實驗數據(辨識架構三)

為了使 NORM 及 BBB 類型的心電圖信號能夠達到最佳的辨識效果，故第三種心電 圖信號辨識架構即利用了 NORM、LBBB 與 RBBB，其 QTP-int 這項特徵值的值域分布，

來對 NORM 與 BBB 類型的心電圖信號，做到完全的分類，其完整的實驗數據，如以下 表格 5.25 所示。

表格 5.25 實驗辨識結果(架構三) 判讀結果

信號種類 NORM BBB APC PVC

NORM 1800 0 0 0

BBB 0 3900 0 0

APC 0 0 1197 3

PVC 0 0 4 296

TP FP FN Se (%) PPV (%) TCA (%)

NORM 1800 0 0 100 100

99.9

RBBB 3900 0 0 100 100

APC 1197 4 3 99.75 99.67

PVC 296 3 4 98.67 99

圖 5.6 Se 數據比較圖(架構三)

圖 5.7 PPV 數據比較圖(架構三)

由以上兩個辨識指標的比較圖便可得知，第三種心電圖信號辨識架構的策略，達成 了在 NORM、BBB、APC 及 PVC 類型的心電圖信號上，皆具有極佳辨識效果之目的，

故為這四種類型的心電圖信號，提供了一個可靠且具效率的辨識方法。

第六章 結論

本論文提出以隱藏式馬可夫模型(HMM)進行心電圖信號的辨識，從心臟構造及心 臟基本功能開始介紹，到認識心電圖信號中的重要波型，並進一步利用這些波型的資 訊，來計算心電圖特徵值，最後，利用這些特徵值來訓練 HMM 模型並進行心電圖信號 的辨識，此外，本論文中採取的是非固定特徵值的 HMM 模型，即針對不同類型的心電 圖信號之辨識，將使用不同種類及數量的心電圖特徵值來進行 HMM 模型的訓練及辨 識，此外，本論文更提出了多種不同的辨識架構，這樣具有彈性的作法，不僅使 HMM 模型的訓練及辨識速度獲得提升，同時也有助於增進辨識的正確率，因此，對於心電圖 信號的辨識來說，HMM 可說是提供了一個快速且可靠的方式。

由於在本論文所進行的實驗中發現到，使用 HMM 進行心電圖信號辨識時，對於 LBBB 與 RBBB 這兩種心電圖信號類型的辨識成果，仍具有改善空間，而造成這樣現象 的原因，則可能為目前所採用之心電圖特徵值集合，並非最佳的心電圖特徵值組合，故 在未來的研究方向部分，應朝向針對不同的心電圖信號類型其重要波型的資訊，設計出 更適合的心電圖特徵值，來建構出更有效的心電圖特徵值集合，以進行 HMM 模型的訓 練以及辨識，而達到提升辨識率的效果。

參考文獻

[1] A. Kadish, “ACC/AHA Clinical Competence Statement on Electrocardiography and Ambulatory Electrocardiography,” J. Am. Coll. Cardiol., vol. 38, no. 7, 2001.

[2] Yun-Chi Yeh, Wen-June Wang, and Che-Wun Chiou, “Heartbeat Case Determination Using Fuzzy Logic Method on ECG Signals,” International Journal of Fuzzy Systems, Vol. 11, No. 4, December 2009.

[3] L. A. Zadeh, Fuzzy Sets as a Basis for a Theory of Possibility, Fuzzy Sets and Systems 1, 1978.

[4] Z. Dokur, T. Olmez, E. Yazgan, and O. K. Ersoy, “Detection of ECG Waveforms by Neural Networks,” Med. Eng. Phys., vol. 19, pp. 738-741, 1997.

[5] Z. Dokur, and T. Olmez, “ECG Beat Classification by a Novel Hybrid Neural Network,”

Computer Methods and Programs in Biomedicine, vol. 66, pp. 167-181, 2001.

[6] H. G. Hosseini, D. Luo, and K. J. Raynolds, “The Comparison of Different Feed Forward Neural Network Architectures for ECG Signal Diagnosis,” Med. Eng. Phys., vol. 28, pp. 372-378, 2006.

[7] Y. P. Meau, F. Ibrahim, S. A. L. Narainasamy, and R. Omar, “Intelligent Classification of ECG Signal Using Extended EKF Based Neural Fuzzy System,” Computer Methods and Programs in Biomedicine, vol. 82, pp. 157-168, 2006.

[8] I. Christov, G. Gómez-Herrero, V. Krasteva, I. Jekova, A. Gotchev, and K. Egiazarian,

“Comparative Study of Morphological and Time-Frequency ECG Descriptors for Heartbeat Classification,” Med. Eng. Phys., vol. 28, pp. 876-887, 2006.

[9] P. Chazal, M. O’Dwyer, and R. B. Reilly, “Automatic Classification of Heart-beats Using ECG Morphology and Heartbeat Interval Features,” IEEE Trans. on Biomed. Eng., vol. 51, pp. 1196-1206, 2004.

[10] A. Koski, “Modelling ECG Signals With Hidden Markov Models,” Artif. Intell. Med., vol. 8, pp. 453-471, 1996.

[11] MIT-BIH Database Distribution, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139, 1998.

[12] R. M. Rangayyan, Biomedical Signal Analysis: A Case-Study Approach, New York:

Wiley, Inter-Science, 2001.

[13] P. Blunsom, “Hidden Markov Model,” The University of Melbourne, Department of Computer Science and Software Engineering, 19th August 2004.

URL: http://www.cs.mu.oz.au/460/2004/materials/hmm-tutorial.pdf

[14] X. Huang, A. Acero, and H. Wuenon, Spoken Language Processing A Guide to Theory, Algorithm and System Development, Pearson, 2005.

[15] P. Bajpai and S. N. Singh, “Fuzzy Adaptive Particle Swarm Optimization for Bidding Strategy in Uniform Price Spot Market,” IEEE Transactions on Power Systems, vol. 22, No. 4, 2007.

[16] I. Jekova, G. Bortolan, and I. Christov, “Assessment and Comparison of Different Methods for Heartbeat Classification,” Medical Engineering and Physics, vol. 30, pp.

248-257, 2008.

[17] T. Mar, S. Zaunseder, J. P. Martinez, M. Llamedo, and R. Poll, “Optimiztion of ECG Classification by Means of Feature Selection,” IEEE Trans. on Biomed. Eng., vol. 58, no. 8, pp. 2168-2177, 2011.

[18] J. Dai, “Hybrid Approach to Speech Recognition Using Hidden Markov Models and Markov Chains,” IEE Proc.-Vis. Image Signal Process., vol. 141, pp. 273-279, 1994.

[19] K. S. Lee, “EMG-Based Speech Recognition Using Hidden Markov Models With Global Control Variables,” IEEE Trans. on Biomed. Eng., vol. 55, pp. 930-940, 2008.

[20] V. Krishnamurthy, J. B. Moore, and S. H. Chung, “Hidden Markov Model Signal

Automatic Control, vol. 38, no. 1, pp. 146-152, 1993.

[21] M. S. Crouse, R. D. Nowak, and R. G. Baraniuk, “Wavelet-Based Statistical Signal Processing Using Hidden Markov Models,” IEEE Trans. on Signal Processing, vol. 46, no. 4, pp. 886-902, 1998.

[22] D. J. Miller, and M. S. Park, “A Sequence-Based Approximate MMSE Decoder for Source Coding Over Noisy Channels Using Discrete Hidden Markov Models,” IEEE Trans. on Communications, vol. 46, no. 2, pp. 222-231, 1998.

[23] Y. Bengio, V. P. Lauzon, and R. Ducharme, “Experiments on the Application of IOHMMs to Model Financial Returns Series,” IEEE Trans. on Neural Networks, vol. 12, no. 1, pp. 113-123, 2001.

[24] “Heart Function,” The Permanente Medical Group

URL: http://www.permanente.net/homepage/kaiser/pages/f63363.html [25] “Understanding an ECG,” Geeky Medics, 2011.

URL: http://geekymedics.com/2011/03/05/understanding-an-ecg

[26] K. Grauer, “ECG Interpretation Review #34,” ECG Interpretation, 2012.

URL: http://ecg-interpretation.blogspot.tw/2012/01/ecg-interpretation-review-34-acute- mi.html

[27] “ECG Segments,” wb-CME: Electrocardiography Primer

URL: http://www.education.science-thi.org/edu_ecg/ecginclinicalpractice/normalecg/

ecgsections/index.html

[28] “Pediatric ECG Cases,” Medscape Reference

URL: http://reference.medscape.com/features/slideshow/ped-ecg