Electrocardiogram (ECG) Signal Enhancement Using Genetic Soliton Neural Networks (GSNN)

Abstract

A soliton is a solitary wave whose amplitude, shape, and velocity are conserved after a collision with another soliton. Solitons, in general, manifest themselves in a large variety of wave/particle systems in nature: practically in any system that possesses both dispersion (in time or space) and nonlinearity. Solitons have been identified in optics, plasmas, fluids, condensed matter, particle physics, and astrophysics. Yet over the past decade, the forefront of soliton research has shifted to neuroscience. The Soliton model in neuroscience is a recently developed model that attempts to explain how signals are conducted within neurons. It proposes that the signals travel along the cell's membrane in the form of certain kinds of sound (or density) pulses known as solitons. The electrocardiogram (ECG) signal is generated by the rhythmic contractions of the heart. It represents the electrical activity of the heart muscles, and is usually measured by the electrodes placed on body surface. Electrocardiogram (ECG) signal has been widely used in cardiac pathology to detect heart disease. In this paper, Soliton Feed forward Neural Network (SFNN) is proposed for ECG signal enhancement. Computer simulation results demonstratedthat the proposed approach can successfully be used to model the ECG signal and remove high-frequency noise.