QRS Complex Detection Based on Smoothed Nonlinear Energy Operator

摘要

In this work, we present a novel algorithm for QRS complex detection in the Electrocardiogram (ECG) signal. The proposed algorithm is based on a combination of an Infinite Impulse Response (IIR) Filter, a Nonlinear transform termed Smoothed Nonlinear Energy Operator (SNEO) and an efficient simple thresholding process. In our scheme, ButterWorth filter is used to enhance the raw ECG signal and the SNEO is applied to accentuate the QRS complex features. The simulation tests and experimental results carried out on the MIT-BIH Arrhythmia Database show that our proposed approach gives a higher detection performances in comparison with some recently developed techniques with an average Sensitivity (Se) of 99.70%, average Positive Predictivity (P+) of 99.78% and a Detection Error Rate (DER) of 0.52%.