腦電波是從人類的頭皮所量測到的訊號，經由放大、濾雜訊、特徵擷取、分類、辨識，藉由大腦人機介面，可用來控制義肢，或訓練人們的專注力。本研究是提出一個結合主成份分析法及線性鑑別分析法對腦電波訊號做特徵擷取，來提昇辨識想像左右手動的辨識率。本論文中的實驗共有四名受測者，年齡約在二十三歲到二十六歲之間，而實驗主要的內容，是讓受測者想像左手動及右手動並擷取腦電波訊號。在腦電波訊號處理的過程中，利用主成份分析法及線性鑑別分析法做特徵擷取，接著使用最近鄰居法則做資料分類，實驗結果顯示四位受測者的平均辨識率可達85.75%，此辨識率結果優於其他相關方法。

Electroencephalogram (EEG) signals are recorded at the scalp surface through the electrodes. After amplifying, denoising, classifying and recognition the signal, they can be used to control machine equipment or training people for improving concentration by using a Brain Computer Interface(BCI) system. In this paper, a classification method based on Principal Component Analysis(PCA) and Linear Discriminant Analysis (LDA) is proposed to classify imagery tasks for left-hand and right-hand movements. Four healthy subjects, aged 23-26 years, were volunteered to participate in an experiment. During the experiment, two imagery tasks were to be stimuli. The feature extraction can be determined by the Principal Component (PCA) and Linear Discriminant Analysis (LDA). The method also uses Nearest Neighbor Rule (NNR) to classify the processed data. The experimental results show that the average accuracy rates is improved to 85.75%. According to the experimental results, the classification method based on Principal Component (PCA) and Linear Discriminant Analysis (LDA) is better than those of other literatures raised in this paper.

[1]陳志瑋，「研究以小波神經網路作μ波即時鑑別」，國立成功大學機械工程學系碩士論文，2002。
[2]吳岳昌，「探討ERD方法在腦機介面系統設計之效能」，國立交通大學電機與控制工程學系碩士論文，2003。
[3]T. M. Vaughan, “Guest editorial brain-computer interface technology:
A review of the second international meeting,” IEEE Trans. Rehabil.Eng., vol. 11, no. 2, pp. 94–109, 2003.
[4]D. M. Taylor, S. I. H. Tillery, and A. B. Schwartz, “Direct cortical control of 3D neuroprosthetic devices,” Science, vol. 296, no. 5574, pp. 1829–1832, 2002.
[5]謝維延，「禪定腦電波頻帶判讀系統設計」， 國立交通大學電機與控制工程學系碩士論文，2003
[6]劉勇鈞，「應用於指動偵測之腦電波訊號分析系統」， 國立成功大學資訊工程學系 碩士論文，2004。
[7]http://www.internetactu.net/wp-content/documents/bci_brainlab.jpg
[8]B. Blankertz, G. Dornhege, M. Krauledat, K.-R.Müller, V. Kunzmann, F. Losch, and G. Curio, “The berlin brain-computer interface: EEG-based communication without subject training,” IEEE Trans. Rehabil. Eng., vol. 14, no. 2, pp. 147–152, 2006.
[9]Xiang Liao, Dezhong Yao, Dan Wu, and Chaoyi Li, “Combining Spatial Filters for the Classification of Single-Trial EEG in a Finger Movement Task,” IEEE Trans. Biomed. Eng., vol. 54, no. 5, pp. 821-831, 2007.
[10]http://www.dls.ym.edu.tw/neuroscience/nsdivide_c.htm
[11]http://www.dls.ym.edu.tw/neuroscience/functional_c.htm
[12]黃津操，「適應性類神經模糊推論系統辨識腦電波P300」，國立臺灣師範大學機電科技學系碩士論文，2005。
[13]Baharan Kamousi, Zhongming Liu, and Bin He, Fellow, IEEE, “Classification of Motor Imagery Tasks for Brain-Computer Interface Applications by Means of Two Equivalent Dipoles Analysis,” IEEE Transactions On Neural Systems And Rehabilitation Engineering, vol. 13, no. 2, June 2005.
[14]Byung G. Jo and Myung H. Sunwoo, “New Continuous-Flow Mixed-Radix (CFMR) FFT Processor Using Novel In-Place Strategy,” IEEE Transactions on Circuits and Systems-1:Regular Papers, vol. 52, no. 5, pp. 911-919, 2005.
[15]McFarland D. J. McFarland and J. R. Wolpaw, “Sensorimotor rhythm-based brain computerinterface (BCI): Feature selection by regression improves performance,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 13, no. 3, pp. 372–379, 2005.
[16]S. Lemm, B. Blankertz, G. Curio, and K.-R. Müller, “Spatio-spectral filters for improved classification of single trial EEG,” IEEE Trans. Biomed. Eng., vol.52, no. 9, pp. 1541–1548, 2005.
[17]M. Fatourechi, A. Bashashati, R.Ward, and G. Birch, “A hybrid genetic algorithm approach for improving the performance of the LF-ASD brain computer interface” in Proc. Int. Conf. Acoust. Speech Signal Process., 2004, vol. 5, pp. 345–348.
[18]D. J. McFarland and J. R.Wolpaw, “Sensorimotor rhythm-based brain computer
interface (BCI): Feature selection by regression improves performance,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 13, no. 3, pp. 372–379, Sep. 2005.
[19]B. Blankertz, G. Dornhege, C. Schaefer, R. Krepki, J. Kohlmorgen, K. Mueller, V. Kunzmann, F. Losch, and G. Curio, “Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 11, no. 2, pp. 127–131, Jun. 2003.
[20]M. Kirby and C. Anderson, “Geometric analysis for the characterization of nonstationary time-series,” in Springer Applied Mathematical Sciences Series Celebratory Volume for the Occasion of the 70th Birthday of, L. Sirovich, E. Kaplan, J. Marsden, and K. R. K. Sreenivasan, Eds. New York: Springer-Verlag, 2003, ch. 8, pp. 263–292.
[21]C. W. Anderson, E. A. Stolz, and S. Shamsunder, “Multivariate autoregressive models for classification of spontaneous electroencephalogram during mental tasks,” IEEE Trans. Biomed. Eng., vol. 45, no. 3, pp. 277–286, Mar. 1998.
[22]G. Gage, K. Ludwig, K. Otto, E. Ionides, and D. Kipke, “Naive coadaptive cortical control,” J. Neural Eng., vol. 2, pp. 52–63, 2005. T. Rosipal, L. Trejo, and B. Matthews, “Kernel PLS-SVC for linear and nonlinear classification,” in Proc. 20th Int. Conf. Machine Learning(ICML-2003), Washington, DC, 2003, pp. 640–647.
[23]Bernhard Obermaier, Christa Neuper, Christoph Guger, and Gert Pfurtscheller, “Information Transfer Rate in a Five-Classes Brain–Computer Interface,” IEEE Transactions On Neural Systems And Rehabilitation Engineering, vol. 9, no. 3, September 2001.
[24]C. Guger, G. Edlinger, W. Harkam, I. Niedermayer, and G. Pfurtscheller, “How Many People are Able to Operate an EEG-Based Brain-Computer Interface (BCI)?”, IEEE Transactions On Neural Systems And Rehabilitation Engineering, VOL. 11, NO. 2, JUNE 2003.
[25]Gert Pfurtscheller, Christa Neuper, Alois Schl¨ogl, and Klaus Lugger, “Separability of EEG Signals Recorded During Right and Left Motor Imagery Using Adaptive Autoregressive Parameters,” IEEE Transactions On Neural Systems And Rehabilitation Engineering, vol. 6, no. 3, September 1998.
[26]沈世評，「用線性鑑別分析法做冥想的四個方向」，國立臺灣師範大學機電科技學系碩士論文，2005。
[27]林志穎，「數位音訊廣播系統中轉換器之電路設計」，國立成功大學電機工程學系碩士論文，2001。
[28]Aleix M. Martinez, and Avinash C. Kak, “PCA versus LDA,” IEEE Trans on Pattern Analysis and Machine Intelligence, vol.23, no.2, pp. 228 - 233 , 2001.
[29]Jyh-Shing Roger Jang, "Data Clustering and Pattern Recognition," (in Chinese) available at the links for on-line courses at the author's homepage at http://www.cs.nthu.edu.tw/~jang.
[30]張志豪、陳鴻彬、陳柏琳，「資料導向線性特徵轉換於中文大詞彙連續語音辨識之應用」， 「2005年全國計算機會議(National Computer Symposium, NCS)」， December 15-16, 2005。
[31]Jieping Ye and Qi Li, “A Two-Stage Linear Discriminant Analysis via QR-Decomposition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, pp. 929 – 941, 2005.
[32]洪倩玉，「建立動態線性鑑別分析於線上人臉辨識與驗證」。國立成功大學資訊工程學系碩士論文，2003。
[33]S. Noushath, Kumar G. Hemantha, and P. Shivakumara, “(2D)2LDA: An efficient approach for face recognition,” Pattern Recognition, vol 39, pp. 1396 – 1400, 2006.
[34]陳若涵，「以音樂內容為基礎的情緒分析與辨識」。國立清華大學資訊與應用系統學系碩士論文，2006。
[35]Keinosuke Fukunaga and Donald Hummels, “Leave-one-out Procedures for Nonparametric Error Estimates,” IEEE Trans on Pattern Analysis and Machine Intelligence, vol. 11, no. 4, pp. 421-423, 1989.
[36]Ömer Nezih Gerek and Dogan Gökhan Ece, “Power-Quality Event Analysis Using Higher Order Cumulants and Quadratic Classifiers,” IEEE Transactions on Power Delivery, vol. 21, no. 2, pp. 883-889, 2006.
[37]http://www.ics.uci.edu/~mlearn/MLRepository.html
[38]http://www.neuroscan.com/landing.cfm
[39]http://www.mathworks.com/
[40]J. Malmivuo and R. Plonsey, Bioelectromagnetism, 1st ed. New York, New York: Oxford University Press, 1995.