近年來，腦機介面 (Brain–computer interface, BCI) 作為溝通大腦與外界的新橋梁，是很多研究團隊的熱門項目並被應用在眾多領域之中。
腦電波(Electroencephalography, EEG)至今已發現許多特性，比如事件相關同步/去同步(event related synchronization/desynchronization, ERS/D)。依據事件相關同步/去同步的理論，再由腦機介面對腦電波訊號進行處理，便能達到解析人類運動想像(motor imagery, MI)的目的。
本研究提出一個應用於事件相關同步/去同步腦機介面的分類辨識演算法，其中包含對線上資料庫原始資料的正規化與時頻分析，依據事件相關同步/去同步分析擴大不同群資料間之差異並降維，最後在交叉驗證下以K最近鄰、支持向量機以及類神經網絡作為對資訊的分類演算法並比較。本篇論文著重於對特徵的擷取，提出一個嶄新並有效的擷取方法「閥值偵測」，與如何最佳化其所使用之參數。其基礎在於對應運動腦區之能量變化會較於劇烈，因此定義一個閥值來計算其能量變化超越此閥值之次數，作為特徵值以進行分類。其閥值之定義方法以腦波帽各電極所接收到之最大能量一定百分比獲得，並有一套標準衡量其百分比之數值。
分析之粗資料使用自線上資料庫，共使用96個受測者資料，每個受測者左/右手運動想像資料各21筆。離線實驗結果顯示本研究提出之方法其辨識率相較使用同一個資料庫來源的其他方法有一定的提升，對左右手運動意圖的辨識率最高可達到97.62%。

In recent years, Brain–computer interfaces (BCIs) have been widely studied and become popular research topics on the applications of many fields.
Several electroencephalography (EEG) features have been discovered so far, such as event related synchronization/desynchronization (ERS/D). By recording the EEG signal from BCI and processing based on ERS/D, the objective to analyze and estimate human motor intention is accessed. However, EEG signal is unstable and non-linear, and has a low tolerance for noise. Therefore, how to process the signal and extract features properly is the main topic in this field.
In this study, we propose a classification algorithm for L/R hand motor imagery (MI) based on ERS/D. Several techniques are applied, including Short-Time Fourier Transform (STFT), cosine normalization, feature extraction based on ERS/D, Linear discriminant analysis (LDA), k-nearest neighbors algorithm (kNN), Support Vector Machine (SVM), Artificial Neural Network (ANN) and Leave-One-Out Cross-Validation (LOOCV). We mainly focus on designing the methods to extract the features, which are novel and robust, and propose how to optimize the parameters in it.
Results show that our proposed method has a better performance than others with same database, and the classification accuracy 97.62% for L/R hand MI is achieved.

中文摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vi
表目錄 ix
第 1 章 緒論 1
1.1 前言 1
1.2 研究動機與目的 4
1.3 章節簡介 4
第 2 章 文獻回顧 5
2.1 事件相關之同步與去同步 5
2.2 實驗設備 8
2.3 分析方法 10
第 3 章 系統架構 12
3.1 實驗環境與實驗方法 13
3.2 分類辨識演算法流程 16
3.3 訊號前處理 17
3.4 特徵擷取 20
3.5 特徵降維 24
3.6 特徵分類 28
3.7 交叉驗證 37
第 4 章 實驗結果與討論 40
4.1 效能評估參數 40
4.2 特徵擷取參數 40
4.3 交叉驗證樣本散布圖 44
4.4 類神經網路結果討論 48
4.5 分類演算法比較 49
4.6 全部受測者準確率以及閥值比較 50
4.7 與其他論文比較 53
第 5 章 結論與未來展望 53
參考文獻 54

[1] Niedermeyer E. and da Silva F.L. Electroencephalography: Basic Principles, Clinical Applications, and Related Fields. Lippincot Williams & Wilkins. 2004. ISBN 0-7817-5126-8.
[2] Po-Chih Kuo, Yi-Ti Chen, Yong-Sheng Chen, Li-Fen Chen, Decoding the Perception of Endogenous Pain from Resting-state MEG, NeuroImage, 2016 http://www.sciencedirect.com/science/article/pii/S1053811916305183
[3] Sharbrough F, Chatrian G-E, Lesser RP, Lüders H, Nuwer M, Picton TW (1991): American Electroencephalographic Society Guidelines for Standard Electrode Position Nomenclature. J. Clin. Neurophysiol 8: 200-2.
[4] Ed Grabianowski,“How Brain-computer Interfaces Work,＂HowStuffWorks.com,
http://computer.howstuffworks.com/brain-computer-interface1.htm, 2007.
[5] Y. M. Chi, Y. T. Wang, Y. Wang, C. Maier, T. P. Jung, and G. Cauwenberghs, “Dry and Noncontact EEG Sensors for Mobile Brain–Computer Interfaces,＂ Neural Systems and Rehabilitation Engineering, IEEE Transactions on, vol.20, no.2, pp.228–235, March 2012.
[6] available: http://www.bem.fi/book/13/13.htm
[7] G. Pfurtscheller, C. Neuper, C. Guger, W. Harkam, H. Ramoser, A. Schlogl, B. Obermaier, and M. Pregenzer, “Current trends in graz brain-computer interface (bci) research,” Rehabilitation Engineering, IEEE Transactions on, vol. 8, no. 2, pp. 216–219, Jun 2000.
[8] L. Penghai, and W. Baikun, “A Study on EEG Alpha Wave-based Brain-Computer Interface Remote Control System,＂ Mechatronics and Automation, 2007. ICMA 2007. International Conference on,pp.3179–3184, Aug. 2007.
[9] Gert Pfurtscheller and Christa Neuper, “Motor Imagery and Direct Brain–Computer Communication,” proceedings of the IEEE, vol. 89, no. 7, July 2001
[10] L. Bi, X. Fan, and Y. Liu, “EEG-Based Brain-Controlled Mobile Robots: A Survey,＂ Human-Machine Systems, IEEE Transactions on, vol.43, no.2, pp.161–176, March 2013.
[11] A. L. Goldberger, L. A. N. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, and H. E. Stanley, "PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals," Circulation, vol. 101, pp. e215-e220, 2000.
[12] R. N. Bracewell, The Fourier Transform and Its Applications, 3rd ed., Boston, McGraw Hill, 2000.
[13] Alan V. Oppenheim, Ronald W. Schafer, John R. Buck : Discrete-Time Signal Processing, Prentice Hall, ISBN 0-13-754920-2
[14] available: https://www.mathworks.com/help/wavelet/gs/from-fourier-analysis-to-wavelet-analysis.html
[15] Schalk, Gerwin; Mellinger, Juergen (2010). A Practical Guide to Brain-Computer Interfacing with BCI2000 (1st ed.). Springer.
[16] K. K. Ang, C. Guan, K. S. Chua, B. T. Ang, C. Kuah, C. Wang, K. S. Phua, Z. Y. Chin, and H. Zhang, “A clinical study of motor imagery-based brain-computer interface for upper limb robotic rehabilitation,＂ Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE, pp. 5981–5984, 3-6 Sept. 2009.


[17] M. R. Portnoff, “Representation of digital signals and systems based on short-time Fourier analysis,” ZEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-28, pp. 55-69, Feb. 1980.
[18] Devijver, P. A., and J. Kittler, Pattern Recognition: A Statistical Approach, Prentice-Hall, London, 1982
[19] Harris, F. J. (1978). "On the use of windows for harmonic analysis with the discrete Fourier transform". Proceedings of the IEEE. 66: 51. doi:10.1109/PROC.1978.10837.
[20] JL Flanagan, Speech Analysis, Synthesis and Perception, Springer- Verlag, New York, 1972
[22] Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006, pp 192.
[23] Richard O. Duda, Peter E. Hart, and David G. Stork, Pattern Classification, 2nd ed., John Wiley & Sons, 2001, pp 123.
[24] Altman, N. S. (1992). "An introduction to kernel and nearest-neighbor nonparametric regression". The American Statistician. 46 (3): 175–185. doi:10.1080/00031305.1992.10475879.
[25] C. C. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition,＂ in Proceeds of Int. Conference on Data Mining and Knowledge Discovery, vol. 2, pp. 121–167, 1988.
[26] Jean-Philippe Vert, Koji Tsuda, and Bernhard Schölkopf (2004). "A primer on kernel methods". Kernel Methods in Computational Biology.
[27] Graves, Alex; and Schmidhuber, Jürgen; Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks, in Bengio, Yoshua; Schuurmans, Dale; Lafferty, John; Williams, Chris K. I.; and Culotta, Aron (eds.), Advances in Neural Information Processing Systems 22 (NIPS'22), December 7th–10th, 2009, Vancouver, BC, Neural Information Processing Systems (NIPS) Foundation, 2009, pp. 545–552
[28] DREYFUS, STUART E. (1990). "Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure". Journal of Guidance, Control, and Dynamics. 13 (5): 926–928. ISSN 0731-5090. doi:10.2514/3.25422.
[29] Kohavi, Ron. A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. 1995, 2 (12): 1137–1143. (Morgan Kaufmann, San Mateo)
[30] Ana Loboda, Alexandra Margineanu, Gabriela Rotariu, and Anca Mihaela Lazar. “Discrimination of EEG-Based Motor Imagery Tasks by Means of a Simple Phase Information Method.” (IJARAI) International Journal of Advanced Research in Artificial Intelligence, Vol. 3, No.10, 2014
[31] E. Bou Assi1, S. Rihana2, M. Sawan1. “33% Classification Accuracy Improvement in a Motor Imagery Brain Computer Interface.” Journal of Biomedical Science and Engineering. Vol.10 No.06(2017), Article ID:77330,16 pages 10.4236/jbise.2017.106025