QRS detection based on matching pursuit algorithm

Abstract

The QRS complex is the most significant feature of the electrocardiogram (ECG). This paper introduces a novel algorithm for detection of QRS complexes in ECG based on matching pursuit algorithm (MPA). To recognize QRS Complex regions, time-frequency map of the ECG signal is plotted. Then the correct QRS regions are detected using the map. The performance of the algorithm is evaluated on ECG signals recorded in Bioinstruments Lab at Sahand University of Technology. The results indicate that the proposed method achieves 99.92% of sensitivity and 99.85% of specificity. The percentage of detected error rate is 0.223%. The efficiency of the algorithm in the presence of noise and corruption in ECG is also investigated.