Classification of ECG Signal by Using Wavelet Transform and SVM

ABSTRACT: Advances in computing have resulted in many engineering processes being automated. Electrocardiogram (ECG) classification is one such process. The analysis and classification of ECGs can benefit from the wide availability and power of modern computers. This study presents a method on the usage of computer technology in the field of computerized ECG classification. Computerized electrocardiogram classification can help to reduce healthcare costs by enabling suitably equipped general practitioners to refer to hospital only those people with serious heart problems. Computerized ECG classification can also be very useful in shortening hospital waiting lists and saving life by discovering heart diseases early. This thesis investigates the automatic classification of ECGs into different disease categories using Discrete Wavelet Transform (DWT) and Support Vector Machine (SVM) techniques. The ECG data is taken from standard MIT-BIH database. The model is developed over 20 records of MIT arrhythmia database signals of which is 30 minutes of recording time. A comparison of the use of different feature sets and SVM classifiers is presented. The feature sets include wavelet features, as well as temporal features which taken directly from time domain samples of an ECG. Keywords: ECG, Discrete Wavelet Transform, Support Vector Machine, Arrhythmia. …………………………………………………………………………………………………………………………