臺灣博碩士論文加值系統

一直以來，對於心電訊號異常的診斷或判讀大部分主要依靠著醫生們所擁有的專業知識與資料庫來做判斷，然而若能發展出一套方便又準確的心電圖偵測演算法，必能協助醫生對異常心電訊號的判讀。近幾十年來，許許多多的演算法也因應而產生，然而一套從QRS波到QT波諸如此類的演算法卻很少見，基於此觀點，本論文提出關於QRS波新的兩種演算法，作為未來發展QT波偵測的先行研究。此類演算法以移動平均整流開始，結合三次雲規線包裹特徵訊號，選取適當門檻進而偵測出QRS波。在對MIT-BIH心律不整資料庫所進行訊號的檢測，本文提出演算法均達到99%的準確度。

Most diagnosis for the abnormal electrocardiogram (ECG) depends on the professional knowledge and databases from doctors. However, if a convenient and precise algorithm can be developed to detecting significant events of ECG, it provides doctors a great assistance.
In the past decades, many mature ECG detection algorithms have been constructed to detect the QRS complex but not applicable to finding QT intervals. This thesis develops a cubic spline based method in detecting QRS complex with aim to resolve the QT interval in the future.
First of all, the signal is rectified via moving average, and then the cubic spline is used to enveloping the signal. After selecting adaptive threshold, QRS complex candidates are confined and computed. Finally, the robustness of our method is tested by MIT- BIH Database whence it provides over 99% accuracy in the RR intervals detection.

誌謝
目錄I
圖目錄III
表目錄V
中文摘要VI
AbstractVII
第一章 緒論1
1.1 前言與研究動機1
1.2 論文架構 2
第二章 預備知識3
2.1 心電圖原理3
2.2 移動平均6
2.3 Hilbert 變換7
2.4 三次雲規函數7
第三章 QRS波偵測方法與比較9
3.1 QRS波的各類偵測方法回顧9
3.1.1 心電圖訊號偵測程序9
3.1.2 QRS波偵測演算法回顧9
3.2 演算法一15
3.3 演算法二23
3.4 實驗結果與討論29
3.4.1 演算法一的測驗結果30
3.4.2 演算法一的測驗結果32
3.4.3 結果討論38
第四章 結論與未來展望39
4.1 結論39
4.2 未來展望39
參考文獻40
附錄A42
A.1 MIT-BIH心律不整資料庫簡介42

[1] A. Koski, M. Juhola, and M. Meriste, “Recognition of ECG by attributed finite automata,”
Pattern Recognition 28:1927-1940, 1995.
[2] A. Savitsky and M. J. E. Golay, “Smoothing and differentiation of data by simplified least
squares procedures,” Anal. Chem. 36:1627-1639, 1964.
[3] B. U. Köhler, C. Hennig, and R. Orglmeister, “QRS detection using zero crossing counts,” Int.
J. Med. Informatics 31(1–3):191–208, 1998.
[4] B. U. Köhler, C. Hennig, and R. Orglmeister, “The principles of software QRS detection,” IEEE
Eng. Med. Biol. Mag. 21(1):42–57, 2002.
[5] D. Benitez, P. Gaydecki, A. Zaidi, and A. P. Fitzpatrick, “The use of the Hilbert transform in
ECG signal analysis,” Comput. Biol. Med. 31:399–406, 2001.
[6] 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. 52(1):35
-44, 1997.
[7] MIT-BIH Arrhythmia Database Directory, Harvard University- Massachusetts Institute of
Technology Division of Health Science and Technology, July, 1992. http://www.physionet.org/
[8] P. Flandrin, G. Rilling, and P. Gonçcalvés, “Empirical Mode Decomposition as a filter
bank,”IEEE Signal Processing Lett. 11(2):112-114, 2004.
[9] P. S. Hamilton and W. J. Tompkins, “Quantitative investigation of QRS detection rules using
the MIT/BIH arrhythmiac database,” IEEE Trans. Biomed. Eng. 33:1157-1165, 1986.
[10] R. M. Rangayyan, Biomedical Signal Analysis: A Case-study Approach. IEEE Press: Wiley, New
York, 2002.
[11] S. Dandapat and G.C. Ray, “Spike detection in biomedical signals using midprediction
filter,” Med. Biol. Eng. Comput. 35(4):354-360, 1997.
[12] V. X. Afonso, W. J. Tompkins, T. Q. Nguyen, and S. Luo, “ECG beat detection using filter
banks,” IEEE Trans. Biomed. Eng. 46:192-202, 1999.
[13] Y. H. Hu, W. J. Tompkins, J. L. Urrusti, and V. X. Afonso, “Applications of artificial
neural networks for ECG signal detection and classification,” J. Electrocardiology 26
(Suppl.):66-73, 1993.
[14] Z. Dokur, T. Olmez, E. Yazgan, and O. K. Ersoy, “Detection of ECG waveforms by neural
networks,” Med. Eng. Phys. 19(8):738-741, 1997.
[15] Z.-E. H. Slimane and A. Naït-Ali, “QRS complex detection using Empirical Mode
Decomposition,” Digital Signal. Processing doi:10.1016 /j.dsp.2009.10.017, 2009
[16] 楊正榮,“以小波轉換為基礎的QRS波偵測方法, ”國立中山大學電機與機電工程研究所,碩士論文,2004.
[17] 羅文利, “Cardiovascular System投影片,”輔英科技大學,2008
http://www.iportal.tw/fy105/doc/5766