在諸多生理訊號量測方法中，有關心電訊號的量測與分析一直是備受重視且具有臨床參考價值，尤其是心律變異性（Heart Rate Variability: HRV）近年來一直備受關注。本研究提出一套系統，藉由心電圖(Electrocardiogram, ECG)、血流量(Blood Volume Pulse, BVP)及脈搏(Pulse)三種生理訊號來辨別受測者目前有無飲酒。
本實驗針對HRV作時域(Time domain)及頻域(Frequency domain)的分析，在時域數據上可看出酒精狀態的Mean、Standard Deviation of Normal to Normal、Root Mean Square of Successive Differences這三個特徵值為最小；而在頻域部分，可發現酒精狀態屬於低頻區，為人體交感神經及副交感神經所引起，異於正常狀態及情緒狀態，因此可以證明酒精對人體生理訊號反應的獨特性。此外，我們使用希爾伯特轉換(Hilbert Transformation)，對ECG、BVP、Pulse擷取峰值特徵，取得R-R interval、BVP Peak waveform、Pulse Peak waveform，並利用SVM分類演算法作分類，分類結果可達85%。

Among various physical signal measuring methods, measure and analysis of Physiological Electrical Signal have been valued and referential for clinical experiments. Especially, Heart Rate Variability (HRV) is gradually getting attentions. This study proposes a system to test if experimental subjects drink alcoholic beverages by Electrocardiogram (ECG), Blood Volume Pulse (BVP), and Pulse.
The experiment aims to analyze Time domain and Frequency domain of HRV. In Time domain, the data indicates that the features of Mean, SDNN, and RMSSD are smaller under drinking condition, while the features of Frequency domain are within low frequency range. The consequence is caused by sympathetic and parasympathetic nerve system of human body which is different from the values under normal condition and emotional state. Therefore, it proves that the uniqueness of alcohol affects physical signals of human body. Additionally, we use Hilbert Transformation to get the values of R-R interval, BVP Peak waveform, and Pulse Peak waveform by extracting peak value from the categories of ECG, BVP, and Pulse, and classify these data by SVM classifier. The accuracy of classified result is up to 85%.

Contents
摘 要 i
ABSTRACT ii
誌 謝 iii
Contents iv
Table v
Figures vi
1. Introduction 1
1.1. Background 1
1.2. Pertinent Literature 1
1.3. Motivation 2
1.4. Chapter Outline 3
2. System structure 4
3. Approach 9
3.1. Physiological Signal Acquisition 9
3.2. Signal processing 9
3.2.1. Low-pass 10
3.2.2. High-pass 12
3.2.3. Feature extraction 13
3.3. Fast Fourier transform 15
3.4. Support Vector Machine 15
4. Results 18
4.1. Experiment environment 18
4.2. Experiment Results 19
5. Conclusion 25
Reference 26

[1]Y. Y. L. Wang, M. Y. Jan, C. S. Shyu, C.A. Chiang and W.K. Wang, “The natural frequencies of the arterial system and their relation to the heart rate,” IEEE Trans. on Biomedical Engineering, vol. 51, no. 1, pp. 193-195, Jan. 2004.
[2]W. J. Parer, J.T. Parer, R.H. Holbrook and B.S. Block , “Validity of mathematical methods of quantitating fetal heart rate variability,” Am J Obstet Gynecol, pp. 402-409, Oct. 1985.
[3]M. Malik, J. T. Bigger, A. J. Camm, R. E. Kleiger, A. Malliani, A. J. Moss and P. J. Schwartz, “Heart rate variability: Standards of measurement, physiological interpretation, and clinical use,” European Heart Journal, vol. 17, no. 3, pp. 354-381, 1996.
[4]B. Hyndman and J. Gregory, Spectral Analysis of Sinus Arrhythmia during Mental Loading, 2007, pp. 255-270.
[5]S. Akselrod, D. Gordon, F. A. Ubel, D. C. Shannon, A. C. Berger and R. J. Cohen, “Power spectrum analysis of heart rate fluctuation: a quantitative probe of beat-to-beat cardiovascular control,” Science Magazine, vol. 213, no. 4504, pp. 220-222, July 1981.
[6]C. W. Lin, J. S. Wang and P. C. Chung, “Mining physiological conditions from heart rate variability analysis,” IEEE Computational Intelligence Magazine, vol. 5, no. 1, pp. 50-58, Feb. 2010.
[7]L. Ji, J. Wu, Y. Yang, S. Wang and A. Li, “Activity-aware hrv analysis,” in 2011 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Anchorage, AK, Oct. 2011, pp. 1151-1156.
[8]J. Vila, F. Palacios, J. Presedo, M. Fernandez-Delgado, P. Felix, and S. Barro, “Time-frequency analysis of heart-rate variability,” IEEE Engineering in Medicine and Biology Magazine, vol. 16, no. 5, pp. 119-126, Oct. 1997.
[9]M. Bsoul, H. Minn, and L. Tamil, “Apnea medassist: Real-time sleep apnea monitor using single-lead ecg,” IEEE Trans. on Information Technology in Biomedicine, vol. 15, no. 3, pp. 416-427, May 2011.
[10]F. Agrafioti, D. Hatzinakos, and A. K. Anderson, “Ecg pattern analysis for emotion detection,” IEEE Trans. on Affective Computing, vol. 3, no. 1, pp. 102-115, March 2012.
[11]A. Kampouraki, G. Manis, and C. Nikou, “Heartbeat time series classification with support vector machines,” IEEE Trans. on Information Technology in Biomedicine, vol. 13, no. 4, pp. 512-518, July 2009.
[12]J. Mateo and P. Laguna, “Analysis of heart rate variability in the presence of ectopic beats using the heart timing signal,” IEEE Trans. on Biomedical Engineering, vol. 50, no. 3, pp. 334-343, March 2003.
[13]R. Logier, J. D. Jonckheere, and A. Dassonneville, “An efficient algorithm for r-r intervals series filtering,” in 2004. IEMBS ’04. 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 2, San Francisco, CA, Sept. 2004, pp. 3937-3940.
[14]N. M. Saad, A. R. Abdullah, and F. L. Yin, “Detection of heart blocks in ecg signals by spectrum and time-frequency analysis,” in 2006. SCOReD 2006. 4th Student Conference on Research and Development, Selangor, June 2006, pp. 61-65.
[15]C. Y. Chang, J. Y. Zheng, C. J. Wang and P. C. Chung, “Application of support vector regression for phyciological emotion recognition,” in 2010 International Computer Symposium (ICS), Tainan, Dec. 2010, pp. 12-17.
[16]C. Y. Chang, C. W. Chang and Y. M. Lin, “Application of support vector machine for emotion classification,” Master''s thesis, 2012.
[17]H. Li, S. Kwong, L. Yang, D. Huang and D. Xiao, “Hilbert-huang transform for analysis of heart rate variability in cardiac health,” IEEE/ACM Trans. on Computational Biology and Bioinformatics, vol. 8, no. 6, pp. 1557-1567, Dec. 2011.
[18]C. C. Chang and C. J. Lin, “Libsvm : a library for support vector machines,” 2001.