跳到主要內容

臺灣博碩士論文加值系統

(44.192.38.248) 您好!臺灣時間:2022/11/30 22:58
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:陳偉福
研究生(外文):CHEN WEIFU
論文名稱:基於深度學習之心電圖疾病辨識
指導教授:李柏磊
學位類別:碩士
校院名稱:國立中央大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:108
語文別:中文
論文頁數:64
中文關鍵詞:心電圖心律不整深度學習卷積神經網絡心房顫動心室期外收縮心房期外收縮左束支傳導阻滯右束支傳導阻滯心室顫動心室性心動過速
相關次數:
  • 被引用被引用:0
  • 點閱點閱:182
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
近年來,根據世界衛生組織(WHO)的統計,心血管疾病已經成為導致死亡和殘疾的重要原因之一,最常見的心血管疾病則為心律不整。通常,臨床醫生通過觀察長時間的心電圖(ECG)進行診斷是相當耗時且困難的。現在,良好的醫護環境逐漸受到重視,但醫療資源依然有限。幸運的是,今天深度學習的發展在影像識別和生物醫學訊號分析領域取得了巨大成功。 卷積神經網絡(CNN)是其中一種著名的深度學習方法,它具有先進的特徵自動提取和強健性。 在這個研究中,我們開發了一種新穎且高精度的CNN系統,用於心房顫動(Atrial Fibrillation, AFIB),心室期外收縮(Premature ventricular contraction, PVC),心房期外收縮(Premature atrial contraction, PAC),左束支傳導阻滯(Left bundle branch block, LBBB),右束支傳導阻滯(Right bundle branch block, RBBB),心室顫動(Ventricular Fibrillation,VFIB) 和心室性心動過速(Ventricular Tachycardia, VT)7類心電圖疾病和正常竇性心律(Normal sinus rhythm, NSR)的辨識,在這項研究中,所有用於訓練和測試的心電圖數據皆取自於MIT-BIH數據庫。 本系統對上述七種類型的心臟疾病和正常的心電圖數據進行分類,準確度達到95%。 這項研究證明了其在臨床應用中的可行性,加以改進後未來可作為臨床醫師診斷的輔助工具。
In recent years, cardiovascular disease has become the leading cause of death and disability according to the statistics by the World Health Organization. The most common form of cardiovascular disease being arrhythmia. Sometimes, it becomes time-consuming and difficult for clinicians to observe electrocardiogram (ECG) and analyze the arrhythmia. Fortunately, deep learning has brought great success in the fields of image recognition and biomedical signal analysis. The Convolutional Neural Network (CNN) is a such famous method of deep learning with advanced automatic feature extraction and robustness. In this work, we developed a novel system of CNN for automatic detection of arrhythmia based on ECG signals. The ECG signals were obtained from a publicly available arrhythmia database. We have obtained Normal sinus rhythm (NSR), Atrial Fibrillation(AFIB), Premature ventricular contraction (PVC), Premature atrial contraction (PAC), Left bundle branch block(LBBB), Right bundle branch block(RBBB), Ventricular Fibrillation (VFIB) and Ventricular Tachycardia (VT) ECG data from MIT-BIH arrhythmia database which includes recordings of many common and life-threatening arrhythmias along with clinical annotation. Our system has achieved an detection accuracy of 95% for the aforementioned seven types of arrhythmia. Hence, it is evident that our work has potential to be implemented in clinical settings to serve as an adjunct tool for the doctor. Furthermore, this work will be improved to achieve better performance in the future.
中文摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vii
表目錄 ix
第一章 緒論 1
1-1 前言 1
1-2 研究動機 2
1-3 文獻探討 3
1-4 論文章節架構 4
第二章 基本原理介紹 5
2-1 心電圖基本介紹 5
2-1-1 心電圖產生原理 5
2-1-2 心電圖訊號 6
2-2 心電圖的量測 8
2-2-1 三項標準雙極肢體導程的定義和接法 8
2-2-2 三項加壓單極肢體導程的定義和接法 9
2-2-3 六項單極胸前導程的定義和接法 9
2-3 心律不整 11
2-3-1 心律不整的分類 11
2-3-1-1 心房期外收縮 12
2-3-1-2 心室期外收縮 12
2-3-1-3 心室顫動 12
2-3-1-4 心室性心搏過速 12
2-3-1-5 心房顫動 13
2-3-1-6 左束枝傳導阻滯 13
2-3-1-7 右束枝傳導阻滯 14
第三章 深度學習介紹 15
3-1 深度學習的發展 15
3-1-1 類神經網路 16
3-2 卷積神經網路 18
3-2-1 卷積層 19
3-2-2 池化層 20
3-3 全連接層 20
3-4 激活函數 21
3-6 Dropout 22
3-7 深度學習的工具 22

第四章 研究設計與方法 23
4-1 系統架構 23
4-1-1 資料下載和整理 23
4-2 資料前處理 26
4-2-1 濾波 26
4-2-2 去除基線漂移 26
4-2-3 資料平滑處理 28
4-2-4 Pan and Tompkins QRS波定位方法 29
4-2-5 Zero crossing peak detection 30
4-2-6 閥值法分離心室性心搏過速和心室顫動 31
4-3 心電訊號特徵提取 32
4-4 實驗設計 33
4-5 研究方法驗證 34
第五章 結果與討論 35
5-1 Batch normalization 的使用 36
5-2 不同層數卷積層的結果比較 37
5-3 LSTM的結果比較 38
5-4 MLP多層感知器的結果比較 39
5-5 SVM 的使用和結果比較 40
5-6 交叉驗證 41
5-7 網路模型性能評估 43
5-8 研究方法驗證結果 45
第六章 結論與未來展望 47
第七章 參考文獻 49
[1]行 政 院 衛 生 署 : 衛 生 福 利 統 計 專 區 , 死 因 統 計 ,https://dep.mohw.gov.tw/DOS/cp-4472-48034-113.html,上網日期:2019-06-21
[2] Can Ye, Miguel Tavares Coimbra, B.V.K. Vijaya Kumar, ” Arrhythmia Detection and Classification using Morphological and Dynamic Features of ECG Signals”, Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE, pp. 1918-1921, 2010.
[3] Hari Mohan Rai, Anurag Trivedi, Shailja Shukla, Vivechana Dubey, ” ECG Arrhythmia Classification using Daubechies Wavelet and Radial Basis Function Neural Network”, Engineering (NUiCONE), 2012 Nirma University International Conference on , pp. 1-6, Dec. 2012.
[4] Chun-Cheng Lin, Chun-Min Yang, ” Heartbeat Classification using Normalized RR Intervals and Wavelet Features”, pp. 650-653, Jun. 2014.
[5] Shivajirao M. Jadhav, Sanjay L. Nalbalwar, Ashok A. Ghatol, ” ECG Arrhythmia Classification using Modular Neural Network Model”, Biomedical Engineering and Sciences (IECBES), 2010 IEEE EMBS Conference on, pp. 62-66, Dec. 2010.
[6] S. M. Jadhav, Dr. S. L. Nalbalwar, Dr. Ashok Ghatol, ” Artificial Neural Network Based Cardiac Arrhythmia Classification Using ECG Signal Data”, Electronics and Information Engineering (ICEIE), 2010 International Conference On, vol.1, pp. V1-228-V1-231, Aug. 2010.
[7] Komal Waseem, Awais Javed, Rashad Ramzan, Muddassar Faroo, ” Using Evolutionary Algorithms for ECG Arrhythmia Detection and Classification”, Computer Modeling and Simulation, 2009. EMS '09. Third UKSim European Symposium on, pp. 112-117, Nov. 2009.
[8] Stanislaw Osowski, Stanislaw Osowski, Robert Siroic, Krzysztof Siwek,” Genetic Algorithm for Integration of Ensemble of Classifiers in Arrhythmia Recognition”, Instrumentation and Measurement Technology Conference, 2009. I2MTC '09. IEEE , pp. 1496-1500 , May. 2009.
[9] Jalal A. Nasiri, Mahmoud Naghibzadeh, H. Sadoghi Yazdi, Bahram Naghibzadeh, ” ECG Arrhythmia Classification with Support Vector Machines and Genetic Algorithm”, Computer Modeling and Simulation, 2009. EMS '09. Third UKSim European Symposium on, pp. 187-192, Nov. 2009.
[10] Stockman G C, Kanal L N. Problem reduction representation for the linguistic analysis of waveforms[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1983 (3):287-298.
[11] Kundu M, Nasipuri M, Basu D K, et al. A reasoning system for on-line interpretation of ECG signal[C]. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on. IEEE, 1993, 2: 626-630.
[12] Kundu M, Nasipuri M, Basu D K. Knowledge-based ECG interpretation: a critical review[J].Pattern Recognition, 2000, 33(3): 351-373.
[13] Karimifard S, Ahmadian A, Khoshnevisan M, et al. Morphological heart arrhythmia detection using hermitian basis functions and kNN classifier[C]. Engineering in Medicine and Biology Society, 2006. EMBS'06. 28th Annual International Conference of the IEEE.IEEE, 2006: 1367-1370.
[14] 劉雄飛, 晏晨偉, 胡志坤. 基於數學形態學及支援向量機的心率失常識別[J]. 電腦應用, 2013, 33(4):1173-1175.
[15] Song M H, Lee J, Cho S P, et al. Support vector machine based arrhythmia classification using reduced features[J]. International Journal of Control Automation and Systems, 2005,3(4): 571.
[16] 湯麗平, 張健, 劉劍,等. 基於支持向量機的心律失常診斷研究[J]. 鐳射雜誌, 2012,33(4):80-82.
[17] Homaeinezhad M R, Atyabi S A, Tavakkoli E, et al. ECG arrhythmia recognition via a neuro-SVM–KNN hybrid classifier with virtual QRS image-based geometrical features[J]. Expert Systems with Applications, 2012, 39(2): 2047-2058.
[18] Tran H L, Pham V N, Vuong H N. Multiple neural network integration using a binary decision tree to improve the ECG signal recognition accuracy[J]. International Journal of Applied Mathematics and Computer Science, 2014, 24(3): 647-655.
[19] Alickovic E, Subasi A. Effect of multiscale PCA de-noising in ECG beat classification for diagnosis of cardiovascular diseases[J]. Circuits, Systems, and Signal Processing, 2015, 34(2): 513-533.
[20] Tran H L, Pham V N, Vuong H N. Multiple neural network integration using a binary decision tree to improve the ECG signal recognition accuracy[J]. International Journal of Applied Mathematics and Computer Science, 2014, 24(3): 647-655.
[21] Javadi M, Arani SA, Sajedin A, et al. Classification of ECG arrhythmia by a modular neural network based on mixture of experts and negatively correlated learning[J]. Biomedical Signal Processing and Control. 2013, 8(3):289-96.
[22] Silipo R, Marchesi C. Artificial neural networks for automatic ECG analysis[J]. Signal Processing, IEEE Transactions on, 1998, 46(5): 1417-1425.
[23] Fitria D, Ma'sum MA, Imah EM, et al. Automatic arrhythmias detection using various types of artificial neural network based learning vector quantization (LVQ)[J]. Jurnal Ilmu Komputer dan Informasi. 2014, 7(2):93-103.
[24] Martis RJ, Acharya UR, Min LC. ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform[J]. Biomedical Signal Processing and Control. 2013, 8(5):437- 48.
[25] Rai HM, Trivedi A, Shukla S. ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier[J]. Measurement. 2013, 46(9):3238-46.
[26] Wang J S, Chiang W C, Hsu Y L, et al. ECG arrhythmia classification using a probabilistic neural network with a feature reduction method[J]. Neurocomputing, 2013, 116: 38-45.
[27]Zihlmann, Martin et al., "Convolutional Recurrent Neural Networks for Electrocardiogram Classification." arXiv preprint rXiv:1710.06122 (2017).
[28] Warrick, Philip, and Masun Nabhan Homsi, "Cardiac Arrhythmia Detection from ECG Combining Convolutiol and Long Short-Term Memory Networks
[29]Soliński, Mateusz et al., "Classification of Atrial Fibrillation in Short-term ECG Recordings Using a Machine Learning Approach and Hybrid QRS Detection.", Computing 44 (2017).
[30] Maknickas et al., "Atrial Fibrillation Classification Using QRS Complex Features and LSTM.", Computing 44 (2017).
[31] By Wapcaplet - Own work, CC BY-SA 3.0, File:Diagram of the human heart (cropped).svg
[32]https://www.favoriteplus.com/prodimages/FP-RMH/handheld-ECG-FP-RMH-manual.pdf
[33] https://ya-webdesign.com/explore/ekg-drawing-anatomical-heart/
[34]https://www.cablesandsensors.com/pages/12-lead-ecg-placement-guide-with-illustrations
[35]https://www.dcbiomed.com/proimages/materials/Brochures_and_related_Articles/Introductory_guide_to_ECG_C2_0-950820.pdf
[36]https://subscription.packtpub.com/book/big_data_and_business_intelligence/9781785880360/1/ch01lvl1sec11/the-history-and-rise-of-deep-learning
[37]https://www.wandouip.com/t5i256938/
[38]http://www.programmersought.com/article/5764149301/
[39]https://medium.com/datadriveninvestor/neural-network-and-dropouts-b6690c869a18
[40]https://physionet.org/cgi-bin/atm/ATM?database=mitdb&tool=plot_waveforms
[41]https://docs.scipy.org/doc/scipy-0.18.1/reference/generated/scipy.signal.resample_poly.html
[42]A Real-Time QRS Detection Algorithm JIAPU PAN AND WILLIS J. TOMPKINS, SENIOR MEMBER, IEEE-IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. BME-32, NO. 3, MARCH 1985
[43]Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and EMD functions - Emran M Abu Anas, Soo Y Lee, Md K Hasan
[44]TensorFlow+Keras深度學習人工智慧實務應用 作者: 林大貴 出版社:博碩 出版日期:2017/06/09
[45] https://keras.io/callbacks/#earlystopping
[46]Vapnik, V. Support-vector networks. Machine Learning. 1995, 20 (3): 273–297. doi:10.1007/BF00994018
[47]https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊