臺灣博碩士論文加值系統

本研究提出使用心電圖(Electrocardiogram, ECG)與光體積變化描計圖(Photoplethysmprgraphy, PPG)來建構一套嚴重心律不整之辨識系統，辨識四種疾病，心搏過慢(Bradycardia)、心搏過速(Tachycardia)、心室頻脈(Ventricular Tachycardia)以及心搏停止(Asystole)。
提出的辨識方法分為兩個部分，第一個部分為使用最簡單且直接的方式，以連續心率與波寬特徵來直接辨識嚴重心律不整。第二個部分為使用直接辨識搭配分類器辨識，使用到的分類器有兩種，支持向量機(SVM)與倒傳遞類神經網路(BPNN)。在特徵擷取中，本研究發現當疾病發生時，ECG訊號與PPG訊號的波形與振幅皆會產生變化，故提出波形相關特徵期望能提升辨識率，從結果得知，本研究所提出的波形相關特徵對於整體辨識率是有所幫助的。另外，為了能在更有效地提升整體辨識率與減少辨識所花費之時間，研究中亦提出了階層式的分類方法，利用直接辨識(Direct, D)與分類器辨識(Classifier, C)作搭配，分別為DC、DDC與DCC，並使用留一交叉驗證的方式得到辨識結果，從研究結果得知，不管在任何訊號組合下，皆以DDC系統架構(搭配BPNN)擁有較佳之辨識率，使用兩種訊號辨識率為99.24%，使用ECG訊號辨識率為99.24%，使用PPG訊號辨識率為94.66%。
在本研究中，雖然以使用兩種訊號與單一使用ECG訊號搭配DDC系統架構辨識效果最佳，但本研究最終目標是期望僅用PPG訊號來辨識嚴重心律不整，由結果顯示，單一使用PPG訊號搭配DDC系統架構辨識效果可達到94.66%之辨識率，且平均辨識一筆所花費時間約為0.11秒，此結果亦證明了辨識嚴重心律不整演算法的高效能和即時辨識的可行性。

In this study, we proposed a serious arrhythmia recognition system based on two physiological signals. Electrocardiogram (ECG) and Photoplethysmprgraphy (PPG) were used to recognize four kinds of disease, including bradycardia, tachycardia, ventricular tachycardia, and asystole.
The proposed method was divided into two parts. The first part was the direct identification method that recognized serious arrhythmias by a continuous heart rate and pulse width characteristics. The second part used direct identification combined with a classifier for recognition. Two classifiers, support vector machine (SVM) and back-propagation neural network (BPNN) were used. For the feature extraction, we discovered that when the disease occurred, the waveform and amplitude of the ECG signal and PPG signal would change. Therefore, we hope to use the waveform relevant features to improve the accuracy. The results showed that the waveform relevant features proposed in this study raised the overall recognition rate. Moreover, in order to more effevtively enhance the overall accuracy and reduce the recognition time, we proposed multi-level classification methods that combined direct recognition method (D) and classifier recognition method (C), including DC, DDC, and DCC. We also employed leave-one-out scheme for cross validation. According to the results, regardless of signal combination, DDC system with BPNN classifier had best the accuracy. The accuracy was 99.24% when using two signals, 99.24% when using ECG signal alone, 94.66% when using PPG signal alone for recognition.
According to the result, although the use of two signals and ECG signal with DDC system have the best performance, our final goal is to use PPG signal alone for serious arrhythmia recognition. The accuracy could reach 94.66% when using PPG signal alone with DDC system for recognition, and the average time was about 0.11 seconds to recognize one record. The result demonstrated the high-capability and real-time recognition feasibility of the proposed serious arrhythmia recognition system.

誌謝 I
摘要 II
Abstract III
目錄 V
圖目錄 VII
表目錄 IX
第一章 緒論 1
1.1 研究動機 1
1.2 相關研究 2
1.3 研究目標 3
1.4 研究架構 3
第二章 文獻探討 4
2.1 生理訊號介紹 4
2.1.1 心電圖 4
2.1.2 光體積變化描計圖 9
2.2 疾病介紹 12
2.2.1 嚴重心律不整 12
2.2.2 心搏過慢(Bradycardia) 13
2.2.3 心搏過速(Tachycardia) 14
2.2.4 心室頻脈(Ventricular Tachycardia) 15
2.2.5 心搏停止(Asystole) 16
2.3 理論背景 17
2.3.1 小波轉換(Wavelet Transform) 17
第三章 研究方法 19
3.1 生理訊號擷取 20
3.1.1 資料庫介紹 20
3.1.2 資料庫篩選 21
3.2 訊號前處理 23
3.2.1 去除基線飄移 23
3.2.2 去除高頻雜訊 25
3.3 心電圖(ECG)特徵擷取 28
3.2.1 時域特徵 28
3.2.2 波寬與振幅特徵 29
3.2.3 HRV序列特徵 30
3.2.4 Binary序列特徵 31
3.2.5 頻譜特徵[39] 32
3.2.6 高階矩特徵[40] 32
3.2.7 VF-Filter Leakage[41] 33
3.2.8 非線性特徵 34
3.4 光體積變化描計圖(PPG)特徵擷取 36
3.4.1 時域特徵與HRV序列統計特徵 36
3.4.2 呼吸頻率特徵 37
3.4.3 振幅特徵 37
3.4.4 HRV序列特徵 38
3.4.5 脈搏速率特徵 43
3.4.6 灌流指標特徵 44
3.4.7 波寬特徵與波谷到波峰距離佔整段波長的比例特徵 45
3.5 特徵正規化 46
3.6 分類 46
3.6.1 直接辨識法(Direct Identification) 46
3.6.2 支持向量機(Support Vector Machine)[57][58][59] 50
3.6.3 類神經網路簡介[59][62] 55
3.6.4 直接辨識法搭配分類器 57
3.6.5 交叉驗證 61
第四章 研究結果與討論 62
4.1 研究所使用的數據 62
4.2 直接辨識法 63
4.2.1 比較定義 63
4.2.2 三種訊號組合結果 64
4.3 直接辨識法搭配分類器 65
4.3.1 使用ECG訊號與PPG訊號 65
4.3.2 單一使用ECG訊號 69
4.3.3 單一使用PPG訊號 74
4.4研究結果討論 81
4.4.1 比較不同系統架構 81
4.4.2 比較不同訊號組合 88
4.4.3 比較系統花費時間 90
4.5 相關文獻比較 92
第五章 結論與未來發展 94
5.1 結論 94
5.2 未來發展 95
參考文獻 97
附錄 103

[1] “心血管疾病是美國人的頭號殺手”， http://sampan.org/zh-hant/2016/01/
[2] “臺灣103年十大死因”，http://www.mohw.gov.tw/CHT/DOS/Statistic.aspx?f_list_no=312&fod_list_no=5595
[3] N. V. Thakor, Y. S. Zhu, and K.Y. Pan., “Ventricular tachycardia and fibrillation detection by a sequential hypothesis testing algorithm,” IEEE Transactions on Biomedical Engineering, Vol. 37, No. 9, pp. 837-843, September. 1990.
[4] X. S. Zhang, Y. S. Zhu, N. V. Thakor, and Z. Z. Wang, “Detecting ventricular tachycardia and fibrillation by complexity measure,” IEEE Transactions on Biomedical Engineering, Vol. 46, No. 5, pp. 548-555, May. 1999.
[5] M. A. Arafat, A. W. Chowdhury, and Md. K. Hasan. “A simple time domain algorithm for the detection of ventricular fibrillation in electrocardiogram,” Signal, Image and Video Processing, Vol. 5, Issue. 1, pp.1-10, March. 2011.
[6] Z. Hou, Y. Zhang, “Ventricular Fibrillation Detection by An Improved Time Domain Algorithm Combined with SVM,” Medical Biometrics, pp. 189-194, 2014.
[7] Q. Li, C. Rajagopalan, “Ventricular Fibrillation and Tachycardia Classification Using a Machine Learning Approach,” IEEE Transactions on Biomedical Engineering, Vol. 61, pp. 1607-1613, June. 2014.
[8] J. S. Karthika, J.M. Thomas, J.J. Kizhakkethottam, “Detection of life-threatening arrhythmias using temporal, spectral and wavelet features,” IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pp. 1-4, December. 2015.
[9] “Electrocardiography”, https://en.wikipedia.org/wiki/Electrocardiography
[10] 周嘉陞， “心電圖學必備”，合記圖書出版社, 2001.
[11] “Cardiology Teaching Package”, http://www.nottingham.ac.uk/nursing/practice/resources/cardiology/function/chest_leads.php
[12] “ECG Scanner Basics”, http://compharm.net/ecg_scanner/basics/
[13] J. Pan, W. J. Tompkins, “A Real-Time QRS Detection Algorithm,” IEEE Transactions on Biomedical Engineering, Vol. Bme-32, No. 3, pp. 230-236, March. 1985.
[14] B. Hertzman, C. R. Spielman, “Observations on the finger volume pulse
recorded photoelectrically,” Am. J. Physiol. , Vol. 119, pp. 334-335, 1937.
[15] “Photoplethysmography”, https://lookfordiagnosis.com/mesh_info.php?term=photoplethysmography&lang=1
[16] T. Tamura, Y. Maeda, M. Sekine, M. Yoshida, “Wearable Photoplethysmographic Sensors—Past and Present,” Electronics, Vol.3, pp. 282-302, 2014.
[17] B Khanoka, Y Slovik, D Landau, M Nitzan, “Sympathetically Induced
Spontaneous Fluctuations of the Photoplethysmographic Signal,” Medical &
Biological Engineering and Computing, Vol. 42, Issue. 1, pp. 80-85, January. 2004.
[18] “AngioScan”, https://www.angioscan.ru/en/radiascan/devices/radiascan-501/16-science/publish
[19] “Pulse Trace”, http://www.micromedical.co.uk/downloads/pdf/pulse2.pdf
[20] M. Bolanos, H. Nazeran, E. Haltiwanger, “Comparison of Heart Rate Variability Signal Features Derived from Electrocardiography and Photoplethysmography in Healthy Individuals,” Engineering in Medicine and Biology Society, pp. 4289-4294, 2006.
[21] “心律不整”，https://en.wikipedia.org/wiki/Cardiac_arrhythmia
[22] “猝死症多與心律不整有關”，http://www.lmcf.org.tw/htm_f/healthy/healthy19.htm
[23] “心搏過緩”， http://www.ca2-health.com/
[24] “Tachycardia”, https://en.wikipedia.org/wiki/Tachycardia
[25] “Ventricular Tachycardias”, http://patient.info/doctor/ventricular-tachycardias
[26] “Asystole”, https://en.wikipedia.org/wiki/Asystole
[27] “心搏停止”， http://cht.a-hospital.com/
[28] “Wavelet”, https://en.wikipedia.org/wiki/Wavelet
[29] 陳欩融，“ 一個使用小波分頻編碼簿的心電圖壓縮法 ”，國立中正大學電機所，92年
[30] S. G. Mallat, “a theory for multiresolution signal decomposition: the wavelet representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 7, pp. 674-693, July. 1989.
[31] “Challenge 2015 Training Set”, http://www.physionet.org/challenge/2015/
[32] “MIMIC Database”, https://www.physionet.org/physiobank/database/mimicdb/
[33] “MIMIC II Waveform Database”, https://physionet.org/mimic2/
[34] D. Zhang,” Wavelet Approach for ECG Baseline Wander Correction and Noise Reduction,” Engineering in Medicine and Biology 27th Annual Conference Shanghai, China, pp. 1212-1215, September. 2005.
[35] R. W. Picard, E. Vyzas, J. Healey, "Toward Machine Emotional Intelligence: Analysis of Affective Physiological State," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 10, pp. 1175-1191, October. 2001.
[36] M. Brennan, M. Palaniswami, P. Kamen, “Do Existing Measures of Poincare Plot Geometry Reflect Nonlinear Features of Heart Rate Variability? ,” IEEE Transactions on Biomedical Engineering, Vol. 48, No. 11, pp. 1342-1346, 2001
[37] A. Riasi, M. Mohebbi, “Prediction of ventricular tachycardia using morphological features of ECG signal,” Artificial Intelligence and Signal Processing, pp. 170-175, March. 2015.
[38] I. Jekova, “Shock advisory tool: Detection of life-threatening cardiac arrhythmias and shock success prediction by means of a common parameter set,” Biomedical Signal Processing and Control, Vol. 2, Issue. 1, pp. 25-33, January. 2007.
[39] S. Barro, R. Ruiz, D. Cabello, and J. Mira, “Algorithmic sequential decision making in a frequency domain for life threatening ventricular arrhythmias and imitative artifacts: a diagnostic system,” Journal of Biomedical Engineering, Vol. 11, Issue. 4, pp. 320-328, July. 1989.
[40] A. Ghaffari, M. R. Homaeinezhad, M. Khazraee, and M. M. Daevaeiha, “Segmentation of Holter ECG Waves Via Analysis of a Discrete Wavelet-Derived Multiple Skewness–Kurtosis Based Metric,” Annals of Biomedical Engineering, Vol. 38, No. 4, pp. 1497–1510, April. 2010.
[41] S. Kuo and R. Dillman, “Computer detection of ventricular fibrillation,” in Proc. Comput. Cardiol., pp. 347–349, 1978.
[42] C. E. Shannon, “A Mathematical Theory of Communication,” The Bell System Technical Journal, Vol. 27, pp. 379–423, 623–656, 1948.
[43] G. E. Powell and I. C. Percival, “A spectral entropy method for distinguishing regular and irregular motion of Hamiltonian systems,” Mathematical and General, Vol. 12, pp. 2053-2071, 1979.
[44] S. M. Pincus, “Heart rate control in normal and aborted-SIDS infants,” American Journal of Physiology, Vol. 33, pp. 638-646, 1991.
[45] A. Metin, “Approximate Entropy and Its Application in Biosignal Analysis ,“ Nonlinear Biomedical Signal Processing：Dynamic Analysis and Modeling, IEEE Press, Vol. 2, pp. 72-91, 2000.
[46] K. Nakajima, T. Tamura, H. Miike, “Monitoring of heart and respiratory
rates by photoplethysmography using a digital filtering technique, ” Med. Eng. Phys., Vol.18, No.5, pp. 365-372,July. 1996.
[47] I. Yalcin, K. Mehmet, “Combining classical HRV indices with wavelet entropy measures improves to performance in diagnosing congestive heart failure,” Computers in Biology and Medicine, Vol. 37, Issue. 10, pp. 1502-1510 , October. 2007.
[48] M. Brennan, M. Palaniswami, P. Kamen, “Do Existing Measures of Poincare Plot Geometry Reflect Nonlinear Features of Heart Rate Variability? ,“ IEEE Transactions on Biomedical Engineering, Vol. 48, No. 11, pp. 1342-1346, 2001.
[49] 陳俊傑，“以LabVIEW為基礎之視覺誘發電位分析與睡眠腦波分期整合系統”，南台科技大學電機工程學系碩士論文，2010。
[50] J. S. Richman and R. J. Moorman, “Physiological time-series analysis using approximate entropy and sample entropy,” Am J Physiol Heart Circ Physiol, Vol. 278, pp. 2039-2049, 2000.
[51] 林文勇，“流化床中床質磨損與混沌分析”，逢甲大學化學工程學系碩士論文，2002。
[52] L. T. Fan, D. Neogi, M. Yashima and R. Nassar, “Stochastic Analysis of a Three-Phase Fluidized Bed : Fractal Approach,” AIChE J., 36(10), pp. 1529-1535, 1990.
[53] M. J. Katz, “Fractals and Analysis of Waveforms,” Computers in Biology and Medicine, Vol. 18, Issue. 3, pp. 145-156, 1988.
[54] T. Balli, R. Palaniappan, “A Combined Linear & Nonlinear Approach for Classification of Epileptic EEG Signals,” IEEE Engineering in Medicine and Biology Conference on Neural Engineering, pp. 714-717, 2009.
[55] Task Force of The European Society of Cardiology and The North American
Society of Pacing and Electrophysiology, “Heart rate variability. Standards of
measurement, physiological interpretation, and clinical use, ” Circulation,
Vol. 93, pp. 1043-1065, 1996.
[56] A. Granelli, I. Östman-Smith, “Noninvasive peripheral perfusion index as a possible tool for screening for critical left heart obstruction,” Acta Paediatrica, pp. 1455-1459, 2007.
[57] “Support Vector Machines簡介”，http//www.cmlab.csie.ntu.edu.tw/~cyy/learning/tutorials/SVM2.pdf.
[58] “LIBSVM: a library for support vector machines”, http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf
[59] 范振翔，“使用區域化特徵與校正策略偵測心肌缺血事件的研究”，國立中正大學電機所，2013。
[60] V. Vapnik, “An Overview of Statistical Learning Theory,” IEEE Transactions on Neural Networks, pp. 988-999, 1999.
[61] Chang, Lin., “a Library for Support Vector Machines”, 2001.
[62] “神經網路”， http://nccur.lib.nccu.edu.tw/bitstream/140.119/35873/6/25700606.pdf
[63] 林羣晨，“以心電圖為基礎之心血管疾病專家防治系統”，慈濟大學，2007。