基于運(yùn)動想象腦電信號非線性特性分析的腦—機(jī)接口研究
發(fā)布時間：2018-09-03 13:35
【摘要】：腦-機(jī)接口（Brain-Computer Interface，BCI）是一種幫助人們利用他們的大腦控制和使用外部設(shè)備的一種通信系統(tǒng)，在此過程中不需要外周神經(jīng)和肌肉的參與。BCI是一門涉及神經(jīng)科學(xué)、信號處理、計算機(jī)科學(xué)等多個領(lǐng)域的交叉學(xué)科。近20年來，已成為國際智能科學(xué)領(lǐng)域的一個研究熱點。BCI研究的核心就是如何將用戶的腦電信號轉(zhuǎn)換成外部設(shè)備的控制信號。所以BCI研究最重要的工作就是要尋找合適的信號處理和轉(zhuǎn)換方法，使得人腦的意識特征信號能夠快速、準(zhǔn)確地被計算機(jī)識別。一般來說，BCI系統(tǒng)可以看成是一個模式識別系統(tǒng)。一個BCI系統(tǒng)是否成功主要取決于兩個方面的因素：①獲取的特征能夠區(qū)分不同的意識任務(wù)；②分類算法準(zhǔn)確有效。所以如何建立準(zhǔn)確可靠的特征提取模型和設(shè)計高效的分類算法是目前研究的主要難點。 目前，在基于運(yùn)動想象的腦-機(jī)接口研究中，對EEG進(jìn)行特征提取和分類往往都建立在EEG信號是線性的這一假設(shè)的基礎(chǔ)之上。然而，大量研究表明，EEG信號是非線性的，采用線性方法來對EEG信號進(jìn)行處理，會導(dǎo)致其非線性特征丟失，從而減弱這些特征在區(qū)分不同意識任務(wù)時的性能。所以，本論文在針對EEG信號的非線性特性研究的基礎(chǔ)上，根據(jù)目前特征提取和分類算法中存在的問題，提出了新的基于EEG非線性特性的特征提取算法，并通過仿真實驗證明了其可行性。論文的主要研究內(nèi)容包括以下幾個方面： ①對EEG動力學(xué)模型的非線性特性進(jìn)行分析。通過相空間重構(gòu)技術(shù)，對求解得到的EEG信號進(jìn)行了重構(gòu)。得出了he的吸引子隨著參數(shù)p ee和pe i變化的規(guī)律。從而證實了大腦中存在混沌這一觀點。對實際測得的EEG信號進(jìn)行了非線性特性的研究。計算了腦-機(jī)接口競賽提供的兩個基于運(yùn)動想象的數(shù)據(jù)集中EEG樣本的最大Lyapunov指數(shù)，計算結(jié)果表明，幾乎所有的標(biāo)準(zhǔn)數(shù)據(jù)集當(dāng)中的EEG樣本的最大Lyapunov指數(shù)均大于零。進(jìn)一步證實了大腦中存在混沌的論點，因而可以使用非線性分析方法來對EEG信號進(jìn)行分析。 ②分別計算了兩個標(biāo)準(zhǔn)數(shù)據(jù)集樣本的幾種常見的混沌特征量，即最大Lyapunov指數(shù)、關(guān)聯(lián)維數(shù)和近似熵，并分別使用最大Lyapunov指數(shù)、關(guān)聯(lián)維數(shù)和近似熵作為運(yùn)動想象的特征進(jìn)行分類。結(jié)果表明，直接使用最大Lyapunov指數(shù)和關(guān)聯(lián)維數(shù)作為運(yùn)動想象任務(wù)的特征，不能很好的區(qū)分各種運(yùn)動想象任務(wù)。而近似熵是衡量時間序列中產(chǎn)生新模式概率大小的一種度量，它更適合表示不同的意識任務(wù)。在對近似熵特征進(jìn)行分析的基礎(chǔ)上，提出了一種基于時間窗的近似熵特征提取和分類算法。該算法模擬在線腦-機(jī)接口的情況，在每個時間窗內(nèi)對意識任務(wù)進(jìn)行分類，，實驗結(jié)果表明，分類器能較好的區(qū)分左右手運(yùn)動想象任務(wù)。 ③提出了一套基于相空間重構(gòu)的特征提取方法。從理論上證明了相空間重構(gòu)函數(shù)具有濾波功能，并能夠?qū)EG信號進(jìn)行相位和幅度調(diào)節(jié)，從而使相空間的特征更能區(qū)別不同的腦電任務(wù)。基于相空間的特征提取方法保留了傳統(tǒng)的線性特征提取方法的優(yōu)勢，又使獲取的特征具有相空間的信息，因而提高了分類器的分類性能。本文使用了2003和2005兩屆腦機(jī)接口競賽提供的數(shù)據(jù)進(jìn)行了仿真，并采用了和競賽相同的評價標(biāo)準(zhǔn)：互信息和最大互信息峭度。實驗結(jié)果表明，該方法是一種極具競爭力的特征提取方法。采用相空間特征的Fisher分類器在Graz2003數(shù)據(jù)集取得了最大互信息值0.67，這是目前報道的最好結(jié)果。在對Graz2005數(shù)據(jù)集進(jìn)行仿真的結(jié)果表明，相空間特征同樣具有很好的效能，在平均最大互信息峭度和分類正確率的評價標(biāo)準(zhǔn)下均取得了很好的成績。 ④針對共空間模式（Common spatial pattern，CSP）在解決多分類問題中的組合方式問題，提出了一種基于CSP和Fisher線性分類器的二叉樹組合方式（BCSP）。在該方式下，F(xiàn)isher線性分類器和CSP以二叉樹的方式進(jìn)行排列。任務(wù)的分類采用二叉查找的方式進(jìn)行。在BCSP中，使用的CSP濾波器和Fisher分類器的數(shù)目比傳統(tǒng)的“一對它”方式更少。而且在N分類過程中，對CSP投影矩陣和分類器的計算也能保持在最多l(xiāng)og2N級別，大大提高了分類的效率，提高了分類的準(zhǔn)確率。 ⑤在線BCI游戲平臺的開發(fā)與實現(xiàn)。在對研究結(jié)果進(jìn)行總結(jié)的基礎(chǔ)上，設(shè)計了一套基于Neuroscan的在線BCI游戲系統(tǒng)。該系統(tǒng)可以通過腦電來進(jìn)行Hangman游戲操作。該系統(tǒng)集成了訓(xùn)練模塊，測試模塊和游戲模塊。能夠完成從訓(xùn)練到實際操作的一整套功能。系統(tǒng)使用了C3、C4和O1通道來記錄EEG信號，其中C3和C4通道的EEG信號用來提取左右手運(yùn)動想象任務(wù)的腦電特征，O1通道的波作為確認(rèn)信號。該系統(tǒng)采用了基于相空間重構(gòu)的特征提取算法和Fisher線性分類器。對6個用戶進(jìn)行實驗的結(jié)果表明，相空間特征均提高了運(yùn)動想象任務(wù)的識別率，從而證明了相空間特征的有效性。 文章的最后對所有的研究工作進(jìn)行了總結(jié)，指出了論文主要研究工作的內(nèi)容和取得的成果，并對下一步的工作進(jìn)行了展望。
[Abstract]:Brain-Computer Interface (BCI) is a communication system that helps people use their brains to control and use external devices without the involvement of peripheral nerves and muscles. BCI is an interdisciplinary subject involving neuroscience, signal processing, computer science and many other fields. In the past 20 years, it has become a success. The core of BCI research is how to convert the EEG signals of users into the control signals of external devices. So the most important task of BCI research is to find suitable signal processing and conversion methods, so that the consciousness characteristic signals of human brain can be recognized quickly and accurately by computer. Generally speaking, a BCI system can be regarded as a pattern recognition system. The success of a BCI system depends on two factors: 1) the acquired features can distinguish different conscious tasks; 2) the classification algorithm is accurate and effective. The main difficulties of previous research.
At present, feature extraction and classification of EEG are often based on the assumption that EEG signals are linear in the study of brain-computer interface based on motor imagery. In this paper, a new feature extraction algorithm based on EEG nonlinear characteristics is proposed on the basis of the nonlinear characteristics of EEG signals and the problems existing in the current feature extraction and classification algorithms. The following aspects should be studied:
(1) The nonlinear characteristics of the EEG dynamic model are analyzed. The EEG signals are reconstructed by the phase space reconstruction technique. The law of the attractor of he changing with the parameters p EE and PE I is obtained. The chaos in the brain is confirmed. The nonlinear characteristics of the EEG signals are studied. The maximum Lyapunov exponents of two EEG samples from the brain-computer interface contest based on motion imagery are calculated. The results show that the maximum Lyapunov exponents of EEG samples from almost all the standard data sets are greater than zero. This further confirms the argument that chaos exists in the brain, so the nonlinear analysis method can be used. The EEG signal is analyzed by the method.
(2) Several common chaotic features of two standard datasets, namely, the maximum Lyapunov exponent, correlation dimension and approximate entropy, are calculated, and the maximum Lyapunov exponent, correlation dimension and approximate entropy are used to classify the motion imagery. Approximate entropy is a measure of the probability of generating new patterns in time series, and it is more suitable for representing different conscious tasks. Based on the analysis of the characteristics of approximate entropy, an approximate entropy feature extraction and classification based on time window is proposed. The algorithm simulates the on-line brain-computer interface and classifies conscious tasks in each time window. The experimental results show that the classifier can distinguish left and right hand motion imagery tasks better.
(3) A method of feature extraction based on phase space reconstruction is proposed. It is proved theoretically that the phase space reconstruction function has the function of filtering and can adjust the phase and amplitude of EEG signals, so that the phase space features can distinguish different EEG tasks better. In this paper, we use the data provided by the 2003 and 2005 BCI contests to simulate and adopt the same evaluation criteria as the contest: mutual information and maximum mutual information kurtosis. Fisher classifier based on phase space features achieves a maximum mutual information value of 0.67 in Graz 2003 data set, which is the best result reported so far. Simulation results on Graz 2005 data set show that phase space features also have good performance in average maximum mutual information kurtosis and score. Good results have been achieved under the accuracy rate of class accuracy.
(4) To solve the problem of combination of common spatial pattern (CSP) in multi-class classification, a binary tree combination method (BCSP) based on CSP and Fisher linear classifier is proposed. In this way, Fisher linear classifier and CSP are arranged in binary tree. The classification of tasks adopts binary search method. In BCSP, the number of CSP filters and Fisher classifiers used is less than the traditional "one-to-one" method, and the calculation of CSP projection matrix and classifier can also be maintained at the maximum log2N level in the N-classification process, which greatly improves the classification efficiency and classification accuracy.
_The development and implementation of online BCI game platform.On the basis of summarizing the research results,an online BCI game system based on Neuroscan is designed.The system can perform Hangman game operation by EEG.The system integrates training module,testing module and game module.It can complete one from training to practical operation. The system uses C3, C4 and O1 channels to record EEG signals. The EEG signals of C3 and C4 channels are used to extract EEG features of left and right hand motion imagery tasks, and the waves of O1 channels are used as confirmation signals. The results show that both the phase space features improve the recognition rate of the motion imagery task, thus proving the validity of the phase space features.
At the end of the paper, all the research work is summarized, and the main research contents and achievements are pointed out, and the future work is prospected.
【學(xué)位授予單位】：重慶大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：TN911.7
本文編號：2220121
[Abstract]:Brain-Computer Interface (BCI) is a communication system that helps people use their brains to control and use external devices without the involvement of peripheral nerves and muscles. BCI is an interdisciplinary subject involving neuroscience, signal processing, computer science and many other fields. In the past 20 years, it has become a success. The core of BCI research is how to convert the EEG signals of users into the control signals of external devices. So the most important task of BCI research is to find suitable signal processing and conversion methods, so that the consciousness characteristic signals of human brain can be recognized quickly and accurately by computer. Generally speaking, a BCI system can be regarded as a pattern recognition system. The success of a BCI system depends on two factors: 1) the acquired features can distinguish different conscious tasks; 2) the classification algorithm is accurate and effective. The main difficulties of previous research.
At present, feature extraction and classification of EEG are often based on the assumption that EEG signals are linear in the study of brain-computer interface based on motor imagery. In this paper, a new feature extraction algorithm based on EEG nonlinear characteristics is proposed on the basis of the nonlinear characteristics of EEG signals and the problems existing in the current feature extraction and classification algorithms. The following aspects should be studied:
(1) The nonlinear characteristics of the EEG dynamic model are analyzed. The EEG signals are reconstructed by the phase space reconstruction technique. The law of the attractor of he changing with the parameters p EE and PE I is obtained. The chaos in the brain is confirmed. The nonlinear characteristics of the EEG signals are studied. The maximum Lyapunov exponents of two EEG samples from the brain-computer interface contest based on motion imagery are calculated. The results show that the maximum Lyapunov exponents of EEG samples from almost all the standard data sets are greater than zero. This further confirms the argument that chaos exists in the brain, so the nonlinear analysis method can be used. The EEG signal is analyzed by the method.
(2) Several common chaotic features of two standard datasets, namely, the maximum Lyapunov exponent, correlation dimension and approximate entropy, are calculated, and the maximum Lyapunov exponent, correlation dimension and approximate entropy are used to classify the motion imagery. Approximate entropy is a measure of the probability of generating new patterns in time series, and it is more suitable for representing different conscious tasks. Based on the analysis of the characteristics of approximate entropy, an approximate entropy feature extraction and classification based on time window is proposed. The algorithm simulates the on-line brain-computer interface and classifies conscious tasks in each time window. The experimental results show that the classifier can distinguish left and right hand motion imagery tasks better.
(3) A method of feature extraction based on phase space reconstruction is proposed. It is proved theoretically that the phase space reconstruction function has the function of filtering and can adjust the phase and amplitude of EEG signals, so that the phase space features can distinguish different EEG tasks better. In this paper, we use the data provided by the 2003 and 2005 BCI contests to simulate and adopt the same evaluation criteria as the contest: mutual information and maximum mutual information kurtosis. Fisher classifier based on phase space features achieves a maximum mutual information value of 0.67 in Graz 2003 data set, which is the best result reported so far. Simulation results on Graz 2005 data set show that phase space features also have good performance in average maximum mutual information kurtosis and score. Good results have been achieved under the accuracy rate of class accuracy.
(4) To solve the problem of combination of common spatial pattern (CSP) in multi-class classification, a binary tree combination method (BCSP) based on CSP and Fisher linear classifier is proposed. In this way, Fisher linear classifier and CSP are arranged in binary tree. The classification of tasks adopts binary search method. In BCSP, the number of CSP filters and Fisher classifiers used is less than the traditional "one-to-one" method, and the calculation of CSP projection matrix and classifier can also be maintained at the maximum log2N level in the N-classification process, which greatly improves the classification efficiency and classification accuracy.
_The development and implementation of online BCI game platform.On the basis of summarizing the research results,an online BCI game system based on Neuroscan is designed.The system can perform Hangman game operation by EEG.The system integrates training module,testing module and game module.It can complete one from training to practical operation. The system uses C3, C4 and O1 channels to record EEG signals. The EEG signals of C3 and C4 channels are used to extract EEG features of left and right hand motion imagery tasks, and the waves of O1 channels are used as confirmation signals. The results show that both the phase space features improve the recognition rate of the motion imagery task, thus proving the validity of the phase space features.
At the end of the paper, all the research work is summarized, and the main research contents and achievements are pointed out, and the future work is prospected.
【學(xué)位授予單位】：重慶大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：TN911.7
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 劉沖;趙海濱;李春勝;王宏;;基于CSP與SVM算法的運(yùn)動想象腦電信號分類[J];東北大學(xué)學(xué)報(自然科學(xué)版);2010年08期
2 楊立才,李佰敏,李光林,賈磊;腦-機(jī)接口技術(shù)綜述[J];電子學(xué)報;2005年07期
3 吳邊;蘇煜;張劍慧;李昕;張吉財;陳衛(wèi)東;鄭筱祥;;基于P300電位的新型BCI中文輸入虛擬鍵盤系統(tǒng)[J];電子學(xué)報;2009年08期
4 徐寶國;宋愛國;費(fèi)樹岷;;在線腦機(jī)接口中腦電信號的特征提取與分類方法[J];電子學(xué)報;2011年05期
5 張愛華;楊彬;黃玲;靳伍銀;;基于傅里葉變換的腦機(jī)接口系統(tǒng)實現(xiàn)方法[J];蘭州理工大學(xué)學(xué)報;2008年04期
6 李娟;楊琳;劉金龍;楊德龍;張晨;;基于自適應(yīng)混沌粒子群優(yōu)化算法的多目標(biāo)無功優(yōu)化[J];電力系統(tǒng)保護(hù)與控制;2011年09期
7 王瑞琪;李珂;張承慧;;基于混沌多目標(biāo)遺傳算法的微網(wǎng)系統(tǒng)容量優(yōu)化[J];電力系統(tǒng)保護(hù)與控制;2011年22期
8 高諾;魯守銀;張運(yùn)楚;姚慶梅;;腦機(jī)接口技術(shù)的研究現(xiàn)狀及發(fā)展趨勢[J];機(jī)器人技術(shù)與應(yīng)用;2008年04期
9 鄧志東;李修全;鄭寬浩;姚文韜;;一種基于SSVEP的仿人機(jī)器人異步腦機(jī)接口控制系統(tǒng)[J];機(jī)器人;2011年02期
10 孫進(jìn);張征;周宏甫;;基于腦機(jī)接口技術(shù)的康復(fù)機(jī)器人綜述[J];機(jī)電工程技術(shù);2010年04期
本文編號：2220121
本文鏈接：http://sikaile.net/kejilunwen/wltx/2220121.html
最近更新
教材專著
