Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/97042
標題: 低複雜度光學式即時心室性早期收縮偵測系統之設計
Design of a Low Complexity PPG-based Real-time PVCs Detection System
作者: 魏名汎
Ming-Fan Wei
關鍵字: 光學式心跳量測
心室早期收縮偵測
心電圖
嵌入式系統
Photoplethysmography (PPG)
Premature Ventricular Contraction (PVC)
Electrocardiogram (ECG)
Multi-parameter Intelligent Monitoring in Intensive Care (MIMIC)
SoC
引用: [1] V. Kanvinde, Principles And Practice of Cardiopulmonary Physical Therapy, ed: LWW, 1996. [2] N. I. Goldstein, 'Cardiopulmonary physical therapy: a clinical manual,' Journal of Cardiopulmonary Rehabilitation and Prevention, vol. 17, pp. 126-127, 1997. [3] D. P. Zipes and H. J. J. Wellens, 'Sudden cardiac death,' Circulation, vol. 98, pp. 2334-2351, 1998. [4] T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, 'Wearable photoplethysmographic sensors—past and present,' Electronics, vol. 3, pp. 282-302, 2014. [5] M.-Z. Poh, D. J. McDuff, and R. W. Picard, 'Non-contact, automated cardiac pulse measurements using video imaging and blind source separation,' Optics Express, vol. 18, pp. 10762-10774, 2010. [6] H. S. Shin, C. Lee, and M. Lee, 'Adaptive threshold method for the peak detection of photoplethysmographic waveform,' Computers in Biology and Medicine, vol. 39, pp. 1145-1152, 2009. [7] D.-G. Jang, S. Park, M. Hahn, and S.-H. Park, 'A real-time pulse peak detection algorithm for the photoplethysmogram,' Int. J. Electron. Electr. Engin, vol. 2, pp. 45-49, 2014. [8] T.-H. Fu, S.-H. Liu, and K.-T. Tang, 'Heart rate extraction from photoplethysmogram waveform using wavelet multi-resolution analysis,' Journal of Medical and Biological Engineering, vol. 28, pp. 229-232, 2008. [9] A. Johansson, 'Neural network for photoplethysmographic respiratory rate monitoring,' Medical and Biological Engineering and Computing, vol. 41, pp. 242-248, 2003. [10] G. M. Friesen, T. C. Jannett, M. A. Jadallah, S. L. Yates, S. R. Quint, and H. T. Nagle, 'A comparison of the noise sensitivity of nine QRS detection algorithms,' IEEE Transactions on Biomedical Engineering, vol. 37, pp. 85-98, 1990. [11] C.-C. Chiu, T.-H. Lin, and B.-Y. Liau, 'Using correlation coefficient in ECG waveform for arrhythmia detection,' Biomedical Engineering: Applications, Basis and Communications, vol. 17, pp. 147-152, 2005. [12] M. Fejtová, J. Macek, and L. Lhotská, 'ECG events detection and classification using wavelet transform and decision trees,' Final Programme & Proceedings EUNITE, vol. 2001, pp. 99-101, 2001. [13] R. V. Andreao, B. Dorizzi, and J. Boudy, 'ECG signal analysis through hidden Markov models,' IEEE Transactions on Biomedical Engineering, vol. 53, pp. 1541-1549, 2006. [14] P. R. Gomes, F. O. Soares, J. Correia, and C. Lima, 'Cardiac arrhythmia classification using Wavelets and Hidden Markov Models–A comparative approach,' in Proc. of Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2009, pp. 4727-4730. [15] A. Sološenko, A. Petrėnas, and V. Marozas, 'Photoplethysmography-based method for automatic detection of premature ventricular contractions,' IEEE Transactions on Biomedical Circuits And Systems, vol. 9, pp. 662-669, 2015. [16] H. So and K. Chan, 'Development of QRS detection method for real-time ambulatory cardiac monitor,' in Proc. the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1997, pp. 289-292. [17] R. C.-H. Chang, H.-L. Chen, C.-H. Lin, and K.-H. Lin, 'Design of a Low-Complexity Real-Time Arrhythmia Detection System,' Journal of Signal Processing Systems, pp. 1-12, 2017. [18] J. V. Garcia, F. Zhang, and P. C. Ford, 'Multi-photon excitation in uncaging the small molecule bioregulator nitric oxide,' Phil. Trans. R. Soc. A, vol. 371, p. 20120129, 2013. [19] P. Davey, ECG at a Glance: John Wiley & Sons, 2013. [20] A. L. Goldberger, L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, et al., 'Physiobank, physiotoolkit, and physionet,' Circulation, vol. 101, pp. e215-e220, 2000. [21] W. Karlen, S. Raman, J. M. Ansermino, and G. A. Dumont, 'Multiparameter respiratory rate estimation from the photoplethysmogram,' IEEE Transactions on Biomedical Engineering, vol. 60, pp. 1946-1953, 2013. [22] G. B. Moody and R. G. Mark, 'A database to support development and evaluation of intelligent intensive care monitoring,' in Computers in Cardiology, 1996, pp. 657-660. [23] A. Schäfer 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, pp. 15-29, 2013. [24] J. Allen, 'Photoplethysmography and its application in clinical physiological measurement,' Physiological Measurement, vol. 28, p. R1, 2007. [25] H. Lin, W. Xu, N. Guan, D. Ji, Y. Wei, and W. Yi, 'Noninvasive and continuous blood pressure monitoring using wearable body sensor networks,' IEEE Intelligent Systems, vol. 30, pp. 38-48, 2015. [26] J. Pan and W. J. Tompkins, 'A real-time QRS detection algorithm,' IEEE Transactions on Biomedical Engineering, pp. 230-236, 1985. [27] S. Chernenko. (2012). ECG processing. R-peaks detection [Online]. Available: http://www.librow.com/cases/case-2 [Accessed 01-April-2017] [28] D. Benitez, P. Gaydecki, A. Zaidi, and A. Fitzpatrick, 'The use of the Hilbert transform in ECG signal analysis,' Computers in Biology and Medicine, vol. 31, pp. 399-406, 2001. [29] R. A. Schulze, H. W. Strauss, and B. Pitt, 'Sudden death in the year following myocardial infarction: relation to ventricular premature contractions in the late hospital phase and left ventricular ejection fraction,' The American Journal of Medicine, vol. 62, pp. 192-199, 1977. [30] A. Iwasa, M. Hwa, A. Hassankhani, T. Liu, and S. M. Narayan, 'Abnormal heart rate turbulence predicts the initiation of ventricular arrhythmias,' Pacing and Clinical Electrophysiology, vol. 28, pp. 1189-1197, 2005. [31] I. Jekova, G. Bortolan, and I. Christov, 'Pattern recognition and optimal parameter selection in premature ventricular contraction classification,' in Computers in Cardiology, 2004, pp. 357-360. [32] R. C.-H. Chang, C.-H. Lin, M.-F. Wei, K.-H. Lin, and S.-R. Chen, 'High-precision real-time premature ventricular contraction (PVC) detection system based on wavelet transform,' Journal of Signal Processing Systems, vol. 77, pp. 289-296, 2014. [33] E. Gil, P. Laguna, J. P. Martínez, Ó. Barquero-Pérez, A. García-Alberola, and L. Sörnmo, 'Heart rate turbulence analysis based on photoplethysmography,' IEEE Transactions on Biomedical Engineering, vol. 60, pp. 3149-3155, 2013. [34] I. Silva and G. B. Moody, 'An open-source toolbox for analysing and processing physionet databases in matlab and octave,' Journal of Open Research Software, vol. 2, 2014. [35] Xilinx Inc. Zynq-7000 All Programmable SoC. [Online]. Available: https://www.xilinx.com/products/silicon-devices/soc/zynq-7000.html [Accessed 01-Aug-2017] [36] S. Lee, C. Son, and H. Jang, 'Distributed and parallel real-time control system equipped FPGA-Zynq and EPICS middleware,' in Proc. of Real Time Conference (RT), 2016 IEEE-NPSS, 2016, pp. 1-4. [37] L. H. Crockett, R. A. Elliot, M. A. Enderwitz, and R. W. Stewart, 'The Zynq Book,' Strathclyde Academic Media, 2014. [38] Y. Sun and N. Thakor, 'Photoplethysmography revisited: from contact to noncontact, from point to imaging,' IEEE Transactions on Biomedical Engineering, vol. 63, pp. 463-477, 2016. [39] G. Bradski and A. Kaehler, Learning OpenCV: Computer vision with the OpenCV library: ' O''Reilly Media, Inc.', 2008.
摘要: 心臟疾病是國內最主要的死因之一,通常有慢性心血管疾病的病人在心電圖的精準判定下,可由心臟內科醫生定位出疾病,但對於急性的心臟病因,如心室早期收縮,若能即時從穿戴式裝置上判定警示,即可提醒病人注意身體狀況。一般心電圖的量測,都要十二導程以上才能精準判定,但能隨身攜帶的心電圖量測儀器還要能精準判斷心血管疾病,市面上目前並不多,光學式心跳量測近年已成為取代接觸式的心電圖量測系統的最好方法,心率、血氧、疲勞度、甚至包括血壓方面的研究,也能從光學的方法來大概判定,雖然光學式心跳量測相對於接觸式心電圖訊號量測較為簡單,但病理特徵的呈現並不如心電圖來的準確。是以如果能把光學式心跳量測用於簡單的心室早期收縮偵測,便能造福有心血管甚至是隱藏性患者帶來一定的幫助,改善生活的品質。 本論文提出一個低複雜度即時心室早期收縮的偵測系統,分成峰值與心室早期收縮異常訊號偵測兩部份來探討。峰值偵測採用So and Chan方法來偵測脈衝波峰,並分析波峰之間的時間差與心率變異度來做為心室早期收縮的特徵判斷條件。 模擬與驗證採用MIT-BIH MIMIC Database (mimic)所提供的PPG資料。 Improved So and Chan方法可有效降低波峰的偵測錯誤,將原來So and Chan方法用於光學式心跳量測訊號。而心室性早期收縮偵測方法可由特徵值辨識出,偵測正確率可達70%,並在發生心室性早期時發出訊息給使用者。由於演算法複雜度低,可達到即時偵測,適合整合於穿戴式電子產品上。
Heart disease is one of the main causes of death in our country. Even though Patients with the chronic cardiovascular disease can be detected by the Electrocardiogram (ECG) instruments in the hospital, the acute heart disease, such as premature ventricular contractions (PVCs), is still difficult to be found. However, it is of great help for patients to have a wearable device detecting the signal and sending the warnings in advance. In general ECG checking, the doctor may accurately determine the heart disease based on the standard 12-lead electrocardiogram. Unfortunately, not many instruments on the market support ECG that can diagnose the cardiovascular disease. Optical heartbeat measurement in recent years has become the best way to replace the ECG system. Optical instruments provide more advanced measurements in determining physiological symptoms like heart rate, blood oxygen, fatigue, and even blood pressure. The optical heartbeat measurement can be relatively simple whereas ECG performs much more accurate in the fields of pathological features by means of the plethysmograph. Once the optical heartbeat measurement can easily detect premature ventricular contractions, it will benefit the patients with possible cardiovascular and help improve the quality of life for the patients. This dissertation presents a low-complexity real-time PVCs detection system which is divided into two parts: to detect the peak and to investigate early ventricular systolic abnormalities. Peak detection was performed with the So and Chan method, peak to peak interval analysis and heart rate variability were implemented as a characteristic condition for PVCs. Simulation and verification using the plethysmograph data which were provided by MIT-BIH Multi-parameter Intelligent Monitoring in Intensive Care (MIMIC) database. So and Chan is utilized for optical heartbeat measurement signal while the Improved So and Chan method can effectively reduce the error of detecting crest. PVCs detection method can be identified by the eigenvalue, and the correct rate of detection is up to 70%. Besides, the system can send a message to the user in the early ventricular onset. With low-complexity, real-time detection of the algorithm can be achieved. The system is suitable for integration into the wearable devices.
URI: http://hdl.handle.net/11455/97042
文章公開時間: 2020-08-29
Appears in Collections:電機工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.