Classification of Cardiac Arrhythmia Using WT, HRV, and Fuzzy C-Means Clustering

The classification of the electrocardiogram registration into different pathologies disease devisesis a complex pattern recognition task. In this paper, we propose a generic feature extraction forclassification of ECG arrhythmias using a fuzzy c-means (FCM) clustering and Heart Ratevariability (HRV). The traditional methods of diagnosis and classification present someinconveniences; seen that the precision of credit note one diagnosis exact depends on thecardiologist experience and the rate concentration. Due to the high mortality rate of heartdiseases, early detection and precise discrimination of ECG arrhythmia is essential for thetreatment of patients. During the recording of ECG signal, different forms of noise can besuperimposed in the useful signal. The pre-treatment of ECG imposes the suppression of theseperturbation signals. The row date is preprocessed, normalized and then data points areclustered using FCM technique.In this work, four different structures, FCM-HRV, PCM-HRV, FCMC-HRV and FPCM-HRV areformed by using heart rate variability technique and fuzzy c-means clustering. In addition, FCMHRVis the new method proposed for classification of ECG.This paper presents a comparative study of the classification accuracy of ECG signals by usingthese four structures for computationally efficient diagnosis. The ECG signals taken from MIT-BIHECG database are used in training to classify 4 different arrhythmias (Atrial FibrillationTermination).All of the structures are tested by using the same ECG records. The test results suggest thatFCMC-HRV structure can generalize better and is faster than the other structures.