本文關(guān)鍵詞： 腦-機(jī)接口 P300-Speller事件相關(guān)電位 支持向量機(jī) 線性判別分析 基于集成學(xué)習(xí)思想的支持向量機(jī)遞歸特征篩選　出處：《天津大學(xué)》2012年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：P300-Speller是利用稀少事件相關(guān)電位(Event-Related Potential, ERP)—P300信號(hào)特征實(shí)現(xiàn)文字選擇輸入的經(jīng)典人機(jī)交互范式。它能夠?qū)崿F(xiàn)受試者利用腦電與外界進(jìn)行文字交流的功能,已公認(rèn)是腦-機(jī)接口(Brain-Computer Interface, BCI)技術(shù)中目前最為有效的信息輸入與交互的重要手段之一。傳統(tǒng)6×6行列字符閃爍模式的P300-Speller因其存在可選字符數(shù)目有限、信息傳輸效率低、不利于大指令集傳輸?shù)葐?wèn)題,難以滿足實(shí)際應(yīng)用需求。為此,引入新的編碼刺激模式以改進(jìn)傳統(tǒng)P300-Speller范式、擴(kuò)展其字符數(shù)、提高其信息傳輸率并保持較高的分類(lèi)正確率是研發(fā)實(shí)用型P300-Speller BCI亟待解決的關(guān)鍵技術(shù)。 本文首次提出了基于三維編碼字符的閃爍刺激模式,并對(duì)該模式誘發(fā)產(chǎn)生的P300信號(hào)特征進(jìn)行了細(xì)致分析,論證了其取得較高分類(lèi)正確率和信息傳輸率的可行性。在此基礎(chǔ)上研究設(shè)計(jì)了基于三維編碼閃爍模式的64字符和125字符兩種改進(jìn)型P300-Speller;完成了傳統(tǒng)6×6行列字符、三維編碼64字符和125字符三種刺激模式實(shí)驗(yàn);對(duì)實(shí)驗(yàn)數(shù)據(jù)進(jìn)行了具體的預(yù)處理、特征提取與模式識(shí)別及分類(lèi)正確率與信息傳輸率的比較分析。 研究中,首先對(duì)實(shí)驗(yàn)數(shù)據(jù)進(jìn)行濾噪、降采樣等預(yù)處理。之后,分別采用Fisher系數(shù)和r2系數(shù)方法對(duì)腦電特征進(jìn)行了可分性分析;利用相干平均方法提取了腦電特征并分別采用線性判別分析(Linear Discriminant Analysis, LDA)和支持向量機(jī)(Support Vector Machine, SVM)方法進(jìn)行了腦電模式識(shí)別,所有被試的平均分類(lèi)正確率可以達(dá)到99%以上。最后,比較了傳統(tǒng)行列模式和新型三維編碼模式的信息傳輸速率(Information Transfer Rate, ITR),結(jié)果表明三維編碼的ITR(最高平均值為53.59bit/min)明顯高于行列模式(最高平均值為32.94bit/min)。文中還利用基于集成學(xué)習(xí)思想的支持向量機(jī)遞歸特征篩選方法進(jìn)行了導(dǎo)聯(lián)優(yōu)化。優(yōu)化結(jié)果表明,大部分受試者的64導(dǎo)聯(lián)實(shí)驗(yàn)數(shù)據(jù)在去掉60個(gè)次要導(dǎo)聯(lián)后分類(lèi)正確率還能穩(wěn)定在80%以上,且保留的重要導(dǎo)聯(lián)集中在頭頂部,與神經(jīng)電生理學(xué)預(yù)示以頭皮電極監(jiān)測(cè)P300的最佳位置一致。以上研究結(jié)果可望為設(shè)計(jì)開(kāi)發(fā)具有大字符集、大指令集、高信息傳輸率和高分類(lèi)正確率的新型實(shí)用P300-Speller腦-機(jī)接口提供關(guān)鍵技術(shù)保障。
[Abstract]:P300-Speller is Event-Related Potential using rare event-related potentials. ERP)-P300 signal features realize the classical human-computer interaction paradigm of text selection input, which can realize the function of using EEG to communicate with the outside world. It has been recognized as Brain-Computer Interface. The traditional 6 脳 6 column character scintillation mode P300-Speller has a limited number of optional characters because of its existence. Information transmission efficiency is low, which is not conducive to the transmission of large instruction sets, so it is difficult to meet the needs of practical applications. Therefore, a new coding stimulation model is introduced to improve the traditional P300-Speller paradigm. Expanding the number of its characters, improving its information transmission rate and maintaining a high classification accuracy are the key technologies to be solved in the development of practical P300-Speller BCI. In this paper, for the first time, a flicker stimulation model based on 3D coded characters is proposed, and the characteristics of P300 signal induced by this model are analyzed in detail. The feasibility of achieving high classification accuracy and information transmission rate is demonstrated. Based on this, two improved P300-Spell models based on 3D encoding scintillation mode, 64 characters and 125 characters, are studied and designed. Er; The experiments of traditional 6 脳 6 column character, 64 character 3D coding and 125 character stimulation mode are carried out. The experimental data are preprocessed, feature extraction and pattern recognition, classification accuracy and information transmission rate are compared and analyzed. In the study, the experimental data were preprocessed with noise filtering and sampling reduction. Then, the Fisher coefficient and R2 coefficient were used to analyze the separability of EEG characteristics. The EEG features were extracted by the coherent averaging method and linear Discriminant Analysis was used respectively. LDAs and support vector machine support Vector machines (SVM) were used to recognize EEG patterns. The average classification accuracy of all subjects can reach more than 99%. Finally. The information Transfer rate (ITR) of the traditional row-column mode and the new 3D coding mode are compared. The results show that the ITR (maximum average value is 53.59 bit / min) in 3D coding is significantly higher than that in column model (highest average value is 32.94 bit / min). In this paper, the support vector machine recursive feature selection method based on integrated learning is also used to optimize the lead. The optimization results show that. Most of the 64 lead data were stable above 80% after the 60 secondary leads were removed, and the remaining important leads were concentrated on the top of the head. These results are consistent with the best position predicted by neuroelectrophysiology to monitor P300 with scalp electrode. The above results are expected to have a large character set and a large instruction set for design and development. The new practical P300-Speller brain-computer interface with high information transmission rate and high classification accuracy provides key technical support.
【學(xué)位授予單位】：天津大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類(lèi)號(hào)】：R318.0

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳振洲;鄒麗珊;;核Foley-Sammon變換[J];廣州大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年04期

2 胡曉晴,唐娜;體感誘發(fā)電位的基本原理[J];國(guó)外醫(yī)學(xué)(物理醫(yī)學(xué)與康復(fù)學(xué)分冊(cè));2005年02期

3 于玲;吳鐵軍;;集成學(xué)習(xí):Boosting算法綜述[J];模式識(shí)別與人工智能;2004年01期

4 孔薇,楊杰,周越;基于獨(dú)立成分分析的強(qiáng)背景噪聲去噪方法[J];上海交通大學(xué)學(xué)報(bào);2004年12期

5 Kübler A.;Nijboer F.;Mellinger J. ;J.R. Wolpaw;李一明;;ALS患者能利用感覺(jué)運(yùn)動(dòng)節(jié)律控制人腦-電腦接口[J];世界核心醫(yī)學(xué)期刊文摘(神經(jīng)病學(xué)分冊(cè));2005年09期

6 陳華富;獨(dú)立成分分析及其應(yīng)用的研究進(jìn)展[J];生物醫(yī)學(xué)工程學(xué)雜志;2003年02期

7 郝冬梅,阮曉鋼;腦電事件相關(guān)去同步化和同步化的神經(jīng)元群模型[J];生物物理學(xué)報(bào);2005年01期

8 何慶華;吳寶明;王禾;鐘渝;伍亞舟;石銳;程光輝;;不同視覺(jué)刺激模式對(duì)視覺(jué)誘發(fā)電位的影響[J];中國(guó)康復(fù)醫(yī)學(xué)雜志;2007年02期

9 張勝;王蔚;;基于支持向量機(jī)的BCI導(dǎo)聯(lián)選擇算法[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2009年04期

10 楊幫華,顏國(guó)正,嚴(yán)榮國(guó);腦-機(jī)接口研究進(jìn)展[J];中國(guó)醫(yī)療器械雜志;2005年05期

相關(guān)博士學(xué)位論文 前4條

1 何慶華;基于視覺(jué)誘發(fā)電位的腦機(jī)接口實(shí)驗(yàn)研究[D];重慶大學(xué);2003年

2 毛勇;基于支持向量機(jī)的特征選擇方法的研究與應(yīng)用[D];浙江大學(xué);2006年

3 張莉;基于自發(fā)腦電信號(hào)的腦—機(jī)接口的研究[D];重慶大學(xué);2008年

4 綦宏志;腦—機(jī)接口中上肢想象動(dòng)作側(cè)向性識(shí)別的關(guān)鍵技術(shù)研究[D];天津大學(xué);2008年

相關(guān)碩士學(xué)位論文 前1條

1 安興偉;基于數(shù)字拼寫(xiě)的視—聽(tīng)聯(lián)合刺激誘發(fā)ERP研究[D];天津大學(xué);2010年

，

本文編號(hào)：1481584