Search

A novel algorithm for producing smooth nonlinearities on digital hardware is presented. The non-linearities are inherently quadratic and have both symmetrical and asymmetrical variants. The integer (and fixed point) implementation is highly amenable for use with digital gates on an ASIC or FPGA. The implementations are multiplier-less. Scaling of the non-linear output, as required in an LSTM cell, is integrated into the implementation. This too does not require a multiplier. The non-linearities are useful as activation functions in a variety of ANN architectures. The floating point mappings have been compared with other non-linearities and have been benchmarked. Results show that these functions should be considered in the ANN design phase. The hardware resource usage of the implementations have been thoroughly investigated. Our results make a strong case for implementions in edge applications. This document summarizes the findings and serves to give a quick overview of the outcomes of our research\footnote{The authors peer-reviewed manuscripts (available at https://doi.org/10.1016/j.neucom.2021.02.030) offer more detail and may be better suited for a thorough consideration}., Comment: 8 pages, 13 figures, summary paper

A novel two-dimensional (2D) learning framework has been proposed to address the feature selection problem in Power Quality (PQ) events. Unlike the existing feature selection approaches, the proposed 2D learning explicitly incorporates the information about the subset cardinality (i.e., the number of features) as an additional learning dimension to effectively guide the search process. The efficacy of this approach has been demonstrated considering fourteen distinct classes of PQ events which conform to the IEEE Standard 1159. The search performance of the 2D learning approach has been compared to the other six well-known feature selection wrappers by considering two induction algorithms: Naive Bayes (NB) and k-Nearest Neighbors (k-NN). Further, the robustness of the selected/reduced feature subsets has been investigated considering seven different levels of noise. The results of this investigation convincingly demonstrate that the proposed 2D learning can identify significantly better and robust feature subsets for PQ events.

The present study applies a novel two-dimensional learning framework (2D-UPSO) based on particle swarms for structure selection of polynomial nonlinear auto-regressive with exogenous inputs (NARX) models. This learning approach explicitly incorporates the information about the cardinality (i.e., the number of terms) into the structure selection process. Initially, the effectiveness of the proposed approach was compared against the classical genetic algorithm (GA) based approach and it was demonstrated that the 2D-UPSO is superior. Further, since the performance of any meta-heuristic search algorithm is critically dependent on the choice of the fitness function, the efficacy of the proposed approach was investigated using two distinct information theoretic criteria such as Akaike and Bayesian information criterion. The robustness of this approach against various levels of measurement noise is also studied. Simulation results on various nonlinear systems demonstrate that the proposed algorithm could accurately determine the structure of the polynomial NARX model even under the influence of measurement noise.

This paper proposes a new generalized two dimensional learning approach for particle swarm based feature selection. The core idea of the proposed approach is to include the information about the subset cardinality into the learning framework by extending the dimension of the velocity. The 2D-learning framework retains all the key features of the original PSO, despite the extra learning dimension. Most of the popular variants of PSO can easily be adapted into this 2D learning framework for feature selection problems. The efficacy of the proposed learning approach has been evaluated considering several benchmark data and two induction algorithms: Naive-Bayes and k-Nearest Neighbor. The results of the comparative investigation including the time-complexity analysis with GA, ACO and five other PSO variants illustrate that the proposed 2D learning approach gives feature subset with relatively smaller cardinality and better classification performance with shorter run times.

Virtual heart models have been proposed to enhance the safety of implantable cardiac devices through closed loop validation. To communicate with a virtual heart, devices have been driven by cardiac signals at specific sites. As a result, only the action potentials of these sites are sensed. However, the real device implanted in the heart will sense a complex combination of near and far-field extracellular potential signals. Therefore many device functions, such as blanking periods and refractory periods, are designed to handle these unexpected signals. To represent these signals, we develop an intracardiac electrogram (IEGM) model as an interface between the virtual heart and the device. The model can capture not only the local excitation but also far-field signals and pacing afterpotentials. Moreover, the sensing controller can specify unipolar or bipolar electrogram (EGM) sensing configurations and introduce various oversensing and undersensing modes. The simulation results show that the model is able to reproduce clinically observed sensing problems, which significantly extends the capabilities of the virtual heart model in the context of device validation.

The heart is a vital organ that relies on the orchestrated propagation of electrical stimuli to coordinate each heart beat. Abnormalities in the heart's electrical behaviour can be managed with a cardiac pacemaker. Recently, the closed-loop testing of pacemakers with an emulation (real-time simulation) of the heart has been proposed. An emulated heart would provide realistic reactions to the pacemaker as if it were a real heart. This enables developers to interrogate their pacemaker design without having to engage in costly or lengthy clinical trials. Many high-fidelity heart models have been developed, but are too computationally intensive to be simulated in real-time. Heart models, designed specifically for the closed-loop testing of pacemakers, are too abstract to be useful in the testing of physical pacemakers. In the context of pacemaker testing, this paper presents a more computationally efficient heart model that generates realistic continuous-time electrical signals. The heart model is composed of cardiac cells that are connected by paths. Significant improvements were made to an existing cardiac cell model to stabilise its activation behaviour and to an existing path model to capture the behaviour of continuous electrical propagation. We provide simulation results that show our ability to faithfully model complex re-entrant circuits (that cause arrhythmia) that existing heart models can not.