ECG Signal Classification Using DWT, MFCC and SVM Classifier

The diagnosis techniques of diseases which are based on biomedical signals processing are constantly evolving, cardiovascular diseases are no exception to the other biomedical signals. Thanks to the development of signal processing techniques, it has been possible to extract several kinds of information from the ECG signals who told us about the heart's health. The goal of this study is to attempt to create a model based on two methods of signal processing: wavelet analysis and the determination of Mel frequency cepstral coefficients. With the help of this model, it is possible to extract statistical features and MFCC coefficients from approximation coefficients obtained when the discrete wavelet transform (DWT) is applied to analyze an ECG signal. As a result, the various features derived for each approximation coefficient will be classified using a support vector machine classifier (SVM classifier). The classifier's performance has been measured after the use a k fold cross validation technique to avoid the overfitting and the underfitting problems and making the results more reliable and credible.