A Novel Technique for QRS Complex detection in ECG Signal based on Hilbert Transform and Autocorrelation

Abstract

This paper proposes an algorithm for QRS complex detection technique based on Hilbert transform and autocorrelation method. In the proposed method, the period of the ECG signal is calculated first using autocorrelation method and then the R-peaks are detected using Hilbert transform. This method allows R-peaks to be differentiated from large peaked T and P waves with a high degree of accuracy and minimizes the problems associated with baseline drift, motion artifacts, and muscular noise. The performance of the algorithm is evaluated using the records of the MIT-BIH arrhythmia database. A detection error rate of 0.12%, a sensitivity of 99.95% and a positive prediction of 99.94% are achieved for the proposed method. Experimental result shows that the performance of proposed method is better as compared to the other two established techniques like Pan-Tompkins method and the technique which uses only Hilbert transform method.