A New Technique of ECG Feature Extraction and Classification by Wavelet Transform and ANFIS

An electrocardiograph (ECG) is a plot of bioelectrical signal of heart. It records the electrical activity of heart versus time. It is an important diagnostic tool for assessing heart functions. In this paper, Discrete Wavelet Transform (DWT) is used to extract relevant information from the ECG data in order to perform the classification. Wavelets provide efficient localization in both time and frequency. DWT can be used as a valuable tool for non-stationary ECG signal detection. For the classification scheme, the Adaptive Neuro-Fuzzy Interference System (ANFIS) is trained with backpropogation gradient descent method in combination with the least square method. In this work, wavelet and fuzzy logic toolbox are used in MATLAB environment. The processed signal source is obtained from the Massachusetts Institute of Technology Beth Israel Hospital (MIT-BIH) arrhythmia database which was developed for research in cardiac electrophysiology. The results obtained indicate a good prediction accuracy (of 94.25%) validating the choice of the combined use of the current popular techniques for cardiac arrhythmia classification.