本論文旨在應用心率變異參數開發一氣喘偵測演算法。演算法首先將心電訊號經過訊號前處理及雜訊消除後，分別將訊號以2分鐘及10分鐘兩種視窗大小進行切割。各個視窗再依照時域、頻域和非線性三種心率變異分析方式計算出共25種特徵，再利用循序向前選擇法進行特徵選取並降低特徵的維度。最後，本論文分別採用了用於離散辨識之倒傳遞類神經網路及用於連續趨勢辨識之摺積神經網路兩種分類器進行氣喘偵測。本研究共有86位被醫師診斷為氣喘患者之受試者參與，並蒐集每位患者氣喘發作與氣喘未發作兩類心電訊號作為演算法訓練資料。結果顯示，倒傳遞類神經網路之最佳正確率為62.79%；摺積神經網路之最佳正確率為77.33%。表示在氣喘偵測問題上，連續趨勢辨識方法較離散辨識方法更為有效。研究結果驗證本論文提出之演算法可以應用於氣喘辨識分析之可行性。在未來期望能實現演算法於穿戴式載具上，提升氣喘照護之便利性。

This thesis aims to develop an asthma detection algorithm based on heart rate variability (HRV) features. The algorithm starts with electrocardiography (ECG) signal preprocessing and noise removal, and then segments ECG signal into two-minute and ten-minute windows, respectively. After that, a total of 25 HRV features are generated by the time-domain, frequency-domain, and nonlinear analysis for each window. The sequential forward selection (SFS) feature selection method is then employed to select significant features and reduces the dimension of features. With the selected features, two classifiers, a backpropagation neural network (BPNN) for discrete classification and a convolutional neural network (CNN) for continuous time-series trend classification have been applied to detect asthma attacks. A total of eighty-six participants who are diagnosed with asthma by doctors were recruited in this study. The ECG data during asthma attack and non-asthma attack of each participant were recorded for feature generation and asthma detection. The recognition rates of BPNN and CNN for asthma-attack detection were 62.79% and 77.33%, respectively. Obviously, CNN outperforms BPNN in asthma-attack detection. The effectiveness of the proposed algorithm with CNN has been validated by the experimental results. In the future, we hope this algorithm can be applied to wearable devices for improving the efficiency of asthmatic care.

[1]S. Akselrod, D. Gordon, F. A. Ubel, D. C. Shannon, A. C. Barger, and J. Cohen, “Power spectrum analysis of heart rate fluctuation a quantitative probe of beat-to-beat cardiovascular control,” Science, vol. 213, no. 4504, pp. 220-222, 1981.
[2]M. L. Appel, R. D. Berger, J. P. Saul, J. M. Smith, and R. J. Cohen, “Beat to beat variability in cardiovascular variables noise or music,” Journal of the American College of Cardiology, vol. 14, no. 5, pp. 1139-1148, 1989.
[3]M. Bahoura, “Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes,” Computers in Biology and Medicine, vol. 39, no. 9, pp. 824-843, 2009.
[4]R. Bailón, L. Sörnmo, and P. Laguna, “A robust method for ECG-based estimation of the respiratory frequency during stress testing,” IEEE Transactions on Biomedical Engineering, vol. 53, no. 7, pp. 1273-1285, 2006.
[5]P. de Chazal, C. Heneghan, E. Sheridan, R. Reilly, P. Nolan, and M. O’Malley, “Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnea,” IEEE Transactions on Biomedical Engineering, vol. 50, no. 6, pp. 686-696, 2003.
[6]J. Chen, C. Wang, and R. Wang, “Using stacked generalization to combine SVMs in magnitude and shape feature spaces for classification of hyperspectral data,” IEEE Transactions on Geoscience and Remote Sensing, vol. 47, no. 7, pp. 2193-2205, 2009.
[7]H. Fujii, O. Fukutomi, R. Inoue, S. Shinoda, H. Okammoto, T. Teramoto, N. Kondo, H. Wada, K. Saito, T. Matsuoka, and M. Seishima, “Autonomic regulation after exercise evidenced by spectral analysis of heart rate variability in asthmatic children,” Annals of Allergy, Asthma & Immunology,” vol. 85, no. 3, pp. 233-237, 2000.
[8]D. H. Hubel and T. N. Wiesel, “Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex,” The Journal of Physiology, vol. 160, no. 1, pp. 106-154, 1962.
[9]F. Jin, F. Sattar, and S. Krishnan, “Automatic respiratory sound classification using temporal-spectral dominance,” in Proc. IEEE Int’l Conf. Multimedia and Expo, pp. 1-4, 2011.
[10]L. Keahey, B. Bulloch, A. B. Becker, C. V. Pollack, S. Clark, and C. A.Camargo, “Initial oxygen saturation as a predictor of admission in children presenting to the emergency department with acute asthma,” Annals of Emergency Medicine, vol. 40, no. 3, pp. 300-307, 2002.
[11]S. Kiranyaz, T. Ince, and M. Gabbouj, “Real-time patient-specific ECG classification by 1-D convolutional neural networks,” IEEE Transactions on Biomedical Engineering, vol. 63, no. 3, pp. 664-675, 2016.
[12]S. D. Kreibig, “Autonomic nervous system activity in emotion: A review,” Biological Psychology, vol. 84, pp. 394-421, 2010.
[13]B. S. Lin, H. D. Wu, and S. J. Chen, “Automatic wheezing detection based on signal processing of spectrogram and back-propagation neural network,” Journal of Healthcare Engineering, vol. 6, no. 4, pp. 649-672, 2015.
[14]M. F. Lutfi, “Autonomic modulations in patients with bronchial asthma based on short-term heart rate variability,” Lung India, vol. 29, pp. 254-258, 2012.
[15]A. Malliani, M. Pagani, F. Lombardi, and S. Cerutti, “Cardiovascular neural regulation explored in the frequency domain,” Circulation, vol. 84, pp. 482-492, 1991.
[16]N. Montano, T. G. Ruscone, A. Porta, F. Lombardi, M. Pagani, and A. Malliani, “Power spectrum analysis of heart rate variability to assess the changes in sympathovagal balance during graded orthostatic tilt,” Circulation, vol. 90, pp. 1826-1831, 1994.
[17]D. Oletic, B. Arsenali, and V. Bilas, “Low-power wearable respiratory sound sensing,” Sensors, vol. 14, pp. 6535-6566, 2014.
[18]J. Pan and W. J. Tompkins, “A real-time QRS detection algorithm,” IEEE Transactions on Biomedical Engineering, vol. 32, pp. 230-236, 1985.
[19]S. B. Park, Y. S. Noh, S. J. Park, and H. R. Yoon, “An improved algorithm for respiration signal extraction from electrocardiogram measured by conductive textile electrodes using instantaneous frequency estimation,” Medical & Biological Engineering & Computing, vol. 46, pp. 147-158, 2008.
[20]R. W. Picard, E. Vyzas, and 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, 2001.
[21]A. Ram and P. K. Khodiar, “Alteration of autonomic function is associated with disease severity in patients with bronchial asthma,” International Journal of Clinical and Experimental Physiology,” vol. 2, no. 2, pp. 110-114, 2015.
[22]M. R. Raoufy, T. Ghafari, R. Darooei, M. Nazari, S. A. Mahdaviani, A. R. Eslaminejad, M. Almasnia, S. Gharibzadeh, A. R. Mani, and S. Hajizadeh, “Classification of asthma based on nonlinear analysis of breathing pattern,” Plos One, vol. 11, no. 1, pp. 1-17, 2016.
[23]R. J. Riella, P. Nohama, and J. M. Maia, “ Method for automatic detection of wheezing in lung sounds,” Brazilian Journal of Medical and Biological Research, vol. 42, no. 7, pp. 674-684, 2009.
[24]A. Schafer and J. Vagedes, “How accurate is pulse rate variability as an estimate of heart rate variability? A review on studies comparing photoplethysmographic technology with an electrocardiogram,” International Journal of Cardiology, vol. 166, no. 1, pp. 15-29, 2013.
[25]P. Shi, S. Hu, and Y. Zhu, “A preliminary attempt to understand compatibility of photoplethydmographic pulse rate variability with electrocardiogramic heart rate variability,” Journal of Medical and Biological Engineering, vol. 28, no. 4, pp. 173-180, 2008.
[26]S. Tabakov, I. Iliev, and V. Krasteva, “Online digital filter and QRS detector applicable in low resource ECG monitoring systems,” Annals of Biomedical Engineering, vol. 36, pp. 1805-1815, 2008.
[27]M. P. Tulppo, T. H. Mäkikallio, T. E. S. Takala, T. Seppänen, and H. V. Huikuri, “Quantitative beat-to-beat analysis of heart rate dynamics during exercise,” American Journal of Physiology-Heart and Circulatory Physiology, vol. 271, pp. 244-252, 1996.
[28]G. D. Vito, S. D. R. Galloway, M. A. Nimmo, P. Maas, and J. J. V. McMurray, “Effects of central sympathetic inhibition on heart rate variability during steady-state exercise in healthy humans,” Clinical Physiology and Functional Imaging, vol. 22, pp. 32-38, 2002.
[29]J. S. Wang, W. C. Chiang, Y. L. Hsu, and Y. T. C. Yang, “ECG arrhythmia classification using a probabilistic neural network with a feature reduction method,” Neurocomputing, vol. 116, pp. 38-45, 2013.
[30]B. Waske, S. V. D. Linden, J. A. Benediktsson, A. Rabe, and P. Hostert, “Sensitivity of support vector machines to random feature selection in classification of hyperspectral data,” IEEE Transactions on Geoscience and Remote Sensing, vol. 48, no. 7, pp. 2880-2889, 2010.
[31]A. W. Whitney, “A direct method of nonparametric measurement selection,” IEEE Transactions on Computers, vol. 100, no. 9, pp. 1100-1103, 1971.
[32]M. Wisniewski and T. P. Zielinski, “Application of tonal index to pulmonary wheezes detection in asthma monitoring,” in Proc. of 19th IEEE EUSIPCO. Signal Processing, pp. 1544-1548, 2011.
[33]X. Xu and S. Schuckers, “Automatic detection of artifacts in heart period data,” Journal of Electrocardiology, vol. 34, 2001.
[34]Task Force of the European Society of Cardiology and North American Society of Pacing and Electrophysiology, “Heart rate variability: Standards of measurement, physiological interpretation and clinical use,” European Heart Journal, vol. 17, pp. 354-381, 1996.
[35]Global Initiative for Asthma: Global Strategy for Asthma Management and Prevention. [Online]. Available: http://ginasthma.org/2017-online-appendix-global-strategy-for-asthma-management-and-prevention/
[36][Online]. Available: http://www.nhi.gov.tw/mqinfo/Content.aspx?Type=Asthma&List=8
[37]洪千涵，基於心電訊號之自動情緒辨識演算法之開發，國立成功大學電機工程學系碩士論文，2013。
[38]原著：Martin Bartholomew，總校閱：古宏海、邱美妙，解剖學，第一版，全威，台北，pp. 506-507，2010。