This paper explores the biometric identification and verification of human subjects via fingerprints utilising an adaptive FPGA-based weightless neural networks. The exploration espoused here is a hardware-based system motivated by the need for accurate and rapid response to identification of fingerprints which may be lacking in other alternative systems such as software based neural networks. The fingerprints are pre-processed and binarized, and the binarized fingerprints are partitioned into train- and test-set for the FPGA-based neural network. The neural network employed in this exploration is known as Enhanced Convergent Network (EPCN). The results obtained are compared to other alternative systems. They demonstrate the suitability of the FPGA-based EPCN for such tasks.
Adaptive Hardware and Systems, NASA/ESA Conference on. 07/2009;
[show abstract][hide abstract] ABSTRACT: Speeded up robust features (SURF) is a state of the art computer vision algorithm that relies on integral image representation for performing fast detection and description of image features that are scale and rotation invariant. Integral image representation, however, has major draw back of large binary word length that leads to substantial increase in memory size. When designing a dedicated hardware to achieve real-time performance for the SURF algorithm, it is imperative to consider the adverse effects of integral image on memory size, bus width and computational resources. With the objective of minimizing hardware resources, this paper presents a novel implementation concept of a reduced word length integral image based SURF detector. It evaluates two existing word length reduction techniques for the particular case of SURF detector and extends one of these to achieve more reduction in word length. This paper also introduces a novel method to achieve integral image word length reduction for SURF detector.
[show abstract][hide abstract] ABSTRACT: This paper investigates how human identification and identity verification can be performed by the application of an FPGA based weightless neural network, entitled the Enhanced Probabilistic Convergent Neural Network (EPCN), to the iris biometric modality. The human iris is processed for feature vectors which will be employed for formation of connectivity, during learning and subsequent recognition. The pre-processing of the iris, prior to EPCN training, is very minimal. Structural modifications were also made to the Random Access Memory (RAM) based neural network which enhances its robustness when applied in real-time.
ESANN 2009, 17th European Symposium on Artificial Neural Networks, Bruges, Belgium, April 22-24, 2009, Proceedings; 01/2009