在臨床上，偵測出異常心跳一直是很重要但是卻極具挑戰性的議題。因此本篇提出能夠在心率不整的心電圖中(electrocardiogram, ECG)利用最大似然偵測法(maximum likelihood estimation, ML estimation)找出QRS複合波各個性重要參數的兩階段偵測演算法。此演算法以兩個數學模型與其相對應的貝氏架構(Bayesian framework)來描述ECG訊號，以cyclo-stationary model來描述雜訊干擾及QRS波型變異較小的記錄帶與correlated model對應極度心律不整的ECG訊號，與傳統偵測方法不同的是本篇利用QRS複合波完整波型作偵測，並能得到QRS波所有重要參數，如：QRS複合波起始時間與時間長度、峰值大小，心跳頻率，以及其統計特性，如此一來便能夠將偵測得到的資訊提供給醫療單位作更進一步的診斷分析。
使用MIT-BIH心律不整資料庫所提供的ECG訊號與參考標籤進行模擬及驗證，模擬完的偵測結果有高達99.84%的偵測靈敏度(Sensitivity, Se)，99.86%的預測力(Positive predictivity, P+)以及0.29%很低的偵測失敗率(Failed detection, Fd)。與其他演算法比較後不論考慮到的學習時間，或是長時間偵測，而且不失偵測正確性的話，本論文所提出演算法都是較佳的選擇。

The detection for irregular heartbeat in electrocardiogram (ECG) signal have been an important issue in the past thirty years. This work proposes to estimate the QRS complex parameters under arrhythmia based on the maximum-likelihood (ML) principle. To fulfill this goal, two signal models and their Bayesian frameworks considering highly interference in the waveform are studied. Detectors based on the Bayesian framework are considered to be optimal in the statistical signal processing point of view. The stationarity and non-stationarity heartbeats may exist in the measured records are also considered. To reduce the complexity of original ML estimation, its iterative counterpart is investigated by using the decomposition method. Detail information of QRS complexes, including the starting point, duration, and period, can be derived by the proposed method and can be utilized for further medical diagnosis. Simulations use the benchmark MIT-BIH Arrhythmia database to verify the proposed approaches against traditional ones.

[1] B. U. Köhler, C. Hennig, and R. Orglmeister, “The principles of software QRS detection,” IEEE Eng. Med. Biol. Mag., vol. 21, pp. 42-57, Jan./Feb. 2002.
[2] A. K. Salhan , D. Bansal, and M. Khan, “A review of measurement and analysis of heart rate variability,” International Conference on ICCAE’09, pp.243-246, 2009.
[3] W. J. Tompkins, Biomedical Digital Signal Processing, Prentice Hall International Editions, 1993.
[4] J. Pan and W. J. Tompkins, “A real-Time QRS detection algorithm,” IEEE Trans. Biomed. Eng., pp. 230-236, March 1985.
[5] L. Keselbrener, M. Keselbrener, and S. Akselrod, “Nonlinear high pass filter for R-wave detection in ECG signal,” Med. Eng. Phys., vol. 19, no. 5, pp. 481-484, Ju;. 1997.
[6] Y.-C. Yeh and W.-J. Wang, “QRS complexes detection for ECG signal: The difference operation method,” Comput. Methods Programs Biomed., vol. 91, no. 3, pp. 245-254, Sep. 2008.
[7] S. Luo, T. Q. Nguyen, V. X. Afonso, and W. J. Tompkins, “ECG beat detection using filter banks,” IEEE Trans. Biomed. Eng., vol. 46, no. 2, pp. 192-202, Feb. 1999.
[8] F. Jager and U. Pangerc, “Robust detection of heart beats in multimodal records using slope- and peak-sensitive band-pass filters,” Physiol. Meas., vol. 36, no. 8, pp. 1645-1664, Jul. 2015.
[9] C.S. Burrus, H. Guo, and R.A. Gopinath, Introduction to Wavelets and Wavelet Transforms. Upper Saddle River, NJ: Prentice Hall, 1998.
[10] G. Strang and T. Nguyen, Wavelets and Filter Banks. Cambridge, MA: Wellesley-Cambridge Press, 1996.
[11] C. Li, C. Tai, and C. Zheng, “Detection of ECG characteristic points using wavelet transforms,” IEEE Trans. Biomed. Eng., pp. 21-28, 1995.
[12] M. Bahoura, M. Hassani, and M. Hubin, “DSP implementation of wavelet transform for real time ECG wave forms detection and heart rate analysis,” Comput. Methods Programs Biomed., vol. 52, no. 1, pp. 35-44, Jan. 1997.
[13] G. F. Boudreaux-Bartels, R. Murray, and S. Kadambe, “Wavelet transform-based QRS complex detector,” IEEE Trans. Biomed. Eng., vol. 46, no. 7, pp. 838-848, Jul. 1999.
[14] D. Wei, K. Kitamura, K. Yamakoshi, T. Nemoto, W. Chen, X. Zhu, and Y. Kanemitsu, “Real-time monitoring of respiration rhythm and pulse rate during sleep,” IEEE Trans. Biomed. Eng., vol. 53, no. 12, pp. 2553-2563, Dec. 2006.
[15] J. J. Shynk and K.-C. Lai, “A successive cancellation algorithm for fetal heart-rate estimation using an intrauterine ECG signal,” IEEE Trans. Biomed. Eng., vol. 49, no. 9, pp. 943-954, Sep. 2002.
[16] P. S. Hamilton and W. J. Tompkins, “Adaptive matched filtering for QRS detection,” in Proc. IEEE EMBC’88, pp. 147-148, 1988.
[17] A. Ruha, S. Nissila, and S. Sallinen, “A real-time microprocessor QRS detector system with a 1-ms timing accuracy for the measurement of ambulatory HRV,” IEEE Trans. Biomed. Eng., vol. 44, no. 3, pp. 159- 167, Mar. 1997.
[18] K. G. Lindecrantz and H. Lilja, “New software QRS detector algorithm suitable for real time application with low signal-to-noise ratios,” J. Biomed. Eng., vol. 10, no. 3, pp. 280-284, May 1988.
[19] V. X. Afonso and W. J. Tompkins, “ECG QRS Detection,” Biomedical Digital Signal Processing, pp. 236-264, 1993.
[20] H. S. Ozemek, N. M., Schmitt, and S. E. Dobbs, “QRS detection by template matching using real-time correlation on a microcomputer,” Journal of Clinical Engineering, pp. 197-212, 1984.
[21] G. S. Furno and W. J. Tompkins, "QRS detection using automata theory in a batterypowered microprocessor system," IEEE Frontiers of Engineering in Health Care, pp. 155-158, 1982.
[22] G. Vijaya, H. K. Verma, and V. Kumar, “ANN-based QRS-complex analysis of ECG,” J. Med. Eng. Technol., vol. 22, no. 4, pp. 160-167, Jul. 1998.
[23] C. Marchesi and R. Silipo, “Artificial neural networks for automatic ECG analysis,” IEEE Trans. Signal Process., vol. 46, no. 5, pp. 1417-1425, May 1998.
[24] P. S. Hamilton and W. J. Tompkins, “Quantitative investigation of QRS detection rules using the MIT-BIH arrhythmia database,” IEEE Trans. Biomed. Eng., vol. BME-33, no. 12, pp. 1157-1165, 1986.
[25] L. Pecchia, M. Bracale, and P. Melillo, “Remote health monitoring of heart failure with data mining via CART method on HRV features,” IEEE Trans. Biomed. Eng., vol. 58, no. 3, pp. 800-804, Mar. 2011.
[26] M. A. F. Pimentel, M. D. Santos, D. G. Springer, and G. D. Clifford, “Heart beat detection in multimodal physiological data using a hidden semi-Markov model and signal quality indices,” Physiol. Meas., vol. 36, no. 8, pp. 1717-1727, Jul. 2015.
[27] F. DeBoer, M. Elgendi, and M. Jonkman, “Frequency bands effects on QRS detection,” Third International Conference on Bio-inspired Systems and Signal Processing, Valencia, Spain, January 20-23, 2010.
[28] J. C. Silva, K. V. Suarez, M. Najim, P. Gomis, and Y. Berthoumieu“ECG beat detection using a geometrical matching approach,” IEEE Trans. Biomed. Eng., vol. 54, no. 4, pp. 641-650, Apr. 2007.
[29] D.-G Jang, M. Hahn, S.-H. Park, and U. Farooq “A robust method for pulse beat determination in a digital volume pulse waveform with a wandering baseline,” IEEE Trans. Biomed. Circuits Syst., vol. 8, no. 5, pp. 729-737, Oct. 2014.
[30] “PhysioNet,” [Online]. Available: http://www.physionet.org/.
[31] “MIT-BIH Arrhythmia Database Directory,” [Online]. Available: https://physionet.org/physiobank/database/html/mitdbdir/intro.htm.
[32] B. Li, J. Liao, Max Q.-H. Meng, R. Zhang, X. Fang, and Y. Liu, “Design of a real-time ECG filter for resource constraint computer,” in Proc. IEEE ICIA’12, pp. 846-849, 2012.
[33] A. P. Fitzpatrick, A. Zaidi, D. Benitez, and P. A. Gaydecki, “The use of the Hilbert transform in ECG signal analysis,” Comput. Biol. Med., pp. 399-406, 2001.