Cardiac Abnormality Prediction using Logsig-Based MLP Network

Abstract

Regardless of gender, age, or ethnicity, anyone can get cardiac illness. However, the likelihood of intermediate heart failure is very well predicted by family history. Cardiovascular abnormalities, which rarely show early symptoms, cause patients to die suddenly. The electrical activity or surge that makes up the heartbeat is usually erratic. The Multilayer Perceptron (MLP) network is used in this study as an early detection method for cardiac issues. Using a number of training techniques using Logsig as the MLP network's activation function, the cardiac anomaly dataset from the MIT-BIH database is used to train the chosen MLP network. According to the study, the MLP network's BR training strategy outperformed other strategies with mean square errors (MSE) of 0.0212 and regression performance of 0.9867.