本文選題：腦-機(jī)接口 + 多模態(tài)�。� 參考：《杭州電子科技大學(xué)》2017年碩士論文

【摘要】：腦-機(jī)接口(Brain-Computer Interfaces,BCI)是一種直接從中樞神經(jīng)系統(tǒng)提取信息,采用人的思維直接操作外圍設(shè)備的新技術(shù),是未來人機(jī)交互的最高形態(tài)。腦-機(jī)接口不僅廣泛應(yīng)用于醫(yī)學(xué)康復(fù)領(lǐng)域,在軍事、休閑娛樂、心理衛(wèi)生和人工智能等多個(gè)領(lǐng)域都具有較高的研究意義和價(jià)值。本文首先介紹了腦-機(jī)接口的相關(guān)研究背景,針對(duì)傳統(tǒng)基于單一模態(tài)腦電(electroencephalography,EEG)腦-機(jī)接口易受環(huán)境噪聲干擾、分類精度低等問題,在EEG腦-機(jī)接口的研究基礎(chǔ)上,引入功能近紅外成像(function Near Infrared Spectroscopy,fNIRS)技術(shù),設(shè)計(jì)并簡(jiǎn)化了基于握拳動(dòng)作的EEG-fNIRS多模態(tài)腦-機(jī)接口的實(shí)驗(yàn)范式,研究最重要的特征提取與分類環(huán)節(jié)。首先,利用實(shí)驗(yàn)室EEG、fNIRS采集與分析系統(tǒng)對(duì)三名受試者進(jìn)行EEG-fNIRS的同步采集實(shí)驗(yàn),并對(duì)原始信號(hào)進(jìn)行濾波去噪、基線校正等預(yù)處理。根據(jù)握拳動(dòng)作誘發(fā)的EEG信號(hào)的事件相關(guān)去同步、事件相關(guān)同步現(xiàn)象及其時(shí)頻特性,提取了EEG信號(hào)的頻帶能量、AR模型系數(shù)和小波系數(shù)特征;同時(shí)根據(jù)握拳動(dòng)作引起的血液動(dòng)力學(xué)響應(yīng)的特點(diǎn),提取含氧血紅蛋白濃度不同時(shí)段的均值及斜率特征。對(duì)特征向量進(jìn)行歸一化處理之后,采用線性判別分析(Linear Differential Analysis,LDA)及支持向量機(jī)(Support Vector Machines,SVM)對(duì)不同類型特征分類并進(jìn)行8次5折交叉驗(yàn)證。結(jié)果表明,EEG的小波系數(shù)特征分類效果要好于頻帶能量與AR模型參數(shù)結(jié)合的特征;fNIRS的斜率特征分類效果要好于均值特征,其中斜率特征分類正確率最高的時(shí)間段在執(zhí)行動(dòng)作任務(wù)之后的3~5s。其次,根據(jù)單模態(tài)特征分類結(jié)果,提出了基于EEG小波系數(shù)和fNIRS斜率結(jié)合的融合特征,并對(duì)結(jié)合特征使用主成分分析(Principal Component Analysis,PCA)。然后采用LDA、SVM分類,并進(jìn)行8次5折交叉驗(yàn)證,對(duì)比多模態(tài)信號(hào)與單模態(tài)信號(hào)的分類正確率。結(jié)果表明,經(jīng)過特征融合的握拳動(dòng)作任務(wù)平均識(shí)別率比單獨(dú)的EEG特征和fNIRS特征提高3~9%。表明fNIRS能夠顯著增強(qiáng)基于EEG的腦-機(jī)接口性能,利用多模態(tài)腦信號(hào)能夠提高傳統(tǒng)腦-機(jī)接口系統(tǒng)的性能,以及對(duì)實(shí)驗(yàn)范式的簡(jiǎn)化,對(duì)提高EEG-fNIRS多模態(tài)BCI的應(yīng)用有一定的意義。
[Abstract]:Brain-Computer Interface (BCI) is a new technology for extracting information directly from the central nervous system and directly manipulating peripheral equipment by human thinking. It is the highest form of human-computer interaction in the future.Brain-computer interface is not only widely used in the field of medical rehabilitation, but also has high significance and value in military, recreational, mental health, artificial intelligence and other fields.This paper first introduces the related research background of brain-computer interface, aiming at the problems that the traditional brain-computer interface based on single mode electroencephalography (EEG) is vulnerable to environmental noise interference and low classification accuracy, based on the research of EEG brain-computer interface.The functional near infrared imaging function Near Infrared spectroscope of NIR is introduced to design and simplify the experimental paradigm of EEG-fNIRS multimodal brain-computer interface based on grip movement, and the most important feature extraction and classification are studied.Firstly, three subjects were collected synchronously by using the EEGFNIRS acquisition and analysis system in the laboratory, and the original signals were filtered and de-noised, and the baseline correction was performed.According to the event correlation desynchronization, event correlation synchronization and time-frequency characteristics of EEG signal induced by fist grip, the coefficients of AR model and wavelet coefficients of EEG signal are extracted.At the same time, according to the characteristics of hemodynamic response caused by the grip movement, the mean and slope characteristics of hemoglobin concentration in different periods were extracted.After normalization of feature vectors, linear discriminant analysis (LDAs) and support Vector machines (SVM) are used to classify different types of features and perform 5 fold cross validation for 8 times.The results show that the feature classification effect of wavelet coefficients of EEG is better than that of slope feature classification of fNIRS which combines band energy with AR model parameters.Among them, the time period with the highest accuracy of slope feature classification is 3 / 5 s after performing the action task.Secondly, according to the classification results of single mode features, a fusion feature based on EEG wavelet coefficients and fNIRS slope is proposed, and principal component analysis (PCA) is used to analyze the combined features.Then, LDA-SVM is used to classify, and 8 times 5 fold cross validation is carried out to compare the classification accuracy between multimodal signal and single mode signal.The results show that the average recognition rate of grip movement task after feature fusion is 3% higher than that of EEG feature and fNIRS feature.It is shown that fNIRS can significantly enhance the performance of BCI based on EEG, and the performance of traditional BCI system can be improved by using multimodal brain signals, and the simplification of experimental paradigm is of certain significance to improve the application of EEG-fNIRS multimodal BCI.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R318;TN911.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 王力;張雄;;小波濾波與AR模型在腦電信號(hào)處理的應(yīng)用[J];電子器件;2012年04期

2 劉沖;趙海濱;李春勝;王宏;;基于頻帶能量歸一化和SVM-RFE的ECoG分類[J];儀器儀表學(xué)報(bào);2011年03期

3 王耀南,李樹濤;多傳感器信息融合及其應(yīng)用綜述[J];控制與決策;2001年05期

相關(guān)博士學(xué)位論文 前1條

1 余天佑;多模態(tài)與多自由度腦機(jī)接口研究[D];華南理工大學(xué);2013年

相關(guān)碩士學(xué)位論文 前1條

1 李紅英;支持向量分類機(jī)的核函數(shù)研究[D];重慶大學(xué);2009年

，

本文編號(hào)：1736681