進階搜尋


下載電子全文  
系統識別號 U0026-3108201817105300
論文名稱(中文) 應用經驗模態分解與機器學習於洗腎病患人工廔管阻塞分析
論文名稱(英文) Application of Empirical Mode Decomposition and Machine Learning to Arteriovenous Graft Occlusion Analysis for Hemodialysis Patients
校院名稱 成功大學
系所名稱(中) 生物醫學工程學系
系所名稱(英) Department of BioMedical Engineering
學年度 106
學期 2
出版年 107
研究生(中文) 王昱堯
研究生(英文) Yu-Yao Wang
學號 P86051139
學位類別 碩士
語文別 英文
論文頁數 54頁
口試委員 指導教授-鄭國順
共同指導教授-甘宗旦
口試委員-孫永年
口試委員-李宗南
召集委員-陳彥廷
中文關鍵字 聲學  經驗模態分解  動靜脈瘻管  機器學習 
英文關鍵字 phonoangiography  empirical mode decomposition  arteriovenous shunt  machine learning 
學科別分類
中文摘要 動靜脈瘻管的檢測方式通常是透過感覺觸覺的刺激及脈動,或是利用聽診器、督卜勒超音波、血管造影等。然而這些技術皆需要特定的設備和操作者。聲學是一種辨識血管直徑變化的非侵入性方法。在本研究中,建立了一套仿生系統來簡化血流狀況的模擬。聲音的訊號經由電子聽診器紀錄而後進一步做信號處理。聲學和病變的相關已在許多文獻被證實,血管通路的早期診斷,如狹窄或血栓形成是非常重要的問題。本研究的目的是利用聲學的技術來評估動靜脈瘻管狹窄程度,作為分類瘻管阻塞的指標。採用經驗模態分解方法分析阻塞程度和頻譜之間的關係,擷取出特徵後用機器學習去做訓練分類和預判,並利用臨床上的標準都卜勒超音波來做驗證。在22個案例中KNN和SVM分別展現出90.9%和85.7%的準確率,證實經驗模態分解於特徵擷取是可行的。這項非侵入性的評估方法對於家庭照顧及早期檢測是相當具有潛力。
英文摘要 The AV access is usually evaluated by feeling thrill and pulsation through palpation, listening for the bruit by using a stethoscope, Doppler ultrasound imaging, or angiography, etc. However, these techniques require specific equipment and operator. Phonoangiography is a noninvasive tool for identifying vascular diameter change. In this study, a mock model has been set up to simplify the simulation of blood flow condition. Phonographic signal is recorded by electronic stethoscope and further signal processed. The relationship of phonographic signals and stenotic lesions is studied. Early detection of hemodialysis access problems such as stenosis and thrombosis is very important issue. The purpose of this study is to develop a phonographic system to evaluate arteriovenous shunt (AVS) stenosis of hemodialysis patients. The degree of stenosis (DOS) is used as an index to classify the AV access condition, and is determined by the narrowing percentage of normal vessels. The empirical mode decomposition (EMD) method is applied to analyze the relationship between DOS and spectrogram. After feature extraction, use machine learning to train prediction model and classify. Verification is based on Doppler ultrasound which is the golden standard in clinical application. In 22 cases, KNN and SVM show 90.9% and 85.7% accuracy respectively, it proved that empirical mode decomposition is feasible in feature extraction. This noninvasive method may be useful and potential for early detection in home-care use.
論文目次 中文摘要 I
ABSTRACT II
致謝 IV
LIST OF TABLES VI
LIST OF FIGURES VII
Chapter 1. Introduction 1
1.1 Background 1
1.2 Arteriovenous Shunt (AVS) 4
1.3 Arteriovenous Shunt problem 6
1.4 Examination of arteriovenous fistula 6
1.5 Standard evaluation in the clinic 8
1.6 Literature review 10
1.7 Motivation and purpose 13
Chapter 2. Methods and Material 14
2.1 Experimental design 14
2.2 Mock model 14
2.3 Data 17
2.4 Empirical mode decomposition (EMD) 17
2.5 Intrinsic mode function (IMF) 19
2.6 Signal processing 20
2.7 Spectrogram 22
2.7 Problems of EMD 23
2.7.1 Misjudgment in Extreme 23
2.8 Classifier 24
2.8.1 K Nearest Neighbor (KNN) 24
2.8.2 Support Vector Machine (SVM) 26
Chapter 3. Results and Discussion 28
3.1 Results 28
3.1.1 Software System 28
3.1.2 Simulation Results 32
3.1.3 Real Case Results 34
3.1.4 Classification 37
3.2 Discussion 43
Chapter 4. Conclusion and prospect 48
4.1 Conclusion 48
4.2 Prospect 49
References 50
參考文獻 [1] Glomerular filtration rate categories [online].
Available:https://www.kidney.org/kidneydisease/siemens_hcp_gfr
[2] 2017 USRDS annual data report international comparisons [online]. Available: https://www.usrds.org/2017/view/Default.aspx
[3] Health care insurance expenses and percentage of top 20 disease in Taiwan, 2014 [online]. Available:http://en1000g.shop2000.com.tw/product/p14766149
[4] Health care insurance expenses and percentage of top 20 disease in Taiwan, 2015 [online]. Available:https://www.nhi.gov.tw/Resource/webdata/27297_2_%E5%9C%8B%E4%BA%BA%E5%85%A8%E6%B0%91%E5%81%A5%E5%BA%B7%E4%BF%9D%E9%9A%AA%E5%B0%B1%E9%86%AB%E7%96%BE%E7%97%85%E8%B3%87%E8%A8%8A.pdf
[5] Health care insurance expenses and percentage of top 20 disease in Taiwan, 2016 [online]. Available:https://data.nhi.gov.tw/resource/Opendata/%E5%9C%8B%E4%BA%BA%E5%85%A8%E6%B0%91%E5%81%A5%E5%BA%B7%E4%BF%9D%E9%9A%AA%E5%B0%B1%E9%86%AB%E7%96%BE%E7%97%85%E8%B3%87%E8%A8%8A.pdf
[6] Pathophysiology of blood vessels [online]. Available:https://www.indiamart.com/proddetail/arteriovenous-fistula-vein-graft-procedures-6875675397.
[7] Catheter [online]. Available:http://nephronlove.tumblr.com/post/19106025899/woowoowoowoo-my-catheter
[8] She-Meng Cheng, Suk-Ping Ng, Fei-Shih Yang, Shin-Lin Shih, ‘‘Interventional Treatment for Complete Occlusion of Arteriovenous Shunt: Our Experience in 39 cases,’’ 中華放射醫誌Chin J Radiol; 28: 137-142, 2003.
[9] Vascular Access Work Group. Clinical practice guidelines for vascular access. Am J Kidney Dis; 48 Suppl 1: S248, 2006.
[10] Sidawy AN, Spergel LM, Besarab A, et al. ‘‘The Society for Vascular Surgery: clinical practice guidelines for the surgical placement and maintenance of arteriovenous hemodialysis access.’’, J VascSurg; 48:2S, 2008.
[11] 陳世宜, 王碩盟, 吳明修, ‘‘彩色與強力都卜勒超音波:一般原理及在腎臟學的臨床應用’’, 腎臟與透析: 民國93年16卷3期
[12] Arif Asif, ‘‘Taking the weight off the fistula: the importance of vein transposition and fistula evaluation in obese patients,’’ Nature Clinical Practice Nephrology volume 3, pp. 308-309, 2007.
[13] Arif Asif, Carlos Leon, Luis Carlos Orozco-Vargas, Gururaj Krishnamurthy, Kenneth L. Choi, Carlos Mercado, Donna Merrill, Ian Thomas, Loay Salman, Shukhrat Artikov, and Jacques J. Bourgoignie, ‘‘Accuracy of Physical Examination in the Detection of Arteriovenous Fistula Stenosis,’’ Clin J Am Nephrol 2: pp. 1191-1194, 2007.
[14]Leon, Luis Carlos Orozco-Vargas, Gururaj Krishnamurthy, Kenneth L. Choi,Carlos Mercado, Donna Merrill, Ian Thomas, Loay Salman, Shukhrat Artikov, Jacques J.Bourgoignie, and Arif Asif, ‘‘Accuracy of Physical Examination in the Detection of Arteriovenous Graft Stenosis,’’ 2008.
[15] Pietro Ravani, Robert R. Quinn, Matthew J. Oliver, Divya J. Karsanji, Matthew T. James, Jennifer M. MacRae, Suetonia C. Palmer and Giovanni F.M. Strippoli, ‘‘Preemptive Correction of Arteriovenous Access Stenosis: A Systematic Review and Meta-analysis of Randomized Controlled Trials,’’ Am J Kidney Dis; 67(3): pp. 446-460, 2016.
[16] Anas Mohd Noor, ‘‘Non-Imaging Acoustical Properties in Monitoring Arteriovenous Hemodialysis Access. A Review,’’ J. Eng. Technol. Sci., vol. 47, no. 6, pp. 658-673, 2015.
[17] Pablo V´asquez, Marco Mungu´ıa M., Elisabeth Mattsson, Bengt Mandersson,‘‘Application of the Empirical Mode Decomposition in the study of murmurs from Arteriovenous Fistula Stenosis,’’32nd Annual International Conference of the IEEE EMBS Buenos Aires, Argentina, August 31 - September 4, 2010.
[18] Marco Mungu´ıa M., Pablo V´asquez , Bengt Mandersson, ‘‘Characterisation of Arteriovenous Fistula’s Sound Recordings using Principal Component Analysis,’’ 31st Annual International Conference of the IEEE EMBS Minneapolis, Minnesota, USA, September 2-6, 2009.
[19] Hsien-Yi Wang, Cho-Han Wu, Chien-Yue Chen, and Bor-Shyh Lin, ‘‘Novel Noninvasive Approach for Detecting Arteriovenous Fistula Stenosis,’’ IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, vol. 61, no. 6, June, 2014.
[20] Pavlos Malindretos, Christos Liaskos, Panagiotis Bamidis, Ioannis Chryssogonidis,
Anastasios Lasaridis, Pavlos Nikolaidis, ‘‘Computer assisted sound analysis of arteriovenous fistula in hemodialysis patients,’’ Int J Artif Organs, 2013.
[21] Mikkel Grama, Jens Tranholm Olesena, Hans Christian Riisa, Maiuri Selvaratnama, Michalina Urbaniaka, ‘‘Stenosis detection algorithm for screening of arteriovenous fistulae,’’ SEMCON conference paper 1-6, 2010.
[22] AtsuTodo, Noriyuki Someya, Tomomi Kadonaka, Hirofumi Hasegawa, Masanori Yoshioka, Yasumasa Hitomi, Ayako Ueno, Takayuki Nishigaki, Masami Mitani, Yuko Mizuno-Matsumoto, Hitoshi Katsurao, ‘‘Frequency analysis of shunt sounds in the
arteriovenous fistula on hemodialysis patients,’’ SCIS-ISIS 2012, Kobe, Japan, November 20-24, 2012.
[23] Comparison of different algorithm [online]. Available: http://access.ee.ntu.edu.tw/Ongoing_Project/HHT/HHT.htm
[24] M Manjula, A V R S Sarma, ‘‘Comparison of Empirical Mode Decomposition and Wavelet Based Classification of Power Quality Events,’’ Energy Procedia 14, pp. 1156-1162, 2012.
[25] Domenico Labate, Fabio La Foresta, Gianluigi Occhiuto, Francesco Carlo Morabito, Aime Lay-Ekuakille, PatriziaVergallo, ‘‘Empirical Mode Decomposition vs. Wavelet
Decomposition for the Extraction of Respiratory Signal from Single-Channel ECG: A Comparison,’’ IEEE Sensors Journal, vol. 13, no. 7, July, 2013
[26] Denis Donnelly, ‘‘The Fast Fourier and Hilbert-Huang Transforms: A Comparison,’’ International Journal of Computers, Communications & Control vol. I, no. 4, pp. 45-52, 2006.
[27] Yi-Chu Li, Fan-Ming Yu, Chung-Dann Kan, “Evaluation of Arteriovenous Shunt Stenosis induced Phonographic Signal on Hemodynamics in Hemodialysis Patients”, Master’s Thesis of Department of Aeronautics and Astronautics, National Cheng Kung University, June, 2015.
[28] Norden E. Huang, Zheng Shen, Steven R. Long,Manli C. Wu, Hs ing H. Shih, Quanan Zheng, Nai-Chyuan Yen, Chi Chao Tung, Henry H. Liu, ‘‘The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,’’ The Royal Society, 1998.
[29] Yung-Hung Wang, Chien-Hung Yeh, Hsu-Wen Vincent Young, Kun Hu,
Men-Tzung Lo, ‘‘On the computational complexity of the empirical mode decomposition algorithm,’’ Physica A 400, pp. 159-167, 2014.
[30] Jont B. Allen, ‘‘Short Term Spectral Analysis, Synthesis, and Modification by Discrete Fourier Transform,’’ IEEE Transactions On Acoustics, Speech, And Signal Processing, vol. ASSP-25, no. 3, June, 1977.
[31] F. N. Fritsch, R. E. Carlson, ‘‘Monotone Piecewise Cubic Interpolation,’’ SIAM J. NUMER. ANAL. vol. 17, no. 2, April, 1980.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2018-09-04起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2018-09-04起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw