Classification of ECG Signal using Wavelet Transform

Abstract: This paper presents a reliable ECG signal analysis and classification approach using Discrete Wavelet Transform. This methodology is made out of three phases, including ECG signal pre-processing, feature selection, and classification of ECG signal. The ECG signal are being selected and tested from Physio Net Database using MIT-BIH Arrhythmia Database. During this paper, a computerized system is presented to categorize the ECG signals. MIT-BIH ECG arrhythmia database is employed for analysis purpose. After de-noising the ECG signal within the pre-processing stage and extract the subsequent time domain features; mean, variance, standard deviation and skewness are extracted within the feature extraction stage.

Keywords: ECG signal, Signal pre-processing, Discrete wavelet transform, Feature extraction and Classification.