A Novel Hybrid Model Based on Convolutional Neural Network With Particle Swarm Optimization Algorithm for Classification of Cardiac Arrhythmias

An electrocardiogram (ECG) is a non-invasive study used for the diagnosis of cardiac arrhythmias (CAs). The identification arrhythmia depends on its classification. This classification has been approached through different strategies, both mathematical and computational. In this work, new computational model based particle swarm optimization (PSO) algorithm convolutional neural network (CNN) proposed five classes CAs obtained from MIT-BIH Arrhythmia Dataset (MITDB). goal PSO to optimize hyperparameters that define layered architecture CNN, increase accuracy decrease categorical cross-entropy error (CE). found satisfactory in 17.68 hours, obtaining an 98% 97%, CE 0.044968 0.084768, training testing, respectively. These results demonstrate reliable represents innovative approach because it allows dispensing with manual selection CNN.