ECG beat classification using discrete wavelet coefficients

In this work we have developed a new approach to identify different types of electrocardiogram (ECG) beats using discrete wavelet transform (DWT) coefficients. The purpose of the study is to develop a simple algorithm for the diagnosis of some cardiac abnormalities. Five types of cardiac phenomena are considered and for each of these some particular records from the MIT-BIH Arrhythmia Database are selected. For these records DWT coefficients up to level 4 are calculated in the Matlab 7.4.0 environment, using different types of mother wavelets. The maximum value of the approximation coefficients of level 4 is selected as the indicating parameter, which is used to distinguish between different abnormalities. A comparison is made between the performances of different types of mother wavelets to select the mother wavelet providing the best result.