ఇంటర్నేషనల్ జర్నల్ ఆఫ్ స్వార్మ్ ఇంటెలిజెన్స్ అండ్ ఎవల్యూషనరీ కంప్యూటేషన్

నైరూప్య

Training of Multilayer Perceptrons with Improved Particle Swarm Optimization for the Heart Diseases Prediction

Kelwade JP and Salankar SS

The study of Heart rate variability is recently gained momentum for an estimation of heart health. This paper suggests a new approach for enhancement of the prediction accuracy of Multi-Layer Perceptrons (MLP) neural network using improved Particle Swarm Optimization (IPSO) technique. The IPSO computes the weights and biases of MLP for the more accurate prediction of the cardiac arrhythmia classes. This study for heart condition prediction involves selection of Three types of heart signals including Left Bundle Branch Block (LBBB), Normal Sinus Rhythm (NSR), Right Bundle Branch Block (RBBB) from MIT-BIH arrhythmia database, formation of heart rate time series, extraction of features from RR interval time series, implementation of training algorithm and prediction of arrhythmia classes. Several experiments on the proposed training method are carried out to superior the convergence ability of MLP. The experimental results gives comparably better evaluation over gradient based Back-Propagation (BP) learning algorithm.