臺灣博碩士論文加值系統

腦機介面研究是讓使用者能透過腦波的變化來控制電腦系統。可是腦波具有收集不易，卻易受週遭環境干擾的特性。所以本研究的主要目的在於研究獨立成份分析法(ICA)運用於手動腦波控制游標。獨立成份分析法是一種具有分離雜訊，還原原始訊號的統計方法，目前廣泛被利用於訊號處理、影像辨識的主題上。
本研究是透過研究動右手拇指與放鬆時大腦產生的μ波與β波能量值的變化，做為游標控制之用。本研究收集動右手拇指的腦波訊號。並利用獨立成份分析法過濾雜成分，快速傅立葉轉換將腦波從時域（time domain）轉換到頻域（frequency domain），再以統計分析方式，分析動右手拇指與放鬆時，μ波與β波（取14-22Hz）的哪些電極點位置和區段的能量值有顯著的差異。之後，將這些有差異的電極點位置和區段做為倒傳遞神經網路的輸入資料。倒傳遞神經網路是用來分類出放鬆和動右手大拇指的腦波。經過倒傳遞神經網路訓練所得的權重，將供即時游標控制之用。
實驗結果發現經獨立成份分析法過濾雜訊後的腦波資料，運用於類神經網路分類辨識與游標控制系統有不錯的效果。

Brain computer interface is a system which enables users to control the computer by the brain wave. However, collecting the brain wave is not easy, and it is easy to be interference by the environment. The goal of the research is to study the effect of independent component analysis performing in the cursor control of brain wave of hand movement. Independent component analysis (ICA) is the statistical method which can separate noise and retrieve original signal. ICA is used to the topics of signal processing, image recognition widely at present.
The research is to study the power of mu and beta activities of the brain for cursor control, while moving the right hand thumb and Loosening. We collected the brain wave signals of the right hand thumb. We used independent component analysis to filter the noise and fast fourier transform to transform brain wave from time domain into frequency domain. Then, by the statistical analysis method, we analyze mu and beta(14-22Hz) activities between moving the right hand thumb and Loosening to find out which electrodes and frames have significant difference. Next, the significant electrodes and frames are used for the input of the back-propagation neural network. The back-propagation neural network is used to classify brain wave between Loosening and moving the right hand thumb. After the learning of the back-propagation neural network, the trained weights are applied to the cursor control.
Based on the brain wave data filtered by independent component analysis, neural network performs well in classification, recognition and the cursor control system.

中文摘要 ………………………………………………………………………………………… i
英文摘要 …………………………………………………………………………………………ii
誌謝 …………………………………………………………………………………………iii
目錄 …………………………………………………………………………………………iv
表目錄 ………………………………………………………………………………………… v
圖目錄 …………………………………………………………………………………………vii

一、 緒論……………………………………………………………………………………1
1.1 研究動機………………………………………………………………………………1
1.2 研究目的………………………………………………………………………………1
1.3 論文架構………………………………………………………………………………2
二、 文獻探討…………………………………………………………………………………3
2.1 大腦的相關理論………………………………………………………………………3
2.2 獨立成份分析法的原理………………………………………………………………10
三、 實驗研究設計…………………………………………………………………………26
3.1 實驗研究設備…………………………………………………………………………26
3.2 實驗設計………………………………………………………………………………28
3.3 腦波訊號分析工具和方法……………………………………………………………30
四、 實驗結果與討論………………………………………………………………………37
4.1 統計分析………………………………………………………………………………37
4.2 分類結果………………………………………………………………………………40
4.3 實機測試結果…………………………………………………………………………46
五、 結論與建議……………………………………………………………………………49
5.1 結論……………………………………………………………………………………49
5.2 建議……………………………………………………………………………………50
參考文獻……………………………………………………………………………………………51
附錄…………………………………………………………………………………………………54

Bell A.J. and Sejnowski T.J. （1995）. An information maximization approach to blind separation and blind deconvolution, Neural Computation, 7(6), 1129-1159.

Hyvärinen A. and Oja. E. （2000）, Independent component analysis: algorithms and applications, Neural Networks, 13(4-5), 411-430.
http://www.cis.hut.fi/~aapo/pub.html#ICA%20on%20Images

Hyvärinen A. （1999）, Survey on independent component analysis, Neural Computing Surveys, 2, 94-128.

Hyvärinen. A. (1998). New approximations of differential entropy for independent component analysis and projection pursuit, Advances in Neural Information Processing Systems 10, 273-279, MIT Press.

Kozelka, J. W., & Pedley, T. A. （1990）. Beta amd mu rhythms, Journal of clinical neurophysiology 7, 191-207.

Jasper, H. H. （1958）, The ten twenty electrode system of the international Federation, Electroencephalography and clinical neurophysiology ,10, 371-375.

Kuhlman, W. N. （1978）. Functional topography of the human mu rhythm, Electroencephalography and clinical neurophysiology., Vol.44, 83-93.

Kuhlman, W. N. （1978a）. EEG feedback training , enhancement of somatosensory cortical activity, Electroencephalography and clinical neurophysiology., Vol.45, 290-294.

Pfurtscheller, G., & Aranibar, A. （1977）. Event-related cortical. desynchronization detected by power measurements of scalp EEG, Electroencephalography and clinical neurophysiology, Vol.42, 817-826.

Pfurtscheller, G., & Klimesch, W. （1989）. Cortical activation pattern during reading and recognition of words with dynamic event-related desynchronnization mapping, In: K. Maurer （Ed.）, Topographic Brain Mapping of EEG and Evoked Potentials.Springer Heidelberg., 305-313.
Pfurtscheller, G., Neuper, C., Schlogl, A., & Lugger, K. (1998), Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters, IEEE Transactions on Rehabilitation Engineering.,6（3）, 316-325.

Pfurtscheller, G., & Lopes da Silva, F. H.,. (1999), Event-related EEG/MEG synchronization and desynchronization : basic principles Electroencephalography and clinical neurophysiology. Vol.100, 1842-1857.

Pfurtscheller, G., & Neuper, C. （1997）, Motor imagery activates primary sensorimotor area in humans, Neuroscience letters., 329, 65-68.

Schalk, G., McFarland, D. J., Hinterberger, T., Birbaumer, N., & Wolpaw, J. R.（2004）, BCI2000: A General-Purpose Brain-Computer Interface （BCI）System,IEEE Transactions on Biomedical Engineering., 51(6), 1034-1043.

Wolpaw, J. R., D. J. McFarland, et al. （2000）, "Brain–Computer Interface Research at the Wadsworth Center", IEEE Transactions on Rehabilitation Engineering., 8（2）, 223.

Wolpaw, J. R., Birbaumer, N., McFarland, D. J., Pfurtscheller G., & Vaughan, T. M. (2002), Brain-computer interface for communication and control, Clinical Neurophysiology., Vol.113, 767-791.

連國珍 (1995)。數位信號處理簡介。台北市：茂昌。

關尚勇、林吉和 (2002)。破解腦電波－EEG 教材。台北縣新店市：藝軒。

呂金河 (1994)。線性代數。台北：華泰

林清江（1992）。心理與教育統計學。台北市：台灣東華

黃昭翰 (2004)。應用腦波於游標控制之腦機介面系統。資訊教育所, 國立台南大學. 碩士論文.

劉育芳 (2004)。人腦-電腦介面系統臨床實驗流程之分析研究。資訊教育所, 國立台南大學. 碩士論文.

維基百科 (Wikipedia) Nyquist–Shannon sampling theorem
http://en.wikipedia.org/wiki/Nyquist%E2%80%93Shannon_sampling_theorem