Detection of Heart Diseases by Analysing QRS Complex

In this paper, we propose a novel method for the detection of heart diseases. It is proposed to develop an automated system for the classification of heart diseases. The proposed system includes pre-processing, peak detection, feature extraction, feature selection and classification. In pre-processing, the noise removal is done and then peak detection of input ECG signal is performed. The peak detection process is used to detect the peaks in the ECG signal. It is for the detection of QRS complex, QRS interval, from the ECG signal. Then, many time domain and frequency domain features are extracted and some among them are selected for the classification of heart diseases. This proposed system may be helpful for the clinical diagnosis of heart diseases like Ventricular Arrhythmias, Atrial Fibrillation and Atrial flutter.