跳到主要內容

臺灣博碩士論文加值系統

(44.212.99.208) 您好!臺灣時間:2024/04/23 23:30
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:陳功儒
研究生(外文):Gong-ru Chen
論文名稱:一個為個別使用者設計的游標控制腦機介面
論文名稱(外文):A Study on Subject-specific Brain-computer Interface for Cursor Control
指導教授:余松年余松年引用關係
指導教授(外文):Sung-nien Yu
學位類別:碩士
校院名稱:國立中正大學
系所名稱:電機工程所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:英文
論文頁數:58
中文關鍵詞:頻譜特徵人腦-電腦介面腦波自迴歸模型特徵選擇
外文關鍵詞:frequency domainauto-regressive modelEEGbrain-computer interface
相關次數:
  • 被引用被引用:0
  • 點閱點閱:336
  • 評分評分:
  • 下載下載:67
  • 收藏至我的研究室書目清單書目收藏:3
本論文主要目的為發展一個人腦-電腦介面,讓使用者透過螢幕上即時顯示的游標來嘗試將游標移動至位於水平(上、下)、垂直(左、右) 兩個維度上的目標。我們首先以於許凱程腦神經科診所的數位腦波機,量得之八位使用者的14 個電極腦波訊號做離線分析,將資料做切割,並以自迴歸模型分析其頻譜之後,取其alpha 波與beta 波之頻譜特徵,試圖以費雪辨別分析與全域搜尋法找出個別使用者最具代表性的電極點的特徵組合,並以不同組合評估及比較其分類準確率。我們發現透過選擇之後的電極特徵,著實讓離線分析的準確率提升,特別是全域搜尋法所選擇之電極特徵組合,對於每一位使用者都有明顯的進步。
我們將每位使用者於離線分析時所得到之最佳的電極點特徵組合應用至即時系統,並以即時的自迴歸分析取其指定的特徵,後端以改良之最小均方 (Leastmean square) 線性分類器當作是游標移動量與電極特徵之間的轉換器,此線性分類器將電極特徵轉換成游標的移動量藉以提供者一個視覺回授路徑,使用者需要自我嘗試著將游標控制擊中目標。
在離線分析的階段,我們以全域搜尋法所選出的電極特徵當作控制源,在水平控制方面,八位使用者的平均準確率為83.3%,垂直控制為77.46%。我們將離線分析結果最佳的兩位使用者特別挑出做線上游標控制實驗,於水平控制之平均擊中率為87.5%,而垂直控制為81.25%。
In this thesis, a brain-computer interface, which is an interface between human brain and the computer, is developed, such that subjects can control the cursor on the
screen to hit the target appears on two-dimensional positions. We utilized the EEG signals of eight subjects, measured by the digital EEG device in a neurologist clinic,
for offline analysis. The signals were segmented and spectral analyzed by the auto-regressive model, such that the frequency domain features of the alpha- and beta-rhythm were calculated. We selected the subject-specific channel-feature pair for each subject by the Fisher discriminality analysis and the full search method, and the
classification accuracies of different channel-feature combinations were evaluated. We discovered that the accuracy of offline analysis was significantly improved with the channel-feature selection. Especially for the channel-feature pair selected by the full search method, substantial improvement for every subject was observed.
We applied the optimal subject-specific channel-feature pair derived in the offline stage for each subject, in the online system. A real-time auto-regressive analysis extracted the designated features and sent them to the modified LMS-based linear classifier such that the features were translated into the movements of the cursor.
The movement translation process produced the cursor movement which further provided a visual feedback pathway to the subject. The subjects self-regulated to control the cursor to hit the target.
In the offline stage, we treated the channel-feature pair selected by the full search method as the control source, and obtained an average accuracy of 83.3% for horizontal control, and 77.46% for vertical control (Table 5.5 and 5.6). The two subjects who have induced the best results were recruited in the online cursor control experiments. For the horizontal movement tasks, we had 87.5% accomplishing rate in average, whereas, 81.25% for vertical (Table 5.11 and 5.12).
中文摘要..................................................I
ABSTRACT.................................................II
TABLE OF CONTENTS........................................IV
LIST OF FIGURES.........................................VII
LIST OF TABLES...........................................IX
I. INTRODUCTION.....................................1
1.1 Motivation.......................................1
1.2 Background.......................................2
1.2.1 Brain............................................2
1.2.2 Electroencephalography (EEG).....................4
1.3 Brain-computer interface.........................6
1.3.1 Categorization of brain-computer interface.......7
1.3.2 Structure of brain-computer interface............9
1.4 Goal of this thesis.............................11
1.5 These framework.................................11
II. LITERATURE REVIEW...............................13
2.1 Graz ERD/ERS-based brain-computer interface [14]..13
2.1.1 Event-related desynchronization and event-related synchronization..........................................13
2.1.2 The Graz BCI....................................14
2.2 The Wadsworth brain-computer interface [12].......15
2.3 Other brain-computer interfaces today.............18
III. EXPERIMENT MATERIALS............................19
3.1 EEG signal acquisition............................19
3.2 Experimental paradigm.............................20
3.2.1 Offline studies.................................20
3.2.2 Online system...................................22
IV. METHODS.........................................25
4.1 System framework................................25
4.2 Feature extraction ..............................27
4.2.1 Signal segmentation.............................28
4.2.2 Auto-regression (AR) model......................28
4.2.3 Feature vector normalization....................30
4.3 Channel-feature selection.......................31
4.3.1 Fisher discriminality analysis..................31
4.3.2 Full search method..............................33
4.4 Classification and movement translation.........34
4.4.1 K nearest neighbor classifier...................34
4.4.2 LMS-based linear classifier.....................35
4.4.3 Pseudo-inverse weight derivation linear classifier ................................................39
V. EXPERIMENTAL RESULTS............................41
5.1 Offline analysis................................41
5.2 Simulation of the online program................45
5.2.1 Results based on pseudo-inverse weight derivation linear classifier........................................45
5.2.2 Results based on LMS-based linear classifier....47
5.3 Online program..................................49
VI. CONCLUSION AND FUTURE WORKS.....................52
6.1 Conclusion......................................52
6.2 Future works....................................53
6.3 Summary.........................................54
REFERENCE ................................................55
[1] J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, and T. M.Vaughan, "Brain-computer interfaces for communication and control," Clinical Neurophysiology, vol. 113, pp. 767-791, Jun 2002.
[2] http://en.wikipedia.org/wiki/Main_Page.
[3] C. Del Gratta, V. Pizzella, F. Tecchio, and G. L. Romani, "Magnetoencephalography - a noninvasive brain imaging method with 1 ms time resolution," Reports on Progress in Physics, vol. 64, pp. 1759-1814, Dec 2001.
[4] http://www.bem.fi/book/13/13x/1302ax.htm.
[5] J. A. Wilson, E. A. Felton, P. C. Garell, G. Schalk, and J. C. Williams, "ECoG factors underlying multimodal control of a brain-computer interface," 2006, pp. 246-250.
[6] W. D. Penny, S. J. Roberts, E. A. Curran, and M. J. Stokes, "EEG-Based communication: A pattern recognition approach," IEEE Transactions on Rehabilitation Engineering, vol. 8, pp. 214-215, Jun 2000.
[7] T. Yamaguchi, K. Nagala, P. Q. Truong, M. Fujio, K. Inoue, and G. Pfurtscheller, "Pattern recognition of EEG signal during motor imagery by using SOM," 2008, pp. 2617-2630.
[8] J. F. Stein, Neuroscience :an introduction: Wiley,2006.
[9] J. R. Wolpaw and D. J. McFarland, "Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans," Proceedings of the National Academy of Sciences of the United States of America, vol. 101,pp. 17849-17854, Dec 2004.
[10] G. E. Fabiani, D. J. McFarland, J. R. Wolpaw, and G. Pfurtscheller, "Conversion of EEG activity into cursor movement by a brain-computer interface (BCI)," IEEE Transactions on Neural Systems and Rehabilitation
Engineering, vol. 12, pp. 331-338, Sep 2004.
[11] D. J. McFarland, A. T. Lefkowicz, and J. R. Wolpaw, "Design and operation of an EEG-based brain-computer interface with digital signal processing technology," Behavior Research Methods Instruments & Computers, vol. 29, pp. 337-345, Aug 1997.
[12] J. R. Wolpaw, D. J. McFarland, and T. M. Vaughan, "Brain-computer interface research at the Wadsworth Center," IEEE Transactions on Rehabilitation
Engineering, vol. 8, pp. 222-226, Jun 2000.
[13] N. Birbaumer, A. Kubler, N. Ghanayim, T. Hinterberger, J. Perelmouter, J. Kaiser, I. Iversen, B. Kotchoubey, N. Neumann, and H. Flor, "The thought translation device (TTD) for completely paralyzed patients," IEEE Transactions on Rehabilitation Engineering, vol. 8, pp. 190-193, Jun 2000.
[14] 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," IEEE Transactions on Rehabilitation Engineering, vol. 8, pp. 216-219, Jun 2000.
[15] D. J. M. J.R. Wolpaw, "EEG-based brain-computer interface," Eletroenceph. Clin. Neurophyiol., vol. 90, pp. 444-449, 1994.
[16] G. Pfurtscheller and F. H. L. da Silva, "Event-related EEG/MEG synchronization and desynchronization: basic principles," Clinical Neurophysiology, vol. 110, pp. 1842-1857, Nov 1999.
[17] G. Pfurtscheller, C. Guger, G. Muller, G. Krausz, and C. Neuper, "Brain oscillations control hand orthosis in a tetraplegic," Neuroscience Letters, vol.292, pp. 211-214, Oct 2000.
[18] C. Neuper, A. Schlogl, and G. Pfurtscheller, "Enhancement of left-rightsensorimotor EEG differences during feedback-regulated motor imagery," Journal of Clinical Neurophysiology, vol. 16, pp. 373-382, Jul 1999.
[19] G. Pfurtscheller, C. Neuper, D. Flotzinger, and M. Pregenzer, "EEG-based discrimination between imagination of right and left hand movement," Electroencephalography and Clinical Neurophysiology, vol. 103, pp. 642-651,
Dec 1997.
[20] A. Schlogl, D. Flotzinger, and G. Pfurtscheller, "Adaptive autoregressive modeling used for single-trial EEG classification," Biomedizinische Technik,
vol. 42, pp. 162-167, Jun 1997.
[21] J. Muller-Gerking, G. Pfurtscheller, and H. Flyvbjerg, "Designing optimal spatial filters for single-trial EEG classification in a movement task," Clinical
Neurophysiology, vol. 110, pp. 787-798, May 1999.
[22] H. Ramoser, J. Muller-Gerking, and G. Pfurtscheller, "Optimal spatial filtering of single trial EEG during imagined hand movement," IEEE Transactions on
Rehabilitation Engineering, vol. 8, pp. 441-446, Dec 2000.
[23] M. P. A. Kostov, "Parallel man-machine training in development of EEG-based cursor control," IEEE Transactions on Rehabilitation Engineering,vol. 8, pp. 203-205, Jun 2000.
[24] G. E. Birch, S. G. Mason, and J. F. Borisoff, "Current trends in brain-computer interface research at the Neil Squire Foundation," 2003, pp. 123-126.
[25] 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, "A direct brain interface based on event-related potentials," IEEE Transactions on Rehabilitation Engineering, vol. 8, pp. 180-185, Jun 2000.
[26] B. Graimann, J. E. Huggins, S. P. Levine, and G. Pfurtscheller, "Toward a direct brain interface based on human subdural recordings and wavelet-packet analysis," IEEE Transactions on Biomedical Engineering, vol. 51, pp. 954-962, Jun 2004.
[27] M. Akay, Biomedical Signal Processing. New Jersey, 1994.
[28] S.-N. Yu and Y.-H. Chen, "Selection of Higher Order Subband Features for ECG Beat Classification," in EUSIPCO 2008 Switzerland, 2008.
[29] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification. New York: Wiley, 2001.
[30] G. Golumb and W. Kahan, "Calculating the Singular Values and Pseudo-inverse of a Matrix," SIAM Numerical Analysis, vol. B 2, pp. 205-224, 1965.
[31] C. M. Bishop, Neural Networks for Pattern Recognition. Oxford, U.K.:Claredon, 1995.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top