ECG Signal Classification System Using GA and BPNN

Abstract

The Genetic Algorithm(GA) , Back Propagation Neural Network (BPNN), can be used to
classify electrocardiogram (ECG) beats in the diagnosis of cardiovascular disease. ECG signals are
typically processed as one-dimensional signals while BPNNs are better suited to multidimensional pattern or image recognition applications. In this study, the morphology and rhythm of heartbeats are fused into a two-dimensional information vector for subsequent processing by BPNN s that include adaptive learning rate and biased dropout methods. The results demonstrate that the proposed BPNN model is effective for detecting irregular heartbeats or arrhythmias via the automatic feature extraction. When the concept was tested on the MIT-BIH arrhythmia database, the model achieved higher performance than other state-ofthe- art methods for five and eight heartbeat categories . A condition of abnormal electrical activity in the heart which is a threat to humans is shown by this electrocardiogram. It is a representative signal containing information about the condition of the heart of the P-QRS-T wave shape and size and their time intervals between its various peaks these are all contain useful information about the nature of disease affecting the heart.