Basic Search / Detailed Display

Author: 沈世評
Shi-Ping Shen
Thesis Title: 用線性鑑別分析法做冥想四個方向的分類
Distinguishing the four Directions in Meditation through Linear Disciminant Analysis
Advisor: 葉榮木
Yeh, Zong-Mu
Degree: 碩士
Master
Department: 機電工程學系
Department of Mechatronic Engineering
Thesis Publication Year: 2005
Academic Year: 93
Language: 中文
Number of pages: 60
Keywords (in Chinese): 大腦人機介面腦電波線性鑑別分析法
Keywords (in English): BCI, EEG, LDA
Thesis Type: Academic thesis/ dissertation
Reference times: Clicks: 249Downloads: 34
Share:
School Collection Retrieve National Library Collection Retrieve Error Report

大腦人機介面(Brain-computer interface)是一種利用腦部訊號跟外界溝通的新技術,其目的是能夠幫助因神經肌肉損傷而行動受阻礙的人。對於內部刺激—想像左右手和腳動—已經有研究過了,但冥想四個方向是值得去研究。有鑑於此,本研究建立一套系統,它以冥想四個方向實驗的腦波訊號作為輸入訊號並利用快速傅立葉分析法找出腦波的特徵,然後利用線性鑑別分析法來分辨這些特徵。最後找出一組可以分辨冥想四個方向的腦波。
經由實驗結果得知,此系統可以利用實驗中分辨率最高的資料做為參考腦波,最佳的分辨率可達80%以上。未來可預計將此運用於人機介面上以造福神經疾病患者或行動不便人士。

The brain-computer interface (brain-computer interface) is a kind of new technology of utilizing brain signals to communicate with the external world. Its purpose is to help the person who is hindered take action because his neural muscle is damaged. Internal stimuli, such as imaging right-hand, left-hand, and foot moving, have been studied, but imaging four directions in meditation is worth being studied. For this reason, a system is developed, and the EEG of the four directions in meditation is taken as input signals and a fast Fourier analysis is used to find the features of the EEG. Then a linear discriminant analysis is adopted to classify the features. Finally, a set of brain waves, which can distinguish four directions in meditation, is obtained.
From the experimental results, it is better to use the data which the accuracy of the classification is the highest in the experiment to be the reference material. The best classification rate in the experiment data is more than 80%. In the future study, the system can be applied to brain-computer interface to benefit neural disease persons or disabled persons.

摘要....................................................I Abstract...............................................II 目錄..................................................III 圖目錄.................................................VI 表目錄................................................VII 第一章 緒論............................................1 一、前言...........................................1 二、研究背景.......................................1 (一)認識腦波..................................1 (二)腦波頻率..................................2 (三)事件相關的電位............................2 (四)腦波擷取系統..............................3 (五)認識冥想..................................5 三、研究動機.......................................5 四、研究目標........................................5 五、研究架構........................................6 六、系統架構........................................8 七、論文架構.......................................10 第二章 文獻探討........................................11 第三章 腦電波分析方法..................................20 一、腦電波的前處理.................................20 二、特徵擷取演算法.................................21 (一)快速傅立葉轉換法...........................22 (二)小波轉換分析...............................25 三、分類器演算法...................................27 (一)線性鑑別分析...............................27 第四章 實驗設備及實驗設計..............................30 一、實驗材料及設備.................................30 (一)受測者.....................................30 (二)本研究實驗的硬體設備.......................31 (三)本研究實驗的軟體設備.......................31 二、實驗硬體架構及器材配置.........................31 三、實驗步驟.......................................32 第五章 實驗結果與討論..................................35 一、快速傅立葉轉換與小波轉換的結果.................35 二、LDA分類器......................................40 三、錯誤率比較與結果分析...........................45 四、討論...........................................50 第六章 結論與未來展望..................................51 一、結論...........................................51 二、未來展望.......................................52 參考文獻...............................................53 附錄...................................................56 圖目錄 圖1.1 四種基本腦電波的頻率分布...........................2 圖1.2 腦電波儀電極配置圖.................................4 圖1.3 研究步驟流程圖.....................................7 圖1.4冥想四個方向的腦波檢測流程圖........................8 圖2.1實驗所用的圖像.....................................11 圖2.2實驗所用的圖像.....................................12 圖2.3虛擬鍵盤判斷的流程圖...............................13 圖2.4實驗所用的圖像.....................................14 圖2.5實驗所用的圖像.....................................15 圖2.6整個系統的示意圖...................................16 圖2.7分類器的對照表.....................................16 圖2.8虛擬鍵盤的示意圖...................................16 圖3.1 想像四個方向之腦電波分析流程......................20 圖3.2 原始腦波圖........................................21 圖3.3 去眼動的腦波圖....................................21 圖3.4 把N/2點的DFT分解成2個N/4點的DFT的流程圖...........24 圖3.5 8點DFT計算的完全分解流程圖.......................24 圖3.6 訊號X經兩次小波分解的流程圖.......................26 圖3.7 原始輸入訊號經多層小波分解後的頻帶分布............27 圖4.1 NeuroScan之NuAmps腦電波儀與實驗用品..............31 圖4.2 腦電波儀電極配置圖................................32 圖4.3 實驗設備示意圖....................................32 圖4.4 調整阻抗值動作....................................33 圖4.5 受測前的實驗圖形................................. 33 圖4.6 提示方向的刺激圖形............................... 34 圖4.7 一次實驗的流程圖................................. 34 圖5.1受測者所有腦電波的頻譜.............................35 圖5.2通道Cz的頻譜.......................................36 圖5.3 (a)載入未進行小波的向上腦電波.....................36 (b)載入未進行小波的向下腦電波...........................36 圖5.4 (a)載入未進行小波的向右腦電波.....................37 (b)載入未進行小波的向左腦電波...........................37 圖5.5 (a)進行小波轉換後的向上腦電波.....................38 (b)進行小波轉換後的向下腦電波...........................38 圖5.6 (a)進行小波轉換後的向右腦電波.....................39 (b)進行小波轉換後的向左腦電波...........................39 圖5.7 S1、S2每一組實驗用FFT做的分辨率..................40 圖5.8 S3、S4每一組實驗用FFT做的分辨率..................41 圖5.9 S1、S2每一組實驗用WT做的分辨率...................41 圖5.10 S3、S4每一組實驗用WT做的分辨率..................42 圖5.11 有明顯特徵的腦電波頻譜...........................42 圖5.12 4個LDA器參數與分類方向之關係圖..................43 圖5.13 S1、S2每一組實驗的分辨率........................45 圖5.14 S3、S4每一組實驗的分辨率........................46 圖5.15 S1、S2明顯的特徵值與分辨率之關係................47 圖5.16 S3、S4明顯的特徵值與分辨率之關係................48 圖5.17 S1、S2明顯的特徵值與無效數據之關係..............48 圖5.18 S3、S4明顯的特徵值與無效數據之關係..............49 表目錄 表2.1世界各地的大腦人機介面系統.........................17 表2.2 BCI系統問題分類...................................19 表5.1 4個LDA器所得到+和一值的查詢方向表................43 表5.2 各個LDA分類器所判定的結果.........................44 表5.3 S1、S2、S3、S4第一次實驗的有效資料數.............46 表5.4 S1、S2、S3、S4第十二組實驗的分辨率...............47 表5.5 調整有效條件到20μv/Hz的分辨率....................49

[1] 吳岳昌(民92)。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。
[2] 李國生(民93)。應用資料挖掘技術於長程聽覺誘發波P300與智商關係之研究。國立台南師範師學院資訊教育研究所碩士論文。
[3] 林景福(民77)。圖解腦波入門。台北市:九州。
[4] 林錦俊(民89)。雙記憶體之快速傅立葉轉換處理器的設計與製作。中華大學電機工程研究所碩士論文。
[5] 洪至懿(民91)。特徵擷取與分類應用與想像左右手手指運動之腦波辨識。國立陽明大學放射醫學科學研究所碩士論文。
[6]謝維廷(民91),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。
[7] Despain, A. M. ,“Very fast transform algorithms for hardware implementation”, IEEE Trans. Comput., vol C-28, pp. 333-341,May 1979.
[8] Haykin S. .Neural Network: A Comprehensive Foundation.–2nd ed, Prentice Hall.1999.
[9] Pfurtscheller G. “ERD as an index of anticipatory behavior”, Handbook of electroencephalography and clinical neurophysiology revised series, vol. 6, pp. 203-217., June 1999.
[10] Allison Brendan Z. and Pineda Jaime A., “ERPs Evoked by Different Matrix Sizes: Implications for a Brain Computer Interface (BCI) System”, IEEE Trans on Neural sys. and Rehabil Eng., vol. 11, no.2, June 2003.
[11] Gibson Oliver J., and James Christopher J. ,”Temporally Constrained ICA: An Application to Artifact Rejection in Electromagnetic Brain Signal Analysis”, IEEE Trans. on Biomedical Eng. , vol. 50, no. 9, Sep. 2003.
[12] James C.J. and Lowe D. ,” Single channel analysis of electromagnetic brain signals through ICA in a dynamical systems framework”, Neural computing research group, Aston university, Birmingham, United Kingdom, 2001.
[13] McFarland D.J. and Wolpaw J.R., “ Multichannel EEG-based brain-computer communication”, Electroencephalography and Clinical Neurophysiology,vol.90, pp.444-9,1994.
[14] Aleksandar Kostov, Julio Carballido, and Jorge Martinez,” Enhancement of EEG control signals in the development of a brain-computer interface”, Faculty of rehabilitation medicine, university of Alberta, 13-16, Oct.1999.
[15] Akiyama T., Gotman J., James C.J., Kobayashi K., and Nakahori T.,” Isolation of epileptiform discharges from unaveraged EEG by independent component analysis”, Clinical Neuro. vol. 110, 1999.
[16] Cheng Ming, Gao Shangkai ,and Gao Xiaorong,” Design and implementation of a brain-computer interface with high transfer rates” IEEE Trans on Bio. Eng., vol. 49, no. 10, Oct. 2002.
[17] Donchin E., Spencer K. M., and Wijesinghe R. ,”The mental prosthesis: assessing the speed of a P300-based brain-computer interface”, IEEE Trans Rehabil Eng, vol.8, no.2, June 2000.
[18] Duda R.O., Hart P. E., and Stork D.G. (2001). Pattern Classification.–2nd ed. (pp30-76). Canada, John Wiley & Sons , Inc.2001.
[19] Troster G., Thaler M., and Wosnitza M.,” A high precision 1024-point FFT processor for 2D convolution”, IEEEE Int. Solid-State Circuit Conf., vol. 41, pp. 118-119, 424, May 1998.
[20] Calhoun G., Jones K. S., McMillan G., and Middendorf M.,” Brain-computer interfaces based on the steady-state visual-evoked response”, IEEE Trans Rehabil Eng., vol.8, pp.211-4, June 2000.
[21] Graimann Bernhard, Mller G., Neuper Christa, and Pfurtscheller G.,” An Asynchronously Controlled EEG-Based Virtual Keyboard: Improvement of the Spelling Rate”, IEEE Trans. Rehabil Eng., vol. 51, no. 6, pp. 979-984, June 2004.
[22] Birbaumer N., Kbler A., Mller G., Neuper C., and Pfurtscheller G., “Clinical application of an EEG-based brain-computer interface: A case study in a patient with severe motor impairment”, Clin. Neurophysiol., vol. 114, no. 3, pp. 399–409, March 2003.
[23] Birbaumer N., Donchin E., Heetderks W.J., McFarland D.J., Peckham P.H., Robinson C.J., Quatrano L.A., Schalk G., Vaughan T.M., and Wolpaw J.R. ,” Brain-computer interface technology:a review of the first international meeting”, IEEE Trans. Rehabilitation Eng., vol.8, pp.164-73, May 2000.
[24] Jaime A. Pineda, David S. Silverman, Andrey Vankov, and John Hestenes, “Learning to Control Brain Rhythms: Making a Brain-Computer Interface Possible”, IEEE Trans. Neural. Syst. vol. 11, no. 2, June 2003.
[25] B. Obermaier, G. R. Mller, and G. Pfurtscheller, “Virtual Keyboard”Controlled by Spontaneous EEG Activity”, IEEE Trans. Neural. Syst. vol.11 no. 4, Dec. 2003.
[26] J. R. Wolpaw, D. J. McFarland, and T. M. Vaughan, “Brain–Computer Interface Research at the Wadsworth Center”, IEEE Trans. Rehabilitation Eng., vol.8 no.2, June 2000.
[27] Reinhold Scherer*, Gernot R. Mller, Christa Neuper, Bernhard Graimann, Gert Pfurtscheller, “An Asynchronously Controlled EEG-Based Virtual Keyboard: Improvement of the Spelling Rate”, IEEE Trans. Biomedical Eng., vol. 51, no. 6, June 2004.

QR CODE