(18.204.227.34) 您好!臺灣時間:2021/05/19 08:44
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:::

我願授權國圖
: 
twitterline
研究生:賴業奇
研究生(外文):Yeh Chi Lai
論文名稱:一個以腦機介面系統為基礎的字元辨識演算法之開發
論文名稱(外文):Development of a signal processing-based technique for Brain Computer Interface (BCI) system with the applications to automated character recognition
指導教授:陳思文陳思文引用關係
指導教授(外文):S. W. Chen
學位類別:碩士
校院名稱:長庚大學
系所名稱:電子工程學研究所
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:2008
畢業學年度:96
論文頁數:63
中文關鍵詞:腦機介面P300腦波字元辨識
外文關鍵詞:Brain Computer InterfaceBCIP300electroencephalogramEEGCharacter Recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:237
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:3
近年來,有越來越多的研究人員,從事大腦人機介面(BCI)開發的研究工作,其起初的發展原因是為了提供一些特殊病患,例如脊椎受傷、全身癱瘓者,甚至於漸凍人,而開發的一種有別於傳統的新的人機溝通方式。由於技術的逐步發展,進而有了以意念操控機械為主題的商業用品,此發展使得腦機介面系統不只應用於病患,也應用於一般大眾身上。本研究主題為一個以腦機介面系統為基礎的字元辨識演算法之開發,簡單的來說就是利用「意念」來打字,而且將其演算法整合至由紐約Wadsworth Center 所提供的BCI2000系統裡。整合後的系統以新的演算法,以偵測腦波P300為特徵,再利用樣板比對的方式來達成一個即時的字元辨識腦機介面系統。在此,我們採用一個由BCI Competition 2003所提供的資料庫來進行演算法的模擬與驗證。經過許多次的實驗證明,以此新的演算法在特定的條件下,可達100%的正確率。
In many years, more and more researchers have dedicated their efforts to exploring Brain Computer Interface (BCI) technology. In originally, the technology is developed for some patients such as brainstem stroke, brain spinal cord injury, or amyotrophic lateral sclerosis (ALS), and is a communication system that that does not depend on the brain’s normal output pathways of peripheral nerves and muscles. Because of the BCI developing, the BCI system is not only for the patients but also for the population. Also, development of BCI systems for consumers is an interesting topic. In this research, a signal processing-based technique for Brain Computer Interface (BCI) system with the applications to automated character recognition is developed. The task of character recognition based on the use of P300 evoked potential, and is implemented on BCI2000 system which offers from Wadsworth Center in New York. The performance evaluated using the database which provide by the BCI competition 2003 produce perfect recognition accuracy, 100%.
Table of Contents
Acknowledgments
Chinese Abstract
Abstract
Table of Contents
List of Figure
List of Table
CHAPTER 1 Introduction
1.1 Motivation
1.2 Overview
CHAPTER 2 Background of this research
2.1 System structure of BCI2000
2.1.1 Operator module
2.1.2 Source module
2.1.3 Signal processing module
2.1.4 Application module
2.2 Deficiency of BCI2000
CHAPTER 3 Methodology
3.1 Integrating an existing commercial A/D converters into BCI2000
3.1.1 Hardware specification of PCI1710HG
3.1.2 Integrating the A/D converter into the source module
3.2 Template matching
3.3 Linear Discriminate Function (LDF)
3.3.1 Classification problem for tow distribution
3.3.2 Classification with multivariate Gaussian distribution
3.4 A novel P300 detection algorithm
3.4.1 The proposed Detection flow
CHAPTER 4 Performance Evaluation
4.1 Descriptions of a computerized EEG database
4.2 Numerical experimental results based on Matlab and discussion
CHAPTER 5 Conclusion & future work
Reference

Figure 1-1 64 positions which generally used on the scalp
Figure 1-2 The general independent BCI is divided some parts, such as signal acquisition, signal processing, and application.
Figure 2-1 Schematic block diagram of the BCI2000 system.
Figure 2-2 some commercial EEG acquisition devices
Figure 2-3 the conceptual diagram of the signal processing module
Figure 2-4 6 by 6 chessboards of characters
Figure 2-5 The solid line present a P300 evoked potential, and the dotted line shows a normal brain wave.
Figure 2-6 StimulusCode:1-6 left-most column, 7-12 upper-most row. StimulusType:1, when intensified row/column contains the desired character. 0, when intensified row/column does not contain the desired character. Flashing:1, intensified. 0, otherwise. SelectedTarget:Label characters, there are 36 characters. 15
Figure 3-1 (a) an A/D converter card (PCI card) or the equipment for EEG acquisition (b) using the database which comes from the EEG recorded device
Figure 3-2 Item1 Set the A/D channels to be either single-ended or differential input . Item2 Set the D/A reference voltage for the D/A output channel 1. Item3 Set the D/A reference voltage for the D/A output channel 2. Click the Options button, display the dialog below to set the expansion board parameters.
Figure 3-3 Item1: Select the expansion board type ( only PCI-1710 HG/HGL supports PCLD-8710).Item2: Disable or enable the CJC ( Cold Junction Compensation) circuitry.Item3: List the channel gain. Item4: Delete the expansion board. Item5: Return Device Manager dialog below.
Figure 3-4 the relation of different modules and functions Figure 3-5 A template with a prediction signal presents here and its correlation coefficient is 0.69.
Figure 3-6 A template with a signal which is notmeaningful presents here and its correlation coefficient is 0.37. 25
Figure 3-7 the range of amplitude features shows around the 71ed point.
Figure 3-8 Alignment of the EEG segment with the P300 template; the correlation coefficient between both signals is 0.0171.
Figure 3-9 The P300 evoked potential detection flow
Figure 4-1 6 by 6 matrix of characters
Figure 4-2 The simulation system of P300 detection procedure in Matlab
Figure 4-3 The percent of correct obtained at each level of communication seed.

Tanle 2-1: It shows the parameters that are related to P300-based BCI.
Tanle 3-1: the specification of ADVANDTECH PCI1710HG 19
Tanle 4-1: The result with twenty designated EEG amplitude values acquires form the simulation.
Tanle 4-2: The result with the morphological information acquires form the simulation.
Tanle 4-3: the result of five designated EEG samples (close to the 300 ms) and the correlation coefficient
Tanle 4-4: A listing of the prediction rates obtained from different values of N
Tanle 4-5: In the original testing database and the prediction rates versus N
4-6: A new P300 template applied to all the 8 words in the original testing dataset.
[1] Touradj Ebrahimi, Jean-Marc Vesin, and Gary Garcia,“Interface in multimedia communication,” IEEE Signal Processing Magazine, January 2003.
[2] Jonathan R.Wolpaw (Guest Editor), Niels Birbaumer, William J. Heetderks, Dennis J. McFarland, P. Hunter Peckham, Gerwin Schalk, Emanuel Donchin, Louis A. Quatrano, Charles J. Robinson, and Theresa M. Vaughan (Guest Editor),“Brain–computer interface technology: a review of the first international meeting,” IEEE Transactions on Rehabilitation Engineering, vol. 8, no. 2, June 2000.
[3] Jorge Baztarrica Ochoa, Gary Garcia Molina, Touradj Ebrahimi, EEG Signal Classification for Brain Computer Interface Applications.
[4] Gerwin Schalk, Member, IEEE, Dennis J. McFarland, Thilo Hinterberger, Niels Birbaumer, and Jonathan R.Wolpaw, “BCI2000: a general-purpose brain-computer interface (BCI) system,” IEEE Transactions on Biomedical Engineering, vol. 51, no. 6, June 2004.
[5] Gilles Blanchard and Benjamin Blankertz,“BCI competition 2003—data set IIa: spatial patterns of self-controlled brain rhythm modulations,” IEEE Transactions on Biomedical Engineering, vol. 51, no. 6, June 2004.
[6] Licai Yang1, Jinliang Li1, Yucui Yao 1, Guanglin Li, “An algorithm to detect P300 potentials based on F-Score channel selection and support vector machines,” IEEE Third International Conference on Natural Computation , ICNC 2007.
[7] Seyedehmina Ayoubian Markazi , Student Member, IEEE, S. Qazi , Student Member, IEEE, Lampros. S. Stergioulas , Member, IEEE , , Anusha Ramchurn , & David Bunce, “Wavelet filtering of the P300 component in event-related potentials,” Proceedings of the 28th IEEE EMBS Annual International Conference, New York city, USA, pp.1719-1722, August 2006
[8] D.J. Krusienski, E.W. Sellers and T.M. Vaughan, “Common spatio-temporal patterns for the P300 speller,” Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering, pp.421-424, USA, May 2-5, 2007
[9] Theresa M. Vaughan, Dennis J. McFarland, Gerwin Schalk, William A. Sarnacki, Dean J. Krusienski, Eric W. Sellers, and Jonathan R. Wolpaw, “The wadsworth BCI research and development program: at home with BCI,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 14, no. 2, June 2006.
[10] Emanuel Donchin, Kevin M. Spencer, and Ranjith Wijesinghe, “The mental prosthesis: assessing the speed of a P300-based brain–computer interface,” IEEE Transactions on Rehabilitation Engineering, vol. 8, no. 2, June 2000.
[11] Donchin, E., Spencer, K.M., Wijensinghe, R., “The mental prosthesis: assessing the speed of a P300-based brain-computer interface,” IEEE Trans. Rehab. Eng. 8:174-179, 2000.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊