Recognition and Evaluation of Heart Arrhythmias via a General Sparse Neural Network

Abstract

In clinical use, an electrocardiogram (ECG) is an essential medical tool for assessing heart arrhythmias. Thousands of human beings worldwide are affected by different cardiac problems nowadays. As a consequence, studying the features of the ECG pattern is critical for detecting a wide range of cardiac diseases. The ECG is a test which assesses the intensity of the electrical impulses in the circulatory system. In the present investigation, detection and examination of arrhythmias in the heart on the system using GSNNs (General sparsed neural network classifier) can be carried out[1]. In this paper, the methodologies of support vector regression(SVR), neural mode decomposition(NMD), Artificial Neural Network (ANN), Support Vector Machine(SVM) and are examined. To assess the suggested structure, three distinct ECG waveform situations are chosen from the MIT-BIH arrhythmia collection. The main objective of this assignment is to create a simple, accurate, and simply adaptable approach for classifying the three distinct heart diseases chosen. The wavelet transform Db4 is used in the present paper to obtain several features from an ECG signal. The suggested setup was created using the MATLAB programme. The algorithms suggested are 98% accurate for forecasting cardiac arrhythmias, which is greater than prior techniques.