A Comparative Study of ECG Beats Variability Classification Based on Different Machine Learning Algorithms

The electrocardiogram (ECG) signal is a method that uses electrodes to record cardiac rates along with sensing minute electrical fluctuations for each cardiac rate. The information is utilized to analyze abrupt cardiac function like arrhythmias and conduction disturbance. The paper proposes strategy classifying ECG signal using various technique. The preprocessing stage includes filtering of input signal via low pass, high pass including Butterworth filter in order to remove clamour of high frequency. From signal, the excess clamour is sliced by Butterworth filter. The peak points are detected by peak detection algorithm, and the signal features are extracted using statistical parameters. At last, extracted feature classification is done via GWO-MSVM, SVM, Adaboost, ANN and Naive Bayes classifier to classify the ECG signal database into normal or abnormal ECG signal. The experimental result indicates the precision of the GWO-MSVM, SVM, Adaboost, ANN and Naive Bayes classifier is 99.9%, 94%, 93%,87.57% and 85.28%. When compared with other classifier, it was determined that precision of GWO-MSVM classifier is high.