Design and analysis of feature extraction algorithm for ECG signals using adaptive threshold method

Automatic External Defibrillator is a device that checks the heart rhythm and can send an electric shock to the heart muscle to restore the rhythm. Electric shock will be given in the case of abnormal heart which in termed as Arrhythmia. Cardiac Arrhythmias shows a condition of abnormal electrical activity in the heart which is a threat to humans. There are various algorithms proposed for the detection and classification of arrhythmia such wavelet transforms, Hilbert transform etc. Among these methods time domain analysis is simple with reduced complexity. This paper presents a feature extraction method in time domain for ECG feature extraction using adaptive threshold method for the detection of various peaks and classification of various heart conditions. This is achieved by extracting ECG features such as P, T wave, QRS complex, PR, QT, RR, ST intervals and ST segment deviations for the classification of heart beats according to different arrhythmias. Data were obtained from the records of MIT-BIH arrhythmia database (only one lead). Cardiac arrhythmias which are found are Tachycardia, Supraventricular Tachycardia and Ventricular Fibrillation.