EKF with PSO technique for delineation of P and T wave in electrocardiogram(ECG) signal

The automated detection and delineation of P and T waves in an electrocardiogram (ECG) is a challenging task in biomedical signal processing community, because of its low amplitude, high gradient of noise and lack of universal delineation rule. In this paper, we have investigated the effectiveness of particle swarm optimization (PSO) with extended Kalman filter (EKF) in order to detect and delineate P and T wave in an ECG. PSO is used for selection of optimized parameters which are required to model the ECG signal and also to initialize parameters of EKF. EKF frame work is used to denoise the raw ECG signal and to detect the peak of P and T wave. Finally square operation is used for delineation of P and T wave. Our algorithm has been successfully verified using one realtime ECG database namely QT database.