Fusion Algorithm for Accurate Delineation of QRS Complex in ECG Signal
- 25 Downloads
In this paper, a novel algorithm for the accurate localization of QRS complex with low average time error is proposed. The idea is thought that the various features of ECG signal like P, Q, R, S and T peaks can be independently detected from raw ECG recording and fused together to obtain a better estimate of QRS position. To explore, in this paper, an algorithm is suggested to first estimate R peak and S peak from raw ECG signal and then fused together to detect and localize QRS complex. The algorithm is validated on all the signals of MIT-BIH arrhythmia database, QT database and noise stress database taken from physionet.org. The algorithm performs reasonably well even for the signals highly corrupted with noise, and these noises are generated by adding the power line interference, electrode motion artifact, baseline wandering interference and muscle artifact to all the signals of MIT-BIH arrhythmia database and QT database. The algorithm performance is confirmed not only with a very high sensitivity and positive predictivity, but also with a very low average time error of 0.63 ms against the 3.03 ms the best results reported so far for the signals of MIT-BIH arrhythmia database and 0.85 ms against the 3.6 ms the best results reported in the literature for the signals of QT database.
KeywordsQRS complex localization ECG signal Wavelet transform S peak Fusion algorithm
The authors would like to thank the anonymous reviewers and editor for their valuable comments which helped in improving this manuscript. The authors would also like to thank the Project Supported by the Government of India, Department of Science and Technology under No. SR/WOS-A/ET-1049/2015(G).
- 1.J. Arteaga-Falconi, H. Al Osman, A. El Saddik, R-peak detection algorithm based on differentiation, in 2015 IEEE 9th International Symposium on Intelligent Signal Processing (WISP) (IEEE, 2015), pp. 1–4Google Scholar
- 3.S. Banerjee, M. Mitra, ECG feature extraction and classification of anteroseptal myocardial infarction and normal subjects using discrete wavelet transform, in 2010 International Conference on Systems in Medicine and Biology (ICSMB) (IEEE, 2010), pp. 55–60Google Scholar
- 7.A. Gacek, W. Pedrycz, ECG Signal Processing, Classification and Interpretation: A Comprehensive Framework of Computational Intelligence (Springer, Berlin, 2011)Google Scholar
- 14.P. Laguna, R.G. Mark, A. Goldberg, G.B. Moody, A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG, in Computers in Cardiology 1997 (IEEE, 1997), pp. 673–676Google Scholar
- 19.R. Mark, G. Moody, MIT-BIH Arrhythmia Database Directory (Massachusetts Institute of Technology, Cambridge, 1988)Google Scholar
- 24.R. Polikar, The Wavelet Tutorial (Rowan Univeristy, 1996)Google Scholar
- 27.S. Rezk, C. Join, S. El Asmi, An algebraic derivative-based method for R wave detection, In 2011 19th European Signal Processing Conference (IEEE, 2011), pp. 1578–1582Google Scholar
- 35.L. Zapanta, C.S. Poon, D. White, C. Marcus, E. Katz, Heart rate chaos in obstructive sleep apnea in children, in 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2004 (IEMBS’04), vol. 2 (IEEE, 2004), pp. 3889–3892Google Scholar