臺灣博碩士論文加值系統

近年來，因心臟疾病死亡的人數占每年全國死亡率的前三名，良好的醫療照護環境逐漸受到重視，但醫療資源依然有限，不足以應付需要看診的病患，因此，透過辨識心律不整演算法自動辨識心電圖特徵，並分析產生出心電圖報告，能夠大幅減輕醫護人員的負擔，本論文將研究如何改進現有的辨識演算法，使心律不整的辨識率提升。本論文提出回饋式支持向量機模型，首先，使用心電圖特徵建立基礎的支持向量機模型，此時模型已經具有一定的辨識率，回饋方式是由醫生檢查辨識結果，將辨識錯誤的資料修正後更新訓練資料集，再產生新的辨識模型，另外，從支持向量機理論中發現，支持向量占所有資料的少部分，同時也是容易產生誤判的資料點，在回饋時只需檢查支持向量，如此一來可以降低醫生需確認的資料量。最後從實驗結果發現，經由回饋方法可以使模型辨識準確率提升，在實驗中比較隨機檢查與檢查支持向量方法，從實驗結果得知，後者只需檢查少量資料就能有效地改善準確率。

For the past few years, the mortality rate of heart disease is among the top three, but the medical resource is still limited to the patient who need to health care. If the ECG arrhythmia can be detected automatically, the medical resource can be better saved and the medical personnel’s burden can be further relieved. This paper studied how to improve the existing ECG arrhythmia pattern recognition algorithms to increase the accuracy of arrhythmia recognition.In this paper we proposed a SVM with feedback mechanism method. First of all, we use the R-R intervals as ECG features to build a SVM model. SVM model is evolved when the ECG arrhythmia pattern is reviewed by doctors iteratively. In particular, only support vectors are needed to be verified by doctors to revise the SVM, as a result, much effort can be saved when numerous ECG data is reviewed by doctors. Results show that our proposed scheme can reduce the verification time while maintain the recognition accuracy.

致謝辭 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 viii
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 2
1.3 論文架構 3
第二章 理論背景與相關知識 4
2.1 心電圖 4
2.1.1 心電訊號產生 4
2.1.2 心電訊號量測 5
2.1.3 心電圖定義 6
2.2 ECG訊號擷取設備 7
2.2.1 傳統ECG擷取 7
2.2.2 心跳帶 8
2.2.3 其他心率擷取設備 8
2.3 MIT-BIH心律不整資料庫 9
2.3.1 常見心律不整 11
2.4 支持向量機(Support Vecotor Machine) 11
2.4.1 SVM理論 12
2.4.2 C-Support Vector Machine(C-SVC) 15
2.4.3 LIBSVM函式庫工具 17
第三章 研究方法與架構 19
3.1 系統架構概述 19
3.2 資料擷取轉換 19
3.2.1 注釋資料擷取 19
3.2.2 ECG特徵計算 20
3.2.3 轉換LIBSVM資料格式 22
3.3 心律不整辨識 23
3.3.1 LIBSVM參數設定與方法 23
3.3.2 初始化資料集與SVM模型 28
3.3.3 SVM模型回饋方法 30
第四章 實驗結果 41
4.1 實驗環境 41
4.1.1 心律不整資料集數據 41
4.1.2 實驗測試方法 43
4.2 實驗結果 43
4.2.1 驗證SVM模型回饋前後準確率 43
4.2.2 驗證心電記錄辨識敏感度與特異度 45
4.2.3 修正資料量與準確率比較 47
第五章 結論與未來展望 51
參考文獻 52
附錄一 55
附錄二 58

[1] A.Alliche, K.Mokrani, ” Higher Order Statistics and ECG Arrhythmia Classification”, Signal Processing and Information Technology, 2003. ISSPIT 2003. Proceedings of the 3rd IEEE International Symposium on, pp. 641-643, Dec. 2003.
[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 Classi?cation”, 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] Jiapu Pan, Willis J. Tompkins, ” A Real-Time QRS Detection Algorithm”, IEEE Transactions on Biomedical Engineering, vol. BME-32, NO. 3, Mar. 1985.
[11] H. C. Bazett., ” An Analysis of The Time-Relations of Electrocardiograms”, History of Electrocardiology, Vol. 2, No. 2, Apr. 1997.
[12] Balraj Singh,Shashi Kala Nagarkoti, B. K. Kaushik,” A Modified Algorithm for Maternal Heart Rate Detection Using RR Interval ”, Emerging Trends in Networks and Computer Communications (ETNCC), 2011 International Conference on, pp. 39-42, Apr. 2011.
[13] Barbosa, P.R.B.,Barbosa-Filho J., Cordovil I., Nadal J., ” The Effect of the Instantaneous RR Interval on the Dynamic Properties of the Heart Rate and the Ventricular Repolarization Duration Variability”, Computers in Cardiology 2000 , pp. 821-824, Sep. 2000.
[14] Zhou Qunyi, ” The Electrocardiogram Classification Research on Electrocardiogram RR Interval Variation”, Computational Intelligence and Design, 2009. ISCID '09. Second International Symposium on, vol. 2, pp. 497-500, Dec. 2009.
[15] MG Tsipouras, DI Fotiadis, D Sideris, ” Arrhythmia Classification using the RR-Interval Duration Signal”, Computers in Cardiology, 2002, pp. 485-488, Sep. 2002.
[16] Chih-Chung Chang and Chih-Jen Lin, ” LIBSVM : a library for support vector machines”, ACM Transactions on Intelligent Systems and Technology, 2011.
[17] 關於起搏器和除顫器(一)心臟的電傳導系統，http://www.overseaswindow.com/node/8656，上網日期：2014-02-12。
[18] 王多柏，心電圖訊號原理及特性Electrocardiography，http://www.cc.ntut.edu.tw/~tpwang/tpwang.files/BioElectronic2012/ECG_tpwang.pdf，上網日期：2014-02-12。
[19] 行政院衛生署：衛生福利統計專區，死因統計，http://www.mohw.gov.tw/cht/DOS/Statistic.aspx?f_list_no=312&fod_list_no=5012，上網日期：2014-05-22。
[20] THE MERCK MANUAL The Merck Manual of Diagnosis and Therapy，http://www.merckmanuals.com/professional/cardiovascular_disorders/cardiovascular_tests_and_procedures/electrocardiography_ecg.html，上網日期：2014-02-12。
[21] 12導程心電圖機，http://tw.bysources.com/sample/show.php?supno=132421&recno=46639，上網日期：2014-05-22。
[22] HeartWave，http://tw.echowell.com.tw/heartwave/，上網日期：2014-05-22。
[23] ANT+ 2.4GHz 高頻數位對碼心率錶，http://tw.echowell.com.tw/product/ph-7/，上網日期：2014-05-22。
[24] ReadMyHeart V2.0，http://www.dcbiomed.com/ReadMyHeart:V2.0.html，上網日期：2014-05-22。
[25] PhysioBank ATM，http://www.physionet.org/cgi-bin/atm/ATM，上網日期：2014-03-05。
[26] Thorsten Joachims, SVM-Light Support Vector Machine, http://svmlight.joachims.org/，上網日期：2014-03-18。
[27] LS-SVMlab, http://www.esat.kuleuven.be/sista/lssvmlab/，上網日期：2014-03-18。