R-Peak Detection from ECG Signals Using Fractal Based Mathematical Morphological Operators

Abstract

The Electrocardiogram (ECG) signal is used to detect cardiac abnormalities by measuring the heart's electrical activity. ECG constitutes the fiducial points P-wave, QRS complex, and T-wave. The QRS complex is the most striking waveform that comprises Q-wave, R-peak, and S-wave. This paper presents a simple, reliable, and intuitive algorithm that meets the clinical needs for real-time R-peak detection using Fractals. The proposed method preprocesses raw ECG signal to remove powerline interference and baseline wander from noisy ECG signal, followed by area calculation using mathematical morphological operators such as erosion and dilation. These operators are implemented using dynamic programming with memoization that helps in achieving accurate results in a shorter duration. The area curve is then resampled and hard thresholded to produce R-peaks. The method achieved a Sensitivity of 95.78%, Positive Predictivity of 97.53%, and a Detection Error Rate of 8.44% on the MIT-BIH Arrhythmia Database. The proposed method is highly effective for realtime applications considering the fast and low computational complexity of fractals.