Search

The creation of a predictive system that correctly forecasts future changes of a stock price is crucial for investment management and algorithmic trading. The use of technical analysis for financial forecasting has been successfully employed by many researchers. Input window length is a time frame parameter required to be set when calculating many technical indicators. This study explores how the performance of the predictive system depends on a combination of a forecast horizon and an input window length for forecasting variable horizons. Technical indicators are used as input features for machine learning algorithms to forecast future directions of stock price movements. The dataset consists of ten years daily price time series for fifty stocks. The highest prediction performance is observed when the input window length is approximately equal to the forecast horizon. This novel pattern is studied using multiple performance metrics: prediction accuracy, winning rate, return per trade and Sharpe ratio. [ABSTRACT FROM AUTHOR]

To enable fast reliable feature matching or tracking in scenes, features need to be discrete and meaningful, and hence edge or corner features, commonly called interest points are often used for this purpose. Experimental research has illustrated that biological vision systems use neuronal circuits to extract particular features such as edges or corners from visual scenes. Inspired by this biological behaviour, this paper proposes a biologically inspired spiking neural network for the purpose of image feature extraction. Standard digital images are processed and converted to spikes in a manner similar to the processing that transforms light into spikes in the retina. Using a hierarchical spiking network, various types of biologically inspired receptive fields are used to extract progressively complex image features. The performance of the network is assessed by examining the repeatability of extracted features with visual results presented using both synthetic and real images. [ABSTRACT FROM AUTHOR]

Intrinsic motivations play an important role in human learning, particularly in the early stages of childhood development, and ideas from this research field have influenced robotic learning and adaptability. In this paper we investigate one specific type of intrinsic motivation, that of novelty detection and we discuss the reasons that make it a powerful facility for continuous learning. We formulate and present one original type of biologically inspired novelty detection architecture and implement it on a robotic system engaged in a perceptual classification task. The results of real-world robot experiments we conducted show how this original architecture conforms to behavioural observations and demonstrate its effectiveness in terms of focusing the system’s attention in areas that are potential for effective learning. [ABSTRACT FROM AUTHOR]

Abstract: Based on the information processing functionalities of spiking neurons, hierarchical spiking neural networks are proposed to simulate visual attention. Using spiking neural networks inspired by the visual system, an image can be decomposed into multiple visual image components. Based on specific visual image components and image features, a visual attention system is proposed to extract attention areas according to top–down volition-controlled signals. The hierarchical spiking neural networks are constructed with a conductance-based integrate-and-fire neuron model and a set of specific receptive fields in different levels. The simulation algorithm and properties of the networks are detailed in this paper. Simulation results show that the attention system is able to perform visual attention of objects based on specific image components or features, and a demonstration shows how the attention system can detect a house in a visual image. Using the proposed saliency index, attention areas of interest can be extracted from spike rate maps of multiple visual pathways, such as ON/OFF colour pathways. According to this visual attention principle, the visual image processing system can quickly focus on specific areas while ignoring other areas. [Copyright &y& Elsevier]

Abstract: We propose a robotics algorithm that is able to simultaneously combine, adapt and create actions to solve a task. The actions are combined in a Finite State Automaton whose structure is determined by a novel evolutionary algorithm. The actions parameters, or new actions, are evolved alongside the FSA topology. Actions can be combined together in a hierarchical fashion. This approach relies on skills that with which the robot is already provided, like grasping or motion planning. Therefore software reuse is an important advantage of our proposed approach. We conducted several experiments both in simulation and on a real mobile manipulator PR2 robot, where skills of increasing complexity are evolved. Our results show that (i) an FSA generated in simulation can be directly applied to a real robot without modifications and (ii) the evolved FSA is robust to the noise and the uncertainty arising from real-world sensors. [Copyright &y& Elsevier]

Abstract: Based on spiking neuron models and different receptive field models, hierarchical networks are proposed to process visual stimuli, in which multiple overlapped objects are represented by different orientation bars. The main purpose of this paper is to show that hierarchical spiking neural networks are able to segment the objects and bind their pixels to form shapes of objects using local excitatory lateral connections. The presented architecture is based on biologically inspired hierarchical structures. Segmentation is achieved through temporal correlation of neuron activities. The properties of these networks are demonstrated using a series of visual scenes representing different stimuli settings. [Copyright &y& Elsevier]

Abstract: The last 50 years has witnessed considerable research in the area of neural networks resulting in a range of architectures, learning algorithms and demonstrative applications. A more recent research trend has focused on the biological plausibility of such networks as a closer abstraction to real neurons may offer improved performance in an adaptable, real-time environment. This poses considerable challenges for engineers particularly in terms of the requirement to realise a low-cost embedded solution. Programmable hardware has been widely recognised as an ideal platform for the adaptable requirements of neural networks and there has been considerable research reported in the literature. This paper aims to review this body of research to identify the key lessons learned and, in particular, to identify the remaining challenges for large-scale implementations of spiking neural networks on FPGAs. [Copyright &y& Elsevier]

Abstract: Limits on synaptic efficiency are characteristic of biological neural networks. In this paper, weight limitation constraints are applied to the spike time error-backpropagation (SpikeProp) algorithm for temporally encoded networks of spiking neurons. A novel solution to the problem raised by non-firing neurons is presented which makes the learning algorithm converge reliably and efficiently. In addition a square cosine encoder is applied to the input neurons to reduce the number of input neurons required. The approach is demonstrated by application to the classical XOR-problem analysis, a function approximation experiment and benchmark data sets. Using input delay neurons and relative timing, the algorithm is also applied to solve a time series prediction problem. The experimental results show that the new approach produces comparable accuracy in classification with the original approach while utilising a smaller spiking neural network. [Copyright &y& Elsevier]

Investigates the purpose of fault diagnosis of electronic systems using artificial intelligent techniques. Isolation of faults on defective systems; Need for automated diagnostic tools; Definition of a diagnostic process.

• Development of a fuzzy classification system to ascertain an overall health status. • Determination of human BPM, RR and rhythm analysis via robotic tactile sensing. • Determination of human CRT and health status via use of tactile sensing and vision. • Pilot study to evaluate accuracy of vital sign measurement and fuzzy triage on human subjects. The ability to quickly and accurately triage a person's medical condition in an emergency situation or other critical scenarios could mean the difference between life and death. Endowing a robotic system with vision and tactile capabilities, similar to those of medical professionals, and thus enabling robots to assess a patient's status in an emergency is a highly sought after characteristic in healthcare robotics. This paper presents a novel fuzzy triage system exploiting visual and tactile sensing, to equip a robot with the skills to accurately determine key vital signs in humans. There are three key signs of human health: respiratory rate, pulse rate (Beats Per Minute (BPM)) and capillary refill time. Using ground truth from a medical professional, the fuzzy triage system is trained and validated initially with informed synthetic data and then further evaluated using vital signs data collected from subjects in a pilot study. Results from this pilot study indicate that the fuzzy triage system is capable of classifying a patient's health using the novel approaches for collecting BPM, Respiratory Rate (RR) and Capillary Refill Time (CRT) which replicate, to some extent, the approaches used by medical professionals for measuring vital signs. Furthermore, the intelligent system proved capable of determining whether a pulse was regular or arrhythmic, whether respiratory rate was regular or irregular, and determining the subject's capillary refill time. Such results imply that this system could ultimately be used, for example, in a home assistance robot for elderly or disabled persons, or as a first responder robot. Ultimately the aim would be that these methods could be utilised by robotic systems in emergency scenarios or disaster zones. [ABSTRACT FROM AUTHOR]

Presents information on the BiCMOS circuits found in a fuzzy system, which can differentiate the different mathematical operations witin the system. How the operating speed of the circuits where maximized; Information on the hardware implementation of implication and defuzzification; Examination of the primary focus of fuzzy logic.

Presents a paper which discussed the area-efficient hardware implementations of neural networks, in novel architecture and synapse design. Special features of the architecture; Information on the synapse design; Consideration of training of the neural networks based on the proposed synapses.

Ensemble models achieve high accuracy by combining a number of base estimators and can increase the reliability of machine learning compared to a single estimator. Additionally, an ensemble model enables a machine learning method to deal with imbalanced data, which is considered to be one of the most challenging problems in machine learning. In this paper, the capability of Adaptive Boosting (AdaBoost) is integrated with a Convolutional Neural Network (CNN) to design a new machine learning method, AdaBoost-CNN, which can deal with large imbalanced datasets with high accuracy. AdaBoost is an ensemble method where a sequence of classifiers is trained. In AdaBoost, each training sample is assigned a weight, and a higher weight is set for a training sample that has not been trained by the previous classifier. The proposed AdaBoost-CNN is designed to reduce the computational cost of the classical AdaBoost when dealing with large sets of training data, through reducing the required number of learning epochs for its ingredient estimator. AdaBoost-CNN applies transfer learning to sequentially transfer the trained knowledge of a CNN estimator to the next CNN estimator, while updating the weights of the samples in the training set to improve accuracy and to reduce training time. Experimental results revealed that the proposed AdaBoost-CNN achieved 16.98% higher accuracy compared to the classical AdaBoost method on a synthetic imbalanced dataset. Additionally, AdaBoost-CNN reached an accuracy of 94.08% on 10,000 testing samples of the synthetic imbalanced dataset, which is higher than the accuracy of the baseline CNN method, i.e. 92.05%. AdaBoost-CNN is computationally efficient, as evidenced by the fact that the training simulation time of the proposed method is 47.33 s, which is lower than the training simulation time required for a similar AdaBoost method without transfer learning, i.e. 225.83 s on the imbalanced dataset. Moreover, when compared to the baseline CNN, AdaBoost-CNN achieved higher accuracy when applied to four other benchmark datasets including CIFAR-10 and Fashion-MNIST. AdaBoost-CNN was also applied to the EMNIST datasets, to determine its impact on large imbalanced classes, and the results demonstrate the superiority of the proposed method compared to CNN. [ABSTRACT FROM AUTHOR]

Abstract: Within mobile robotics, one of the most dominant relationships to consider when implementing robot control code is the one between the robot’s sensors and its motors. When implementing such a relationship, efficiency and reliability are of crucial importance. The latter aspects often prove challenging due to the complex interaction between a robot and the environment in which it exists, frequently resulting in a time consuming iterative process where control code is redeveloped and tested many times before obtaining an optimal controller. In this paper, we address this challenge by implementing an alternative approach to control code generation, which first identifies the desired robot behaviour and represents the sensor-motor task algorithmically through system identification using the NARMAX modelling methodology. The control code is generated by task demonstration, where the sensory perception and velocities are logged and the relationship that exists between them is then modelled using system identification. This approach produces transparent control code through non-linear polynomial equations that can be mathematically analysed to obtain formal statements regarding specific inputs/outputs. We demonstrate this approach to control code generation and analyse its performance in dynamic environments. [Copyright &y& Elsevier]

Abstract: This paper proposes an online inverse-forward adaptive scheme with a KSOM based hint generator for solving the inverse kinematic problem of a redundant manipulator. In this approach, a feed-forward network such as a radial basis function (RBF) network is used to learn the forward kinematic map of the redundant manipulator. This network is inverted using an inverse-forward adaptive scheme until the network inversion solution guides the manipulator end-effector to reach a given target position with a specified accuracy. The positioning accuracy, attainable by a conventional network inversion scheme, depends on the approximation error present in the forward model. But, an accurate forward map would require a very large size of training data as well as network architecture. The proposed inverse-forward adaptive scheme effectively approximates the forward map around the joint angle vector provided by a hint generator. Thus the inverse kinematic solution obtained using the network inversion approach can take the end-effector to the target position within any arbitrary accuracy. In order to satisfy the joint angle constraints, it is necessary to provide the network inversion algorithm with an initial hint for the joint angle vector. Since a redundant manipulator can reach a given target end-effector position through several joint angle vectors, it is desirable that the hint generator is capable of providing multiple hints. This problem has been addressed by using a Kohonen self organizing map based sub-clustering (KSOM-SC) network architecture. The redundancy resolution process involves selecting a suitable joint angle configuration based on different task related criteria. The simulations and experiments are carried out on a 7 DOF PowerCube™ manipulator. It is shown that one can obtain a positioning accuracy of 1 mm without violating joint angle constraints even when the forward approximation error is as large as 4 cm. An obstacle avoidance problem has also been solved to demonstrate the redundancy resolution process with the proposed scheme. [Copyright &y& Elsevier]

As embedded systems are increasingly entrusted with critical tasks, it becomes important that these systems exhibit high levels of reliability. Increasing complexity makes production of fault-free systems extremely difficult. Developing self-repair for embedded systems provides a means to alleviate the effects of a fault. This paper discusses a self-repair methodology for embedded systems that employs the unified modelling language and genetic algorithms. This approach increases the flexibility of systems by enabling the transfer of functionality between hardware and software. This design methodology is demonstrated using a speech recognition system. The benefits of the design for a self-repair strategy are highlighted and the implementation results for two examples of design objectives are presented. [Copyright &y& Elsevier]

Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent years and continues to reveal new characteristics of biological neurons. New technologies can now capture temporal changes in the internal activity of the brain in more detail and help clarify the relationship between brain activity and the perception of a given stimulus. This new knowledge has led to a new type of artificial neural network, the Spiking Neural Network (SNN), that draws more faithfully on biological properties to provide higher processing abilities. A review of recent developments in learning of spiking neurons is presented in this paper. First the biological background of SNN learning algorithms is reviewed. The important elements of a learning algorithm such as the neuron model, synaptic plasticity, information encoding and SNN topologies are then presented. Then, a critical review of the state-of-the-art learning algorithms for SNNs using single and multiple spikes is presented. Additionally, deep spiking neural networks are reviewed, and challenges and opportunities in the SNN field are discussed. [ABSTRACT FROM AUTHOR]

Tactile sensing has recently been used in robotics for object identification, grasping, and material identification. Although human tactile sensing is multimodal, existing tactile material recognition approaches use vibration information only. Moreover, material identification through tactile sensing can be solved as an continuous process, yet state of the art approaches use a batch approach where readings are taken for at least one second. This work proposes a recursive multimodal (vibration and thermal) tactile material identification approach. Using the frequency response of the vibration induced by the material and a set of thermal features, we show that it is possible to accurately identify materials in less than half a second. We conducted an exhaustive comparison of our approach with commonly used vibration descriptors and machine learning algorithms for material identification such as k -Nearest Neighbour, Artificial Neural Network and Support Vector Machines. Experimental results show that our approach identifies materials faster than existing techniques and increase the classification accuracy when multiple sensor modalities are used. [ABSTRACT FROM AUTHOR]

For a considerable time, it has been the goal of computational neuroscientists to understand biological nervous systems. However, the vast complexity of such systems has made it very difficult to fully understand even basic functions such as movement. Because of its small neuron count, the C. elegans nematode offers the opportunity to study a fully described connectome and attempt to link neural network activity to behaviour. In this paper a simulation of the neural network in C. elegans that responds to chemical stimulus is presented and a consequent realistic head movement demonstrated. An evolutionary algorithm (EA) has been utilised to search for estimates of the values of the synaptic conductances and also to determine whether each synapse is excitatory or inhibitory in nature. The chemotaxis neural network was designed and implemented, using the parameterisation obtained with the EA, on the Si elegans platform a state-of-the-art hardware emulation platform specially designed to emulate the C. elegans nematode. [ABSTRACT FROM AUTHOR]

Abstract: This paper investigates alternative approaches to conventional metal interconnect for inter-neuron communication in spiking neural networks (SNNs). Two communication methodologies are considered where the first approach uses a time multiplexing architecture (TMA) where neurons on one layer are sampled sequentially and the associated spikes are transmitted to neurons in subsequent layers via a single metal track. Pulse transmission delays occur between neuron layers and the consequence of these delays on the performance of a SNN is investigated. In the second approach, capacitive coupling (CC) between neuron layers is used as the communication method and a model that predicts the dependency of the coupling signals between neuron layers as a function of the neuron density, frequency and track loading is presented. To maximise the available bandwidth and also the number of frequencies that can be utilised, micro-electro-mechanical systems (MEMS) are considered because of their high Q value. Issues such as frequency matching, MEMS processing, fabrication of capacitors and associated oscillator/filter circuits are discussed. The paper investigates both approaches and a comparison between the silicon area occupied by these and conventional metal is given for a 1.5μm CMOS process. [Copyright &y& Elsevier]