A Novel Algorithm for Quick QRS Complex Detection in ECG Based On Discrete Wavelet Transform

This paper presents an algorithm based on the discrete wavelet transform, for feature extraction from the ElectroCardioGraph (ECG) signal and recognition of abnormal heart beats. Wavelets provide simultaneous time and frequency information. The new algorithm detects the R waves as well as Premature Ventricular Contraction (PVC) waves in the ECG signal. The wavelet transform decomposes the ECG signal into a set of frequency band. By using wavelet decomposition, we reduced the amount of data necessary to be processed by the algorithm to less than ten percent of the original data. The adaptive threshold algorithm is implemented with a value greater than that of R waves and less than the value of PVC. For the standard 24 hour Massachusetts Institute of Technology/Beth Isrel Hospital (MIT-BIH) arrhythmia database, this algorithm correctly detects 99.4 percent of the QRS complexes.