Independent component analysis with learning algorithm for electrocardiogram feature extraction and classification

Abstract

Electrocardiogram (ECG) analysis is a conventional way of finding heart abnormality. It is a clinical procedure in which the electrical activity of the heart is measured during every cardiac cycle and checked for healthiness of the heart. It is approximated in this industrialized world that millions of people expire every 12 months because of various coronary heart diseases and short of prompt detection of uncharacteristic heart rhythms. To detect these abnormalities promptly, the ECG measures should provide the cardiac signals without any mixtures or other disturbances. Though accurate classification of ECG is a challenging task as it varies with time and also with persons of different ages, it is the need of the hour. In this proposed research work, an improved independent component analysis (ICA) algorithm is used to extract pure ECG components from the ECG mixtures before the signals are applied to machine learning classifiers for accurate detection and classification of ECG signals. These machine learning models are applied after the signals are preprocessed to reduce the dimensionality and the training time. This work also uses deep learning convolution neural network (CNN) model with different optimizers for ECG classification and analysis. Classification performance of these algorithms is improved when classification is done after extracting the features using ICA technique.