Design of a Low-Complexity Real-Time Arrhythmia Detection System
- 145 Downloads
This paper presents a low-complexity real-time arrhythmia detection system that includes the QRS complex and arrhythmia detection. The ECG data in the MIT-BIH arrhythmia database were used for simulations and verification. For QRS complex detection, this paper proposes the advanced So and Chan for detecting the R-peak and baseline of the QRS complex. Compared with the accuracy obtained using the original So and Chan method (94.61%), an accuracy of 99.29% was obtained using the advanced So and Chan method. For arrhythmia detection, the proposed system is implemented with an advanced sum of trough and various features of disease symptoms. It can identify tachycardia, bradycardia, premature contraction, and two types of cardiovascular diseases; its detection accuracy can reach 98.05%. If a morbid state occurs, a warning message will be sent to a user. Because of its low complexity, the proposed detection system can be integrated with wearable electronic devices for detecting an arrhythmia immediately.
KeywordsECG QRS complex CVD So and Chan
- 1.Alptekin, O., & Akan, A. (2010). Detection of some heart diseases by the analysis of ECG signals. In Signal Processing and Communications Applications Conference (SIU)(pp. 716–719). 716–719.Diyarbakir, 22–24 April. doi: 10.1109/SIU.2010.5654437
- 4.Hu, Y. H., Tompkins, W. J., Urrusti, J. L., & Afonso, V. X. (1993). Applications of artificial neural networks for ECG signal detection and classification. Journal of Electrocardiology, 26(1), 67–73.Google Scholar
- 6.Martínez , J. P., Olmos, S., ∓ P. Laguna, (2000). Evaluation of a wavelet-based ecg waveform detector on the qt database. In Computers in Cardiology. Los Alamitos, CA: IEEE Computer Society Press, pp. 81–84Google Scholar
- 7.Qiu, Y., Ding, X., Feng, J., & Mo, Z. (2006). QRS complexes detection based on Mexican-hat wavelet. Journal of Biomedical Engineering, 23(6), 1347–1349.Google Scholar
- 8.Chiu, C. C., Lin, T. H., & Liau, B. Y. (2005). Using correlation coefficient in ECG waveform for arrhythmia detection. Biomedical Engineering: Applications, Basis and Communications, 17(3), 147–152.Google Scholar
- 9.Fejtová, M., Macek, J., Lhotská, L. (2001) ECG events detection and classification using wavelet transform and decision trees. In Final Programme & Proceedings EUNITE, (pp 99-101). Aachen: VerlagGoogle Scholar
- 11.Gomes, P.R., Soares, F.O., Correia, J.H. Lima, C.S. (2009) Cardiac arrhythmia classification using wavelets and hidden Markov models-A comparative approach. In Annual International Conference of IEEE Engineering in Medicine and Biology Society (EMBS), 4727–4730. Minneapolis, Minnesota, USA, September 2–6. doi: 10.1109/IEMBS.2009.5334192
- 12.Paul, J.S., Reddy,M.R.S., Kumar, V.J. (1997). Automatic detection of PVC’s using autoregressive models. In Annual International Conference of IEEE Engineering in Medicine and Biology Society (EMBS), pp 68–71. Chicago, IL, 30 Oct.–2 Nov. doi: 10.1109/IEMBS.1997.754465.
- 13.Zhao, L., Wiggins, M., Vachtsevanos, G. (2003). Premature ventricular contraction beat detection based on symbolic dynamics analysis. In International Conference on Circuits, Signals and Systems (CSS)(pp. 48–50). Cancun, Mexico, 19-21 May.Google Scholar
- 14.Nahar, S., ShahNoor bin Munir, M. (2009). Automatic detecion of premature ventricular contraction beat using morphological transformation and cross-correlation. In International Conference on Signal Processing and Communication Systems (ICSPCS) (pp. 1–4). Omaha, NE, 28–30 Sept. doi: 10.1109/ICSPCS.2009.5306426
- 16.Shen, Z.,Hu, C.,Liao,J.,& Meng, M.Q.-H.(2010).Analgorithm of premature contraction detection based on wavelet method. In International Conference on Information and Automation (ICIA) (pp.1053– 1058). Harbin, 20 – 23 June. doi: 10.1109/ICINFA.2010.5512157
- 19.Mark, R.G., Schluter, P.S.,Moody, G.B., Devlin, P.H., Chernoff, D. (1982). An annotated ECG database for evaluating arrhythmia detectors. In Annual International Conference of IEEE Engineering in Medicine and Biology Society (EMBS) (pp. 205–210). IEEE Computer Society Press, Los Alamitor, CA.Google Scholar
- 20.So, H.H., Chan, K.L. (1997). Development of QRS detection method for real-time ambulatory cardiac monitor. In Annual International Conference of IEEE Engineering in Medicine and Biology Society (EMBS), (pp. 289–292). Chicago, IL, 30 Oct.–2 Nov. doi: 10.1109/IEMBS.1997.754529.
- 22.Lee, R. G., Chen, C. C., Tsai, P. Y., & Yang, K. Y. (2004). A portable tele-emergent system supporting electrocardiogram (ECG) discrimination. Journal of National Taipei University Technology, 37(1), 205–213.Google Scholar
- 23.Su, S.H. (2013). Fatigue detection system using enhanced So and Chan method, Thesis of NCHUEE. http://nchuir.lib.nchu.edu.tw/handle/309270000/154671
- 24.Mark, J. B. (1998). Atlas of cardiovascular monitoring (p. 130). New York: Churchill Livingstone.Google Scholar
- 26.Dinh, H.A.N., Kumar, D.K., Pah, N.D., Burton, P. (2001). Wavelets for QRS detection. In Annual International Conference of IEEE Engineering in Medicine and Biology Society (EMBS), (1883–1887). 25-28 October 2001 Istanbul, Turkey. doi: 10.1109/IEMBS.2001.1020593.
- 27.Li, Y., Chen, X. (2011). A robust R-wave detection algorithm in ECG signal. In International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), (pp. 2433–2436). 16-18 Dec. 2011. Changchun, China. doi: 10.1109/TMEE.2011.6199713.
- 28.Pachauri, A., Bhuyan, M. (2009). Wavelet and energy based approach for PVC detection. In International Conference on Emergin Trends in Electronic and Photonic Devices & Systems, (pp. 258–261). 22–24 Dec. 2009 Varanasi. doi: 10.1109/ELECTRO.2009.5441123.