臺灣博碩士論文加值系統

本篇論文包括 “心電圖信號分析”、“主要特徵點的選擇”及“模糊邏輯”三大研究主題。研究主題一是心電圖信號分析，以DOM (Difference Operation Method) 法偵測心電圖(ECG)信號中的QRS 複合波、T波、P波的位置。本主題分成三個步驟，分別是：(1)將待測試的ECG信號作 “差分運算”，其目的是要找精準的R波位置；(2)以R波位置為基準，往R波的前方向找Q波，往R波的後方向找S波，其目的是要找到QRS 複合波；(3)找T波、P波。研究主題二是以區間交集法 (Rang-Intersection method) 選擇主要特徵點。研究主題三是以模糊邏輯 (fuzzy logic) 判斷心律不整。本論文能判斷的心律，包含：正常的心跳(NORM)，及不正常的心跳。不正常的心跳包含LBBB、RBBB、VPC、APC、及PB等五種較常發生的心律。最後，我們再以MIT-BIH 心律不整資料庫中的ECG信號來評估本主題中所提出方法之效能，結果心律之正確判斷率是90.72%。

In this dissertation, some efficient algorithms in three related research topics about ECG signals will be presented and discussed. In the first research topic, a simple method, called the Difference Operation Method (DOM), is proposed to detect the QRS complex of an electrocardiogram (ECG) signal. The proposed DOM includes three stages. The first stage is to find the point R by applying the difference equation operation to an ECG signal. The second stage looks for the points Q and S based on the point R and then finds the whole QRS complex. The three stage looks for the points T and P waves based on the QRS complex. In the second research topic, the reliable method called Range-Intersection method for feature selection of ECG signals. In the third research topic, one method, named “Fuzzy Logic Method (FLM)”, is applied for classifying the cardiac arrhythmia on ECG signals. The proposed methods can accurately classify the normal heartbeats and abnormal heartbeats. Abnormal heartbeats include Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Ventricular Premature Contractions (VPC), Atrial Premature Contractions (APC) and Paced Beat (PB). The proposed methods were evaluated using the MIT-BIH arrhythmia database, the total classification accuracy is 90.72% for FLM method.

摘 要 i
Abstract ii
誌 謝 iii
目 錄 iv
表 目 錄 vi
圖 目 錄 vii
第一章 簡介 1
第二章 QRS複合波的偵測 3
2.1 ECG信號的前置處理 3
2.1.1 前置放大器 3
2.1.2 雜訊的去除 3
2.2 R波的偵測 4
2.3 Q波的偵測 10
2.3.1 設定Q波的合理搜尋範圍 10
2.3.2 第一次修正的Q波檢查範圍 10
2.3.3 第二次修正的Q波檢查範圍 12
2.3.4 Q點位置的選取 14
2.4 S 波的偵測 16
2.4.1 設定S波的合理搜尋範圍 16
2.4.2 第一次修正的S波檢查範圍 16
2.4.3 第二次修正的S波檢查範圍 18
2.4.4 S點位置的選取 19
2.5 T波與P波的偵測 20
第三章 特徵點之定義與特徵值之計算 21
3.1 特徵點的定義 21
3.2 特徵值的統計 24
3.3 各種心跳病症分類之特徵值的統計與分析 29
3.3.1 心跳病症分類1: NORM（正常） 30
3.3.2 心跳病症分類2: LBBB（左束分支阻斷） 31
3.3.3 心跳病症分類3: RBBB（右束分支阻斷） 32
3.3.4 心跳病症分類4: VPC（心室過早收縮） 33
3.3.5 心跳病症分類5: APC（心房過早收縮） 34
3.3.6 心跳病症分類6: PB（Paced beat） 35
第四章 特徵點選取 (Feature selection) 36
4.1 特徵值範圍Ri,j 37
4.2 特徵點的選取 38
4.3 Ni的排序 40
4.4 主要特徵點的選取 40
4.5 選取下一個主要特徵點 41
4.6 主要特徵點與特徵值範圍 41
第五章 模糊邏輯法分析心電圖的心跳種類及性能評估42
5.1 模糊邏輯法(Fuzzy Logic Method) 42
5.2 性能評估 50
第六章 結論與未來展望 57
參考文獻 58
簡 歷 60

[1]黃蓮奇譯，心臟循環系統，台灣光復書局，1996年。
[2]楊杞柳譯，心電圖判讀之快速學習法，財團法人徐氏基金會，1991年。
[3]G. Vijaya, V. Kumar, and H. K. Verma, ANN-based QRS-complex analysis of ECG, J. Med. Eng. Technol., vol. 22, no. 4, pp.160-167, 1998.
[4]Y. H. Hu, W. J. Tompkins, J. L. Urrusti, and V. X. Afouso, Applications of artificial neural networks for ECG signal detection and classification, J. Electrocardiology, vol. 26, no. 1, pp. 66-73, 1993.
[5]R. Poli, S. C. Cagnoni, and G. Valli, Genetic design of optimum linear QRS detectors, IEEE Trans. Biomed. Eng., vol. 42, no. 6, pp. 1137-1141, 1995.
[6]S. Kadambe, R. Murray, and G. F. Boundreaux-Bartels, Wavelet transform-based QRS complex detector, IEEE Trans. Biomed. Eng., vol. 46, no. 6, pp.838-848, 1999.
[7]V. X. Afonso, W. J. Tomkins, T. Q. Nguyen, and S. Luo, ECG beat detection using filter banks, IEEE Trans. Biomed. Eng., vol. 46, no. 2, pp.192-202, 1999.
[8]C. W. Li, C. X. Zheng, and C. F. Tai, Detection of ECG characteristic points using wavelet transforms, IEEE Trans. Biomed. Eng., vol. 42, no. 1, pp. 21-28, 1995.
[9]B.U. Kahler, C. Henning, and R. Orglmeistes, The principles of software QRS Detection., IEEE Engineering in Medicine and Biology, pp. 42-P57, 2002.
[10]X. Xu, and Y. Liu, ECG QRS complex detection using slope vector waveform (SVW) algorithm, 26th Int. Conf of the IEEE EMBS, pp. 3597-3600, 2004.
[11]MIT-BIH database distribution, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139, 1998.
[12]Y.C. Yeh, and W.J. Wang, QRS complexes detection for ECG signal: The Difference Operation method, Computer Methods and Programs in Biomedicine, vol. 91, pp. 245-254, 2008.
[13]R. M. Rangayyan, Biomedical Signal Analysis: A Case-Study Approach, Wiley Inter-Science, New York, 2001.
[14]F. Gritzali, G. Frangakis, and G. Papakonstantinou, Detection of the P and T waves in an ECG, Computers and Biomedical Research, vol, 22, pp. 83-91, 1989.
[15]S. J. Hengeveld and J. H. Van Bemmel, Computer detection of P waves, Computers and Biomedical Research, vol. 9, pp. 125-132, 1976.
[16]Y. Zigel, A. Cohen, and A. Katz, The weighted diagnostic distortion (WDD) measure for ECG signal compression, IEEE Trans. on Biomed. Eng., 47 (11) (2000) 1422-1430.
[17]R. A. J. ohnson, D. W. Wichern, Applied Multivariate Statistical Analysis, Pearson Prentice Hall, New Jersey, 2007.
[18]L. A. Zadeh, Fuzzy sets as a basis for a theory of possibility, Fuzzy Sets and Systems, vol. 1, 1978.
[19]J. Pan, and W. J. Tompkins, A real-time QRS detection algorithm, IEEE Trans. Biomed. Eng., BME-32, no.3, pp. 230-236, 1985
[20]葉雲奇，「Simple and Effective QRS Complexes Detection Scheme and Its Application on Cardiac Arrhythmia Diagnosis by ECG Signals」，中央大學電機研究所，博士論文，民國九十八年。
[21]葉雲奇、林泓志、朱怡雲，以模糊邏輯法分析心電圖的心跳種類，2010年第六屆全國數位訊號處理(DSP)創思設計競賽。