進階搜尋


 
系統識別號 U0026-0812200915233401
論文名稱(中文) 使用支持向量機於癲癇腦波分類之研究
論文名稱(英文) Classification of Epileptic EEG Signals by Using Support Vector Machine
校院名稱 成功大學
系所名稱(中) 電機工程學系碩博士班
系所名稱(英) Department of Electrical Engineering
學年度 97
學期 2
出版年 98
研究生(中文) 鍾銘峻
研究生(英文) Ming-jyun Chung
學號 V2696201
學位類別 碩士
語文別 英文
論文頁數 65頁
口試委員 口試委員-王維倫
口試委員-卓信誠
口試委員-鄭舜文
指導教授-賴源泰
口試委員-高啟洲
中文關鍵字 近似熵  離散小波轉換  支持向量機  腦波信號  癲癇  特徵 
英文關鍵字 SVM  DWT  ApEn  feature  epilepsy  EEG signal 
學科別分類
中文摘要 癲癇是一種常見的神經系統疾病之一,全球有將近1%的人口患有癲癇。癲癇是由大腦內部細胞異常放電所引起,因此在臨床偵測及診斷癲癇上,腦波信號已是非常重要的工具。一般是由訓練有素的專家或醫師利用肉眼檢視的方式,針對量測時間可能達數天之久的腦波信號來判斷癲癇發作的情形,因此這種方式相當地費時。另外,檢視者的主觀性質也將影響到其檢視分類的結果。所以,若有一檢視分類系統能夠自動地執行此程序,正確客觀地對腦波信號作出分類,將可節省許多時間,增加診斷結果的可靠度,輔助醫師作出更精確的診斷。

本篇論文中,我們提出一個架構,將五類的腦波信號藉由離散小波轉換及近似熵的分析過程,抽取出待分類的特徵,再利用支持向量機來針對特徵向量來作分類。首先利用離散小波轉換將濾波後的腦波信號分解為五個有含義的子頻帶,接著針對各個頻帶分別計算其近似熵值,接著我們提出一個特徵選擇的方法,從所求得的各頻帶小波係數統計值及近似熵值中適應性地選取出用以分類的特徵向量,最後再利用支持向量機來對不同類別的特徵向量精確地作分類。由實驗結果顯示,我們所提出的系統架構其分類的準確率可達98%,擁有不錯的效能及可靠度。
英文摘要 Epilepsy is one of the most common neurological disorders, and approximately 1% of people in the world suffer from epilepsy. Epilepsy is caused by abnormal discharges in the brain, thus electroencephalogram (EEG) signal has been an especially valuable clinical tool for the detection and diagnosis of epilepsy. An expert detects epileptic activity by visual inspection of the EEG, which is a time-consuming procedure for recordings that are days long. In addition, the subjective nature of the examination affects the outcome. Hence, automation of this process could save time, making the decision more reliable.

In this paper, we proposed an architecture for classification problem in five-class epileptic EEG-signals. We tried to classify EEG signals with support vector machine (SVM) according to features which were made by discrete wavelet transform (DWT) and approximate entropy (ApEn). The EEG signals were decomposed into five subbands by using DWT, then the ApEn values in subbands were computed. The feature vectors for classification were selected adaptively from statistical wavelet coefficients and ApEn values by proposed feature selection method. Finally, the SVMs were used for classifying the selected features. The experimental results showed the proposed system has great performance and reliability, and the total accuracy of classification could achieve 98%.
論文目次 摘要. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
Abstract. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
誌謝. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
Table of Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .iv
List of Figures. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .vi
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii

Chapter 1 Introduction. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1.1 Electroencephalogram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1.2 Epilepsy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.3 Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .4
1.4 Organization of the Thesis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .6
Chapter 2 EEG-signal Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.1 EEG Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .7
2.2 Background of Discrete Wavelet Transform . . . . . . . . . . . . . . . . . .9
2.2.1 Wavelet Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.2.2 Wavelet Family. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .10
2.2.3 Discrete Wavelet Transform. . . . . . . . . . . . . . . . . . . . . . . . . . . . .12
2.2.4 Convolution Based DWT. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .14
2.3 Multi-resolution Analysis of EEG Signals. . . . . . . . . . . . . . . . . . .18
2.4 Complexity Analysis: Approximate Entropy. . . . . . . . . . . . . . . . .21
2.4.1 Calculation of Approximate Entropy . . . . . . . . . . . . . . . . . . . . . .22
2.4.2 Properties of Approximate Entropy . . . . . . . . . . . . . . . . . . . . . . .25
2.4.3 Examples of Signal Analysis. . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
2.5 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
2.6 Feature Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
Chapter 3 Feature Classification by Support Vector Machine. . . . . . . . . 31
3.1 Background of Support Vector Machine . . . . . . . . . . . . . . . . . . . . 31
3.1.1 Linear Support Vector Classification . . . . . . . . . . . . . . . . . . . . . .32
3.1.2 Linear Support Vector Classification with a Soft Margin . . . . . . 36
3.1.3 Nonlinear Support Vector Classification . . . . . . . . . . . . . . . . . . . 39
3.1.4 Kernel Function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
3.2 Parameters of Support Vector Machine. . . . . . . . . . . . . . . . . . . . . .43
3.2.1 Choice Kernel. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .43
3.2.2 Properties of Parameters. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .44
3.3 Multi-class Support Vector Machine . . . . . . . . . . . . . . . . . . . . . . . .45
3.4 Parameter Optimization. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .47
3.5 Cross-validation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .48
Chapter 4 Experimental Results. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .50
4.1 Multi-resolution Signal Analysis. . . . . . . . . . . . . . . . . . . . . . . . . . . 50
4.2 Experimental Results of Classification. . . . . . . . . . . . . . . . . . . . . .54
4.2.1 Results in the First Experiment. . . . . . . . . . . . . . . . . . . . . . . . . . 54
4.2.2 Results in the Second Experiment. . . . . . . . . . . . . . . . . . . . . . . . 55
Chapter 5 Conclusions. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .57
Appendix. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58
Reference. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .61
參考文獻 [1] International League Against Epilepsy, “Guidelines for epidemiologic studies on epilepsy,” Commission on Epidemiology and Prognosis, International League Against Epilepsy, Epilepsia 34 [4]: pp. 592–596, 1993
[2] W. Blume, H. Lüders, E. Mizrahi, C. Tassinari, W. van Emde Boas, J. Engel, “Glossary of descriptive terminology for ictal semiology: report of the ILAE task force on classification and terminology,” Epilepsia 42 [9]: pp. 1212–1218, 2001.
[3] R. Fisher, W. van Emde Boas, W. Blume, C. Elger, P. Genton, P. Lee, J. Engel, “Epileptic seizures and epilepsy: definitions proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE),” Epilepsia 46 [4]: pp. 470–472, 2005.
[4] World Health Organization, “Epilepsy: aetiogy, epidemiology and prognosis,” February 2001.
[5] The National Society for Epilepsy, “What is Epilepsy?”, 2009 Available from http://www.epilepsynse.org.uk/AboutEpilepsy/Whatisepilepsy
[6] G. D. Cascino, “Epilepsy: contemporary perspectives on evaluation and treatment,” Mayo Clinic Proceedings, 69: pp. 1199–1211, 1994.
[7] J. Engel Jr., “Surgery for seizures,” The New England Journal of Medicine 334: pp. 647–652, 1996.
[8] International League Against Epilepsy, “Proposal for revised clinical and electroencephalographic classification of epileptic seizures,” Commission on Classification and Terminology of the International League Against Epilepsy, Epilepsia 22 [4]: pp. 489–501, 1981.
[9] R. G. Andrzejak, K. Lehnertz, F. Mormann, C. Rieke, P. David, and C. E. Elger, “Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state,” Physical Review E, vol. 64, p. 061907, 2001.
[10] EEG time series. (2006, Nov.). [Online]. Available: http://www.meb.uni-bonn.de/epileptologie/science/physik/physik.htm
[11] R. Polikar, “The Wavelet Tutorial.” http://users.rowan.edu/~polikar/
[12] T. Acharya and P.-S. Tsai, JPEG2000 Standard for Image Compression: Concepts, Algorithms and VLSI Architectures, Wiley-Interscience, 2004.
[13] S. G. Mallat, “A theory for multiresolution signal decomposition: the wavelet representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, pp. 674-693, July 1989.
[14] C. Zhang, C. Wang, and M. O. Ahmad, “A VLSI architecture for a high-speed computation of the 1D discrete wavelet transform,” ISCAS 2005, IEEE International Symposium on Circuits and Systems, vol.2, pp.1461–1464, May 2005.
[15] S.M. Pincus, “Approximate Entropy as a complexity measure,” Chaos 5, pp. 110–117, 1995.
[16] S. M. Pincus, A. L. Goldberger, “Physiological time-series analysis: what does regularity quantify?” American Journal of Physiology - Heart and Circulatory Physiology, vol. 266, pp. H1643-H1656, 1994.
[17] S. M. Pincus et al: “Not all (possibly) “random sequences” are created equal,” Proceedings of the National Academy of Science of the United State of America, Vol. 94, pp. 3513–3518, April 1997.
[18] S. M. Pincus and D. L. Keefe, “Quantification of hormone pulsatility via an approximate entropy algorithm,” American Journal of Physiology, vol. 262, no. 5, pp. e741–e754, 1991.
[19] G.M. Souza, R.V. Ribeiro, M.G. Santos, H.L. Ribeiro, R.F. Oliveira, “Approximate Entropy as a measure of complexity in sap flow temporal dynamics of two tropical tree species under water deficit,” Annals of the Brazilian Academy of Sciences 76 (3) pp. 625–630, 2004.
[20] P.M. Ngan, “Motion detection using Approximate Entropy,” in: Proceedings of the Digital Image Computing Techniques and Applications/Image and Vision Computing, Massey University, New Zealand, pp. 379–384, 1997.
[21] S. Pincus, R.E. Kalman, “Irregularity, volatility, risk, and financial market time series,” Proceedings of the National Academy of Sciences of the United States of America 101 [38] pp. 13709–13714, 2004.
[22] S. M. Pincus, “Assessing serial irregularity and its implications for health,” Annals of the New York Academy of Sciences, vol. 954, no. 10, pp. 245–267, 2001.

[23] R. Silipo, G. Deco, R. Vergassola, and H. Bartsch, “Dynamics extraction in multivariate biomedical time series,” Biological Cybernetic, vol. 79, no. 1, pp. 15–27, 1998.
[24] S. M. Pincus, “Approximate entropy as a measure of system complexity,” Proceedings of the National Academy of Science of the United State of America, vol. 88, pp. 2291-2301, 1994.
[25] I. Daubechies, “The wavelet transform, time-frequency localization and signal analysis,” IEEE Transactions on Information Theory, vol. 36, no. 5, pp. 961–1005, Sep. 1990.
[26] H. Adeli, Z. Zhou, and N. Dadmehr, “Analysis of EEG records in an epileptic patient using wavelet transform,” J. Neurosci. Methods, vol. 123, no. 1, pp. 69–87, 2003.
[27] N. Hazarika, J. Z. Chen, A. C. Tsoi, and A. Sergejew, “Classification of EEG signals using the wavelet transform,” Signal Process., vol. 59, no. 1, pp. 61–72, 1997.
[28] V. Vapnik, Estimation of Dependences Based on Empirical Data, Springer-Verlag, 1982.
[29] C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998.
[30] C. Cortes and V. Vapnik, “Support vector networks,” Machine Learning, vol. 20, pp. 273-297, 1995.
[31] V. Vapnik, The nature of statistical learning theory, Berlin, Germany, Springer-Verlag, 1995.
[32] J. C. Burges and B. Scholkopf, “Imporving the accuracy and speed of support vector learning machines,” in Advances in Neural Information Processing System 9 (M. Mozer, M. Jordan, and T. Petsche, eds.), pp. 375-381, Cambridge, MA: MIT Press, 1997.
[33] G. Fung, O. L. Mangasarian, and J. Shavlik, “Knowledge-based support vector machine classifiers,” in Advances in Neural Information Processing, 2002.
[34] T. Joachims, “Text categorization with support vector machines: learning with many relevant features,” in Proceedings of ECML-98, 10th European Conference on Machine Learning (C. Nedellec and C. Rouveirol, eds.), (Chemnitz, DE), pp. 137-142, Springer Verlag, Heidelberg, DE, 1998.

[35] K. Crammer and Y. Singer, “On the learnability and design of output codes for multiclass problems,” in Computational Learning Theory, pp. 35-46, 2000.
[36] V. Vapnik, Statistical Learning Theory. New York: Wiley, 1998.
[37] R. Fletcher, Practical methods of optimization. Chichester and New York: John Wiley and Sons, 1987.
[38] R. Courant and D. Hilbert, Methods of Mathematical Physics. Interscience, 1953.
[39] C. W. Hsu and C. J. Lin. “A comparison of methods for multi-class support vector machines,” IEEE Transaction on Neural Networks, vol. 13, pp. 415-425, March 2002.
[40] R.E. Fan, P.H. Chen, and C.J. Lin., “Working set selection using the second order information for training SVM,” Journal of Machine Learning Research 6, 1889-1918, April 2005.
[41] P.H. Chen, R.E. Fan, and C.J. Lin., ”A study on SMO-type decomposition methods for Support Vector Machines,” IEEE Transactions on Neural Networks, vol. 17, no. 4, July 2006.
[42] C.W. Hsu, C.C. Chang, and C.J. Lin, ”A practical guide to support vector classification,” Department of Computer Science, National Taiwan University, Taipei, Taiwan. [Online]. Available: http://www.csie.ntu.edu.tw/~cjlin
[43] N. Cristianini and J. Shawe-Taylor, An introduction to support vector machines and other Kernel-based learning methods. Cambridge University Press, 2000.
[44] H. Ocak, “Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy,” Expert Systems with Applications, vol. 36, pp. 2027–2036, 2008
[45] V. Srinivasan, C. Eswaran, N. Sriraam, “Approximate entropy-based epileptic EEG detection using artificial neural networks,” IEEE Transactions on Information Technology in Biomedicine, vol. 11, May 2007.
[46] Ruqiang Yan, Robert X. Gao, “Approximate Entropy as a diagnostic tool for machine health monitoring,” Mechanical Systems and Signal Processing 21, pp. 824-839, 2006
[47] Baikun Wan, Dong Ming, Hongzhi Qi, “Linear and nonlinear quantitative EEG analysis,” IEEE Magazine in Medicine and Biology, vol. 27, September 2008
[48] R. Ferenets, A. Anier, V. Jantti, S. Melto, S. Hovilehto, “Comparison of Entropy and Complexity Measures for the Assessment of Depth of Sedation” IEEE Transactions on Biomedical Engineering, vol. 53, pp. 1067-1077, June 2006.
[49] Zhiwei Li, Minfen Shen, “Classification of Mental Task EEG Signals Using Wavelet Packet Entropy and SVM,” International Conference on Electronic Measurement and Instruments, July 2007.
[50] Meng Hu, Jiaojie Li, Guang Li, Xiaowei Tang, “Classification of Normal and Hypoxia EEG Based on Approximate Entropy and Welch Power-Spectral-Density,” International Joint Conference on Neural Networks, July 2006.
[51] X. S. Zhang, R. J. Roy, E.W. Jensen, “EEG complexity as a measure of depth of anesthesia for patients,” IEEE Transactions on Biomedical Engineering, vol. 48, no. 12, December 2001.
[52] A. T. Tzallas, M. G. Tsipouras, D. I. Fotiadis, “The Use of Time-Frequency Distributions for Epileptic Seizure Detection in EEG Recordings,” Proceedings of the 29th Annual International Conference of the IEEE EMBS, pp. 23-26, August 2007.
[53] N. Radhakrishnan, B. N. Gangadhar, “Estimating regularity in epileptic seizure time-series data,” IEEE Magazine in Medicine and Biology, vol. 17, June 1998.
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2014-07-28起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2014-07-28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