This paper proposes a novel adaptive dictionary (AD) reconstruction scheme to improve the performance of compressed sensing (CS) with electrocardiogram signals (ECG). The method is based on the use of multiple dictionaries, created using dictionary learning (DL) techniques for CS signal reconstruction. The modified reconstruction framework is a two-stage process that leverages information about the signal from an initial signal reconstruction stage. By identifying whether a QRS complex is present and if so, determining a location estimate of the QRS, the most appropriate dictionary is selected and a second stage more refined signal reconstruction can be obtained. The performance of the proposed algorithm is compared with state-of-the-art CS implementations in the literature, as well as the set partitioning in hierarchical trees (SPIHT) wavelet-based lossy compression algorithm. The results indicate that the proposed reconstruction scheme outperforms all existing CS implementations in terms of signal fidelity at each compression ratio tested. The performance of the proposed approach also compares favorably with SPIHT in terms of signal reconstruction quality. Furthermore, an analysis of the overall power consumption of the proposed ECG compression framework as would be used in a body area network (BAN) demonstrates positive results for the proposed CS approach when compared with existing CS techniques and SPIHT.

This paper proposes a novel approach for detecting and tracking vehicles to the rear and in the blind zone of a vehicle, using a single rear-mounted fisheye camera and multiple detection algorithms. A maneuver that is a significant cause of accidents involves a target vehicle approaching the host vehicle from the rear and overtaking into the adjacent lane. As the overtaking vehicle moves toward the edge of the image and into the blind zone, the view of the vehicle gradually changes from a front view to a side view. Furthermore, the effects of fisheye distortion are at their most pronounced toward the extremities of the image, rendering detection of a target vehicle entering the blind zone even more difficult. The proposed system employs an AdaBoost classifier at distances of 10–40 m between the host and target vehicles. For detection at short distances where the view of a target vehicle has changed to a side view and the AdaBoost classifier is less effective, identification of vehicle wheels is proposed. Two methods of wheel detection are employed: at distances between 5 and 15 m, a novel algorithm entitled wheel arch contour detection (WACD) is presented, and for distances less than 5 m, Hough circle detection provides reliable wheel detection. A testing framework is also presented, which categorizes detection performance as a function of distance between host and target vehicles. Experimental results indicate that the proposed method results in a detection rate of greater than 93% in the critical range (blind zone) of the host.

This paper provides a comprehensive review of compressed sensing or compressive sampling (CS) in bioelectric signal compression applications. The aim is to provide a detailed analysis of the current trends in CS, focusing on the advantages and disadvantages in compressing different biosignals and its suitability for deployment in embedded hardware. Performance metrics such as percent root-mean-squared difference (PRD), signal-to-noise ratio (SNR), and power consumption are used to objectively quantify the capabilities of CS. Furthermore, CS is compared to state-of-the-art compression algorithms in compressing electrocardiogram (ECG) and electroencephalography (EEG) as examples of typical biosignals. The main technical challenges associated with CS are discussed along with the predicted future trends.

This paper proposes a performance test framework for vision based vehicle detection systems implemented on road-going vehicles. An extensive literature review outlines the evolution of test frameworks used by a number of recently published vehicle detection systems. The proposed test framework determines the effectiveness of a detection algorithm as a function of distance between the host and target vehicles. The framework assists the characterisation of an algorithm's performance over the full range of distances in which a vehicle can be detected in an image. The test framework is designed for use in blind spot detection, forward collision warning and rear end collision warning applications.

This paper examines the effects of compression on EEG signals, in the context of automated detection of epileptic seizures. Specifically, it examines the use of lossy compression on EEG signals in order to reduce the amount of data which has to be transmitted or stored, while having as little impact as possible on the information in the signal relevant to diagnosing epileptic seizures. Two popular compression methods, JPEG2000 and SPIHT, were used. A range of compression levels was selected for both algorithms in order to compress the signals with varying degrees of loss. This compression was applied to the database of epileptiform data provided by the University of Freiburg, Germany. The real-time EEG analysis for event detection automated seizure detection system was used in place of a trained clinician for scoring the reconstructed data. Results demonstrate that compression by a factor of up to 120:1 can be achieved, with minimal loss in seizure detection performance as measured by the area under the receiver operating characteristic curve of the seizure detection system.

Spiking neural networks (SNNs) attempt to emulate information processing in the mammalian brain based on massively parallel arrays of neurons that communicate via spike events. SNNs offer the possibility to implement embedded neuromorphic circuits, with high parallelism and low power consumption compared to the traditional von Neumann computer paradigms. Nevertheless, the lack of modularity and poor connectivity shown by traditional neuron interconnect implementations based on shared bus topologies is prohibiting scalable hardware implementations of SNNs. This paper presents a novel hierarchical network-on-chip (H-NoC) architecture for SNN hardware, which aims to address the scalability issue by creating a modular array of clusters of neurons using a hierarchical structure of low and high-level routers. The proposed H-NoC architecture incorporates a spike traffic compression technique to exploit SNN traffic patterns and locality between neurons, thus reducing traffic overhead and improving throughput on the network. In addition, adaptive routing capabilities between clusters balance local and global traffic loads to sustain throughput under bursting activity. Analytical results show the scalability of the proposed H-NoC approach under different scenarios, while simulation and synthesis analysis using 65-nm CMOS technology demonstrate high-throughput, low-cost area, and power consumption per cluster, respectively.

The complexity of inter-neuron connectivity is prohibiting scalable hardware implementations of spiking neural networks (SNNs). Traditional neuron interconnect using a shared bus topology is not scalable due to non-linear growth of neuron connections with the neural network size. This paper presents a novel hierarchical NoC (H-NoC) architecture for SNN hardware which addresses the scalability issue by creating a 3-dimensional array of clusters of neurons with a hierarchical structure of low and high-level routers. The H-NoC architecture also incorporates a spike traffic compression technique to exploit SNN traffic patterns, thus reducing traffic overhead and improving throughput on the network. In addition, adaptive routing capabilities between clusters balance local and global traffic loads to sustain throughput under bursting activity. Simulation results show a high throughput per cluster (3.33×109spikes/second), and synthesis results using 65-nm CMOS technology demonstrate low cost area (0.587mm2) and power consumption (13.16mW @100MHz) for a single cluster of 400 neurons, which outperforms existing SNN hardware strategies.

This paper describes a scalable and extendable Remote Field Programmable Gate Array Laboratory (Remote FPGA) which can be used to enhance the learning of digital systems and FPGA applications. The web-based console provides an always-on, real-time, interactive control and visualisation interface to/from a bank of remote FPGAs. A Xilinx ISE project template enables integration of user HDL-based designs to execute on the Remote FPGA. Host-FPGA communication is supported using a register-based interface. Users can create real-time, interactive and visual demonstrators of digital systems components. The paper presents a demonstrator for a Finite State Machine (FSM) application, and illustrates the use of web-based control and visualisation for enhanced learning of FSM behaviour. The paper also presents a case study of the use of Remote FPGA in undergraduate teaching.

This paper presents ACROMUSE, a novel genetic algorithm (GA) which adapts crossover, mutation, and selection parameters. ACROMUSEs objective is to create and maintain a diverse population of highly-fit (healthy) individuals, capable of adapting quickly to fitness landscape change and well-suited to the efficient optimization of multimodal fitness landscapes. A new methodology is introduced for determining standard population diversity (SPD) and an original measure of healthy population diversity (HPD) is proposed. The SPD measure is employed to adapt crossover and mutation, while selection pressure is controlled by adapting tournament size according to HPD. In addition to selection pressure control, ACROMUSE tournament selection selects individuals according to healthy diversity contribution rather than fitness. This proposed selection mechanism simultaneously promotes diversity and fitness within the population. The performance of ACROMUSE is evaluated using various multimodal benchmark functions. Statistically significant results are presented comparing ACROMUSEs fitness and diversity performance to that of several other GAs. By maintaining a diverse population of healthy individuals, ACROMUSE responds to fitness landscape change by restoring better fitness scores faster than other GAs. Analysis of the adaptive operators illustrates that the key benefit of ACROMUSE is the synergy of the operators working together to achieve an effective balance between exploration and exploitation.

This paper presents an Adaptive Genetic Algorithm (AGA) where selection pressure, crossover and mutation probabilities are adapted according to population diversity statistics. The creation and maintenance of a diverse population of healthy individuals is a central goal of this research. To realise this objective, population diversity measures are utilised by the parameter adaptation process to both explore (through diversity promotion) and exploit (by local search and maintenance of a presence in known good regions of the fitness landscape). The performance of the proposed AGA is evaluated using a multi-modal, multi-dimensional function optimisation benchmark. Results presented indicate that the AGA achieves better fitness scores faster compared to a traditional GA.

This paper details the hardware evolution of adaptive Spiking Neural Network (SNN) controllers, implemented on a network of cascaded Field Programmable Analogue Arrays (FPAAs). The fixed architecture, feed forward SNNs are trained using a Genetic Algorithm (GA). An obstacle avoidance simulated robotics controller application is chosen to test the FPAA reconfigurable hardware evolution platform. Evolved behaviours, resulting from FPAA-based SNN controllers, are compared with those obtained using software-based SNN implementations. Results presented indicate the emergence of effective behaviours and adaptation to environmental change.

In this paper a genetic algorithm has been developed to evolve a neural network (NN) implementation of a two input XOR function. This GA will subsequently be used to contrast the relative difficulties of implementing the XOR NN on FPGA's and FPAA's respectively. Two case studies are presented to demonstrate intrinsic evolution of the XOR network on reconfigurable analogue and digital devices. In both cases the GA evolves the synaptic weights and threshold values for an NN implemented on both field programmable gate array (FPGA) and field programmable analogue array (FPAA) hardware platforms