Performance analysis for the Feature Extraction algorithm of an ECG signal

An Electrocardiogram is a significant recording for measuring the electrical activity of the heart. The Feature Extraction of an ECG signal plays a significant role in diagnosing most of the cardiac diseases. This paper concentrates on the algorithm for extraction of the fiducial points of an ECG signal and its performance analysis. To analyze these signals, time-frequency domain is the best suited method. In order to analyze these physiological and non-stationary signals, a Wavelet Transform in which Discrete Wavelet Transform is preferred to Fast Fourier and Short time - Fourier transform. A Discrete Wavelet Transform (DWT) is employed for the better understanding of the ECG signal in Time -Frequency plane with (Haar) as a Mother Wavelet function. The Samples are taken from the available ECG databases PTBDB & QTDB and are checked against the CSE tolerance limits. Since, real time signals like ECG can be easily processed using a DSP processor, the algorithm is targeted onto a ADSP - 2181 to reduce the complexity of the code and obtain optimized power levels.