對於截癱或偏癱患者，本研究試圖利用由動作想像刺激患者μ節律的抑制現像作為控制開關來驅動鏡治療系統的影片重播功能。通過動作想像與視覺回饋的結合，希望這種腦機介面系統能夠比傳統的動作想像系統更有效地恢復腦部功能。然而，為了實現這一目標，我們需要開發一種能夠準確識別動作想像處理過程中產生的μ節律活動演算法。
本研究使用小波轉換來計算不同頻帶中的能量時變模式。通過向量量化編碼方法和主成分分析方法處理小波轉換後的結果，本研究開發了許多特徵來試圖偵測動作想像事件。具體而言，本研究開發並測試了三種不同的分類器。不幸的是，我們無法獲得令人滿意的分類結果。
通過增加腦波訊號頻道的數量，改善實驗環境和提高受測者的參與程度，希望未來的研究以這種結合動作想像與視覺反回饋系統來開發出更有效的μ節律偵測演算法。

For patients with paraplegia or hemiplegia, this work tries to use the inhibition phenomenon of the patient's μ rhythm activated by the motor imagery as a control switch to drive the video replay function of the mirror therapy system. By combining motor imagery with visual feedback, it is hoped that such a brain computer interface (BCI) system can more effectively recover the brain function than the traditional motor imagery system. However, to achieve this goal, we need to develop an algorithm that can accurately identify the μ rhythm activity generated during the motor imagery process.
This study used the wavelet transform to compute the energy time varying patterns in different frequency bands. By processing the wavelet transform results with vector quantization method and principal component analysis method, this study develops a number of features to try to detect the motor imagery events. In specific, this study developed and tested three different classifiers. Unfortunately, we are not able to obtain satisfactory classification results.
By increasing the number of electroencephalography (EEG) signal channels, improving the experimental environment and improving the degree of the involvement of the test subjects, it is hoped that future work can develop a more effective μ rhythm detection algorithm for this integrated motor imagery visual feedback system.

目錄
論文審定書 i
論文公開授權書 ii
誌謝 iii
摘要 iv
Abstract v
目錄 vi
圖次 viii
表次 xiii
第一章 緒論 1
1.1 前言 1
1.2 研究動機及目的 2
1.3 文獻回顧 4
1.4 論文架構 5
第二章 實驗方法與流程 6
2.1 實驗對象 6
2.2 實驗設備與環境 6
2.2.1 腦波擷取程式介面 10
2.3 實驗前處理 11
2.4 實驗流程 15
第三章 分析流程與方法 18
3.1 訊號前處理 18
3.1.1 連續小波轉換(Continuous Wavelet Transform, CWT) 21
3.2 向量量化編碼法(Vector Quantization, VQ) 24
3.2.1 事件與非事件視窗屬於事件基準Codewords的得票百分比 28
3.3 主成份項分析(Principal Components Analysis, PCA) 30
3.3.1 所有事件與非事件視窗各主軸的投影量平均及標準差 34
3.3.2 最大投影量在第N個主軸以下所佔的百分比 37
3.3.3 每個樣本點投影量由大至小排序後與原排序相減之得分百分比 37
3.4 事件及非事件樣本點間能量變動量總和 38
第四章 實驗結果與討論 41
4.1 屬於事件基準Codewords的投票結果 42
4.2 所有事件與非事件視窗各主軸的投影量平均及標準差 51
4.3 最大投影量在第N個主軸以下所佔的百分比 61
4.4 每個樣本點投影量由大至小排序後與原排序相減之得分百分比 64
4.5 事件與非事件樣本點間能量變動量總和 68
第五章 結論與建議 69
參考文獻 70
附錄 72

參考文獻
1. J.R.Wolpaw, N.Birbaumer, D.J.McFarland, G.Pfurtscheller, T.M.Vaughan. (2002). Brain-computer interfaces for communication and control. Clinical neurophysiology, official journal of the International Federation of Clinical Neurophysiology, 113, 767-791.
2. Hsin-Min Lee, Ping-Chia Li, Shih-Chen Fan. (2015). Delayed mirror visual feedback presented using a novel mirror therapy system enhances cortical activation in healthy adults. Jounal of NeuroEngineering and Rehabilitation, 12:56
3. S. P. Levine, J. E. Huggins, S. L. BeMent, R. K. Kushwaha, L. A. Schuh, M. M. Rohde, E. A. Passaro, D. A. Ross, K. V. Elisevich, and B. J. Smith. (2000). A direct brain interface based on event-related potentials. IEEE Trans Rehabil Eng, 8, 180-5
4. G.Pfurtscheller, J.Kalcher, C.Neuper, D.Flotzinger, M.Pregenzer. (1996). On-line EEG classification during externally-paced hand movements using a neural network-based classifier. Electroencephal. Clin. Neurophysiol, 99, 416-425.
5. G.Pfurtscheller, A.Aranibar. (1979). Evaluation of event-related desynchronization (ERD) preceding and following voluntary self-paced movement. Electroenceph. Clin. Neurophysiol, 46, 138-146.
6. G.Pfurtscheller, A.Berghold. (1989). Pattern of cortical activation during planning of voluntary movement. Electroenceph. Clin. Neurophysiol, 77, 250-258.
7. J.Kalcher, D.Flotzinger, C.Neuper, S.Golly, G.Pfurtscheller. (1996). Graz brain-computer interface II-Toward communication between humans and computer based on online classification of three different EEG patterns. Med. Biol. Eng. Comput, 34, 382-388.
8. G.Pfurtscheller, C.Neuper, A.Schlogl, and K.Lugger. (1998). Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans.Rehab.Eng, 6, 316-325.
9. Rizzolatti Giacomo, Craighero Laila. (2004). The mirror-neuron system. Annual Review of Neuroscience, 27, 169-192.
10. Stevens JA, Stoykov ME. (2004). Simulation of bilateral movement tranining through mirror reflection: a case report demonstrating an occupational therapy technique for hemiparesis. Top Stroke Rehabil, 11, 59-66.
11. Jeannerod M. (2001). Neural simulation of action: a unifying mechanism for motor cognition. Neuroimage, 14, 103-109.
12. Ertelt D, Small S, Solodkin A, Dettmers C, McNamara A, Binkofski F, et al. (2007). Action observation has a positive impact on rehabilitation of motor deficits after stroke. Neuroimage, 36(Suppl2) , 164-173
13. Hemzei F, Lappchen CH, Glauche V, Mader I, Rijintjes M, Weiller C. (2012). Functional plasticity induced by mirror training: the mirror as the element connection both hands to one hemisphere. Neuroehabil Neural Repair, 26, 484-496.
14. Brenner N, Rader C. (1976). A New Principle for Fast Fourier Transformation. IEEE Acoustics. Speech&Signal Processing, 24(3), 264-266.
15. Alan V. Oppenheim, Ronald W. Schafer, John R. Buck, Discrete-Time Signal Processing, Prentice Hall, ISBN 0-13-754920-2.
16. Paul S. Addison. (2002). The Illustrated Wavelet Transform Handbook, Institute of Physics, ISBN 0-7503-0692-0.
17. Gray, R.M. (1984). Vector Quantization. IEEE ASSP Magazine, 1(2), 4-29.
18. Jolliffe, I.T., Principal Component Analysis, Springer-Verlag. (1986). 487, ISBN 978-0-387-95442-4.