臺灣博碩士論文加值系統

本研究提出一血壓估測系統，使用光體積變化描記圖(Photoplethysmography, PPG)為生理訊號，估測收縮壓與舒張壓。
本研究資料取自於民國102年國立中正大學心理系翁嘉英教授所主持之科技部研究計畫(NSC102-2410-H194-022)，系統流程依序為資料分類、生理訊號擷取、特徵點偵測、特徵擷取以及血壓估測五個部分。在資料分類方面，將資料分為四大類(健康大學生、高血壓吃藥、高血壓為吃藥、血壓正常但可能有其他疾病)，且每類有四期(基線期、回憶期、描述期、恢復期)。在生理訊號擷取上，依不同類別作訊號擷取並偵測重要特徵點，接著計算各類特徵，包含時間特徵、振幅特徵、波寬特徵、心律變異(HRV)特徵、性別以及年齡，總共65個。在估測方法上，使用倒傳遞類神經網路(Back propagation neural network, BPNN)，經實驗比較後，參數設定如下：隱藏層層數為2層，轉移函數為對數雙彎曲，隱藏層的神經元數目為130。
在結果方面，All train all test驗證在各情況誤差皆能在3mmHg以下；而在兩類(健康大學生、血壓正常但可能有其他疾病)取三期(無描述期)時，使用Leave one out交叉驗證，收縮壓及舒張壓誤差分別為8.598 mmHg、6.89 mmHg；兩類皆只取基線期時，收縮壓及舒張壓誤差分別為7.746 mmHg、6.81 mmHg。

In this study, we proposed a blood pressure estimation system. We estimated systolic and diastolic blood pressure by using Photoplethysmography (PPG).
The database collected by the projects supported by the grants from Ministry of Science and Technology (NSC 102-2410-H-194-022) to Chia-Ying Weng. The system contained five parts, namely data classification, physiological signal acquisition, feature points detection, feature extraction, and blood pressure estimation. In the data classification part, data were divided into four categories including healthy students, hypertensive patients with medication, and hypertensive patients without medication and people but might have other diseases with normal blood pressure. Each of the categories had four stages: baseline, recall, description, and recovery. In the physiological signal acquisition part, we acquired physiological signal and detected important feature points from different categories of signals. And then totally 65 features, including the features of time, amplitude, waveform, HRV, gender, and age were calculated. In the estimation part, we used the back-propagation neural network (BPNN). The parameters were empirically set as follows: 2 hidden layers, transfer function of log-sigmoid, and 130 neurons in the hidden layer.
The results showed that the error in each case was always limited within 3 mmHg by using all-train-all-test validation. When the signals were acquired from healthy students and people with normal blood pressure but might have other diseases and only the more stable three stages, including baseline, recall, and recovery were considered the errors in systolic and diastolic blood pressure were 8.598 mmHg and 6.89 mmHg, respectively, by using leave one out cross-validation. On the other hand, when the data contained the same two categories mentioned above and only the baseline stage was considered, the systolic and diastolic blood pressure errors were reduced to 7.746 mmHg, 6.81 mmHg, respectively.

致謝 I
摘要 II
Abstract III
目錄 V
圖目錄 VIII
表目錄 X
第一章 緒論 1
1.1 前言 1
1.2 研究動機 3
1.3 相關文獻回顧 4
1.4 研究目標 4
1.5 論文架構 4
第二章 研究背景 5
2.1 血壓量測方式及其工作原理 5
2.1.1 侵入式與非侵入式量測 5
2.1.2 聽診法 5
2.1.2 振盪法 6
2.2 光體積變化描記圖與血壓的關係 7
2.2.1 光體積變化描記圖(PPG) 7
2.2.2 心電圖(ECG) 9
2.2.3 脈波傳遞時間(Pulse Transit Time, PTT) 10
2.3 PPG與ABP於生理上之相關性 11
第三章 研究方法 12
3.1資料庫介紹與分類 13
3.2 PPG重要特徵點 13
3.2.1 數位濾波器 14
3.2.2 波峰波谷偵測[11][12] 16
3.2.3 重搏點偵測 18
3.3 特徵擷取 23
3.3.1 時間特徵 24
3.3.2 振幅特徵 25
3.3.3 波寬特徵 25
3.3.4 HRV序列特徵 26
3.3.5 PTT特徵 30
3.3.6 其他特徵 30
3.3.7 特徵正規化 30
3.4 線性迴歸(Linear Regression) 31
3.5 類神經網路(Neural Network) 32
3.5.1 類神經網路的發展[27] 32
3.5.2 倒傳遞類神經網路(Back propagation neural network,BPNN) 32
3.6 驗證方式 37
第四章 實驗結果與討論 38
4.1 線性迴歸分析的結果與討論 39
4.1.1 簡單迴歸分析 39
4.1.2 複迴歸分析 43
4.2 倒傳遞類神經網路參數設定比較 44
4.3 倒傳遞類神經網路結果與討論 47
4.3.1 各類資料於基線期估測結果 47
4.3.2 四類資料分別於各期的估測結果 49
4.3.3 各類資料組合之估測結果 56
4.3.4 HRV與波型相關特徵比較 60
4.4 相關文獻比較 62
第五章 結論與未來發展 64
5.1 結論 64
5.2 未來發展 66
參考文獻 67
附錄 71

[1] 中華民國統計資訊網，http://www1.stat.gov.tw.
[2] J. J. Carr, J. M. Brown, "Introduction to biomedical equipment technology, " 4th ed., Prentice hall, 2001.
[3] J. G. Webster, "Medical Instrumentation: Application and Design, " 4th ed., John
Wiley & Sons Inc. 2010.
[4] 血壓計精準技術，http://www.nml.org.tw.
[5] A. B. Hertzman, C. R. Spielman, "Observations on the finger volume pulse
recorded photoelectrically, " Am. J. Physiol., Vol.119, Page(s): 334-335, 1937
[6] 陳敬修， "使用非侵入式PPG信號評估手術病患舒張壓變化趨勢之研究"，
中山大學機械與機電工程所碩士論文, 2004.
[7] "Wikipedia", http://simple.wikipedia.org/wiki/Main_Page
[8] P. Fung, G. Dumont, G. Ries, C. Mott, M. Ansermino, "Continuous Noninvasive
Blood Pressure Measurement by Pulse Transit Time, " Proceedings of the 26th
Annual International Conference of the IEEE EMBS, Vol. 1, p.p.738-741, Sep. 2004.
[9] S. Y. Ye, G. R. Kim, D. K. Jung, S. W. Baik, G. R. Jeon, "Estimation of Systolic
and Diastolic Pressure using the Pulse Transit Time, " International Journal of
Medical, Health, Biomedical, Bioengineering and Pharmaceutical Engineering,
Vol. 4, p.p.303-308, 2010.
[10] S. Kumar, S. Ayub, "Estimation of Blood Pressure by Using
Electrocardiogram(ECG) and Photoplethysmogram(PPG) , " 2015 Fifth
International Conference on Communication Systems and Network Technologies,
p.p.521-524, 2015.
[11] R. Laulker, N. Daimiwal, "Application of finger photoplethysmography, "
International Journal of Engineering Research and Applications, p.p.877-880,
2012.
[12] D. G. Jang, S. Park, M. Hahn, S. H. Park, "A Real-Time Pulse Peak Detection
Algorithm for the Photoplethysmogram, " International Journal of Electronics
and Electrical Engineering, Vol. 2, p.p. 45-49, 2014.
[13] L. Antonelli, W. Ohley, R. Khamlach, "Dicrotic Notch Detection Using Wavelet
Transform Analysis, " Proceedings of the 16th Annual International Conference
of the IEEE, Vol. 2, p.p. 1216-1217, Nov. 1994.
[14] L. Antonelli, W. Ohley, R. Khamlach, "Wavelet Transform Analysis of the
Arterial Pressure Waveform, " Proceedings of the IEEE-SP International
Symposium, p.p. 568-571, Oct 1994.
[15] 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
[16] 徐佑，"利用形態學特徵偵測心肌缺血的發生"，國立中正大學電機所，101
年
[17] Y. Yoon, G. Yoon, "Nonconstrained Blood Presure Measurement by
Photoplethysmography, " Journal of the Optical of Korea, p.p. 91-95, 2006.
[18] R. Samria, R. Jain, A. Jha, S. Saini, S. R. Chowdhury, "Noninvasive Cuffless
Estimation of Blood Pressure using Photoplethysmography without
Electrocardiograph Measurement, " Department of Electronics and
Communication Engineering, 2014.
[19] M. Kachuee, M. M. Kiani, H. Mohammadzade, M. Shabany, "Cuff-Less High-
Accuracy Calibration-Free Blood Pressure Estimation Using Pulse Transit
Time," Department of Electrical Engineering, 2015.
[20] X. F. Teng, Y. T. Zhang, "Continuous and Noninvasive Estimation of Arterial
Blood Pressure Using a Photoplethysmographic Approach", Proceedings of the
25th Annual lnlematianal Conference of the IEEE EMBS, 2003.
[21] Y. Kurylyak, D. Grimaldi, "A Neural Network-based Method for Continuous
Blood Pressure Estimation from a PPG Signal, " University of Calabria, Rende
(CS), Italy, 2013
[22] S. Lu, H. Zhao, K. Ju, K. Shin, M. L. K. Shelley, K. H. Chon, "Can
photoplethysmography variability serve as an alternative approach to obtain
heart rate variability information, " J. Clin. Monit. Comput., vol. 22, p.p. 23-29,
2008.
[23] X. Chen, T. Chen, F. Luo, J. Li, " Comparison of Valley-to-Valley and Peak-to-
Peak Intervals from Photoplethysmographic Signals to Obtain Heart Rate
Variability in the Sitting Position, " 6th International Conference on Biomedical
Engineering and Informatics, p.p. 214-218, 2013.
[24] 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, p.p. 1342-1346, 2001
[25] 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 37, p.p. 1502-1510, 2007
[26] 線性迴歸，https://zh.wikipedia.org/
[27] 劉芳岑，"以次頻帶分解法進行雙導程心電圖搏動辨識之研究"，國立中正
大學電機所，99年
[28] M. T. Hagan, H. B. Demuth, M. H. Beale, "Neural Network Design, " First
published , 1996.
[29] Z. Shen, F. Miaq, Q. Meng, Y. Li, "Cuffless and Continuous Blood Pressure
Estimation based on Multiple Regression Analysis, " 2015 5th International
Conference on Information Science and Technology, 2015.
[30] M. Kachuee, M. M. Kiani, H. Mohammadzade, M. Shabany, "Cuff-Less Blood
Pressure Estimation Algorithms for Continuous Health-Care Monitoring, " IEEE
Transactions on Biomedical Engineering, 2016.
[31] 世界衛生組織，http://www.who.int/
[32] 刺胳針(雜誌)，http://www.thelancet.com/
[33] 台灣高血壓學會，http://www.ths.org.tw/