A COMPARATIVE STUDY AND ANALYSIS ON THE CLASSIFICATION OF ECG SIGNALS

Abstract

Electrocardiogram (ECG) is a method used to measure the rate and regularity of heartbeats. Comparison of overall ECG waveform pattern and shape enables doctors to diagnose possible diseases. Currently there is computer based analysis which employs certain signal processing to diagnose a patient based on ECG recording. Signal processing usually takes the form of a transformation of a signal into another signal that is in some sense more desirable than the original. The purpose of this research is to address in identifying the Normal, Apnea, Tachycardia and Ischemia signals using the method of Principal Component Analysis (PCA) and various classifiers i.e. Support Vector Machine (SVM), Artificial Neural Networks (ANN), Fuzzy Logic and a hybrid of ANN and Fuzzy Logic called as Neuro-Fuzzy Logic. PCA algorithm is used to extract the relevant information from the ECG input data which are their P-QRS-T parameters values. Then the extracted features data is analyzed and classified using Support Vector Machine (SVM), Artificial Neural Networks (ANN), Fuzzy Logic and a hybrid of ANN and Fuzzy Logic called as Neuro-Fuzzy Logic classifiers. The proposed algorithm is implemented and also tested in MATLAB software. The ECG signal are being selected and tested from PhysioNet Database using MIT-BIH Arrhythmia Database. Among the classifiers utilized during this project, Neuro-Fuzzy classifier successfully classifies the Normal, Apnea, Tachycardia and Ischemia signals with the rate of accuracy is 95.83%. The analysis system also can be achieved using rest of the classifiers such as Fuzzy Logic, ANN and SVM with accuracies of 91.70%, 87.50% and 85.40% respectively for each sample tested of Normal, Apnea, Tachycardia and Ischemia classes proposed.