Spectrum approach based hybrid classifier for classification of ECG signal

Heart is one of the crucial parts of a human being. The heart produces electrical signals and these signals are called cardiac cycles. The graphical recording of these cardiac cycle produced by an Electrocardiograph is called as Electro cardio gram (ECG) signal. In this work an algorithm has been developed to detect the five abnormal beat signals which includes Left bundle branch block beat (LBBB), Right bundle branch block beat (RBBB), Premature Ventricular Contraction (PVC), Atrial Premature Beat (APB) and Nodal (junction) Premature Beat (NPB) along with the normal beat. In order to prepare an appropriate input vector for the neural classifier several pre processing stages have been applied. Tri spectrum is used to extract features from the ECG signal. Hybrid classifier is used to classify the ECG beat signal. Hybrid classifier use both ABC algorithm and genetic algorithm to train the beat signals in the neural network. Finally, the MIT-BIH [1] database is used to evaluate the proposed algorithm. The beat classification system gives an accuracy of 71%, sensitivity 67% and specificity 79%.