多類運動想象腦電模式識別及其在電動輪椅控制上的應(yīng)用
發(fā)布時間：2018-09-13 16:47
【摘要】：腦-機接口是一種不依賴外周神經(jīng)和肌肉組織的參與，在大腦和計算機或其他電子設(shè)備之間直接建立交流和控制通路的技術(shù)，從而將大腦信號解讀成相應(yīng)的命令來實現(xiàn)與外部世界的交流與控制。該技術(shù)不僅具有重要的理論研究價值，還具有實際的應(yīng)用前景，已成為生物醫(yī)學(xué)工程領(lǐng)域的研究熱點之一，而基于運動想象腦電信號的研究是腦-機接口的一個重要分支。 本文的研究建立在國家自然科學(xué)基金資助項目(61201302)的要求上，從課題的研究背景及意義出發(fā)，介紹了腦電信號的特點，分析了運動想象腦電信號的預(yù)處理、特征提取、模式分類的方法。本文進一步介紹了本文腦電信號的采集裝置及方案，并通過其對腦電信號進行處理，然后將特定的運動想象任務(wù)轉(zhuǎn)化為與其相對應(yīng)的控制命令，最后輸入到電動輪椅上，控制其完成特定的運動。本文完成了以下研究工作，并取得了一些研究成果： (1)腦電信號預(yù)處理階段：本文采用優(yōu)化的廣義權(quán)重估計算法對腦電信號進行預(yù)處理，它可以在一定程度上消除與運動無關(guān)的信號，同時也可以增強運動想象的信噪比，從而為腦電信號的特征提取和模式分類提供好的基礎(chǔ)條件。 (2)腦電信號特征提取階段：從常規(guī)運動想象激活的局部腦區(qū)分析的角度出發(fā)，考慮到運動想象腦電信號中存在很多與運動想象無關(guān)的頻率信號，而共空間模式特征提取方法缺少對頻率信息的處理，本文提出了一種雙樹復(fù)小波與共空間模式相結(jié)合的特征提取方法。該方法首先選取特定通道的腦電信號，然后利用雙樹復(fù)小波多尺度分解，獲取適當(dāng)?shù)念l段，接著將各頻段的信號聯(lián)合起來輸入到空間濾波器中，從而得到所需的特征向量。此外，從復(fù)雜腦功能網(wǎng)絡(luò)的角度出發(fā)，又提出了一種基于腦功能網(wǎng)絡(luò)鄰接矩陣分解的新方法。該方法首先采用多通道運動想象腦電信號構(gòu)建腦功能網(wǎng)絡(luò)，然后對相應(yīng)的鄰接矩陣進行奇異值分解，依據(jù)矩陣奇異值特征向量定義了腦電的特征參數(shù)，最后將其組合為特征向量。 (3)腦電信號模式分類階段：為了提高BCI系統(tǒng)中分類精度和分類速度，提出了一種基于深度自編碼降維的主軸動態(tài)核聚類分類方法。首先，為了降低特征向量之間的相關(guān)性和計算的復(fù)雜度，引入深度自編碼方法將特征向量進行降維處理，然后利用主軸動態(tài)核聚類分類進行分類識別。另外，由于支持向量機能夠解決小樣本估計、非線性、非平穩(wěn)信號的分類問題，所以本文設(shè)計了基于多核學(xué)習(xí)支持向量機的多類分類器，可使分布復(fù)雜的數(shù)據(jù)信息在高維的特征空間中得到更充分的體現(xiàn)，在減少支持向量數(shù)目的同時提高分類精度。 (4)電動輪椅控制實驗：首先設(shè)計四類運動想象的實驗范式，并采集相應(yīng)的腦電信號，然后將利用優(yōu)化的廣義權(quán)重估計算法實現(xiàn)盲源分離，接著采用雙樹復(fù)小波-共空間模式相結(jié)合的方法提取出腦電特征向量，進而使用多核學(xué)習(xí)支持向量機多類分類器對所得特征向量進行分類識別，，最后將識別結(jié)果轉(zhuǎn)化為控制命令控制電動輪椅運動，三名受試者的平均正確率分別為66.78%，76.58%和72.53%。
[Abstract]:Brain-computer interface (BCI) is a technology that directly establishes communication and control channels between brain and computer or other electronic devices without the involvement of peripheral nerves and muscle tissues, thus interpreting brain signals into corresponding commands to achieve communication and control with the outside world. This technology is not only of great theoretical value, but also of great theoretical value. It has practical application prospects and has become one of the hotspots in the field of biomedical engineering. The study of EEG based on motor imagery is an important branch of brain-computer interface.
This paper is based on the requirement of the project supported by the National Natural Science Foundation of China (61201302). Starting from the research background and significance of the subject, the characteristics of EEG signals are introduced, and the methods of pretreatment, feature extraction and pattern classification of motor imagery EEG signals are analyzed. This paper completes the following research work and achieves some research results:1.
(1) EEG signal preprocessing stage: This paper uses the optimized generalized weight estimation algorithm to preprocess the EEG signal, which can eliminate the motion-independent signal to a certain extent, but also can enhance the signal-to-noise ratio of motor imagination, thus providing a good basis for feature extraction and pattern classification of EEG signal.
(2) Feature extraction of EEG signals: From the point of view of the analysis of local brain regions activated by conventional motor imagery, considering that there are many frequencies unrelated to motor imagery in motor imagery EEG signals, and the common spatial pattern feature extraction method lacks the processing of frequency information, this paper proposes a dual-tree complex wavelet and common space. First, the EEG signals of a specific channel are selected, and then the appropriate frequency bands are obtained by the dual-tree complex wavelet multi-scale decomposition. Then, the signals of each frequency band are jointly input into the spatial filter to obtain the desired eigenvectors. A new method based on the adjacency matrix decomposition of the brain functional network is proposed. Firstly, the brain functional network is constructed by using multi-channel motor imagery EEG signals, and then the corresponding adjacency matrix is singular value decomposition (SVD). According to the singular value eigenvector of the matrix, the characteristic parameters of the EEG are defined and combined into the eigenvector.
(3) EEG pattern classification stage: In order to improve the classification accuracy and speed in BCI system, a dynamic clustering classification method based on deep self-coding dimensionality reduction is proposed. In addition, support vector machine can solve the problem of small sample estimation, non-linear, non-stationary signal classification, so this paper designs a multi-class classifier based on multi-kernel learning support vector machine, which can make the distributed complex data information get more in the high-dimensional feature space. It fully reflects that the classification accuracy can be improved while reducing the number of support vectors.
(4) Electric wheelchair control experiment: Firstly, four kinds of experimental paradigms of motion imagery are designed, and corresponding EEG signals are collected. Then the optimized generalized weight estimation algorithm is used to realize blind source separation. Then, the EEG feature vectors are extracted by the method of dual-tree complex wavelet-common-space pattern, and then the multi-kernel learning support vector is used. Finally, the recognition results are converted into control commands to control the motion of the electric wheelchair. The average accuracy of the three subjects is 66.78%, 76.58% and 72.53% respectively.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TN911.7
本文編號：2241759
[Abstract]:Brain-computer interface (BCI) is a technology that directly establishes communication and control channels between brain and computer or other electronic devices without the involvement of peripheral nerves and muscle tissues, thus interpreting brain signals into corresponding commands to achieve communication and control with the outside world. This technology is not only of great theoretical value, but also of great theoretical value. It has practical application prospects and has become one of the hotspots in the field of biomedical engineering. The study of EEG based on motor imagery is an important branch of brain-computer interface.
This paper is based on the requirement of the project supported by the National Natural Science Foundation of China (61201302). Starting from the research background and significance of the subject, the characteristics of EEG signals are introduced, and the methods of pretreatment, feature extraction and pattern classification of motor imagery EEG signals are analyzed. This paper completes the following research work and achieves some research results:1.
(1) EEG signal preprocessing stage: This paper uses the optimized generalized weight estimation algorithm to preprocess the EEG signal, which can eliminate the motion-independent signal to a certain extent, but also can enhance the signal-to-noise ratio of motor imagination, thus providing a good basis for feature extraction and pattern classification of EEG signal.
(2) Feature extraction of EEG signals: From the point of view of the analysis of local brain regions activated by conventional motor imagery, considering that there are many frequencies unrelated to motor imagery in motor imagery EEG signals, and the common spatial pattern feature extraction method lacks the processing of frequency information, this paper proposes a dual-tree complex wavelet and common space. First, the EEG signals of a specific channel are selected, and then the appropriate frequency bands are obtained by the dual-tree complex wavelet multi-scale decomposition. Then, the signals of each frequency band are jointly input into the spatial filter to obtain the desired eigenvectors. A new method based on the adjacency matrix decomposition of the brain functional network is proposed. Firstly, the brain functional network is constructed by using multi-channel motor imagery EEG signals, and then the corresponding adjacency matrix is singular value decomposition (SVD). According to the singular value eigenvector of the matrix, the characteristic parameters of the EEG are defined and combined into the eigenvector.
(3) EEG pattern classification stage: In order to improve the classification accuracy and speed in BCI system, a dynamic clustering classification method based on deep self-coding dimensionality reduction is proposed. In addition, support vector machine can solve the problem of small sample estimation, non-linear, non-stationary signal classification, so this paper designs a multi-class classifier based on multi-kernel learning support vector machine, which can make the distributed complex data information get more in the high-dimensional feature space. It fully reflects that the classification accuracy can be improved while reducing the number of support vectors.
(4) Electric wheelchair control experiment: Firstly, four kinds of experimental paradigms of motion imagery are designed, and corresponding EEG signals are collected. Then the optimized generalized weight estimation algorithm is used to realize blind source separation. Then, the EEG feature vectors are extracted by the method of dual-tree complex wavelet-common-space pattern, and then the multi-kernel learning support vector is used. Finally, the recognition results are converted into control commands to control the motion of the electric wheelchair. The average accuracy of the three subjects is 66.78%, 76.58% and 72.53% respectively.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TN911.7
【參考文獻】
相關(guān)期刊論文 前10條
1 黃思娟;吳效明;;基于能量特征的腦電信號特征提取與分類[J];傳感技術(shù)學(xué)報;2010年06期
2 王攀;沈繼忠;施錦河;;想象左右手運動的腦電特征提取[J];傳感技術(shù)學(xué)報;2010年09期
3 羅志增;曹銘;;基于多尺度Lempel-Ziv復(fù)雜度的運動想象腦電信號特征分析[J];傳感技術(shù)學(xué)報;2011年07期
4 周顏軍,王雙成,王輝;基于貝葉斯網(wǎng)絡(luò)的分類器研究[J];東北師大學(xué)報(自然科學(xué)版);2003年02期
5 徐寶國;宋愛國;費樹岷;;在線腦機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
6 劉高平;趙杜娟;黃華;;基于自編碼神經(jīng)網(wǎng)絡(luò)重構(gòu)的車牌數(shù)字識別[J];光電子.激光;2011年01期
7 龔衛(wèi)國;劉曉營;李偉紅;李建福;;雙密度雙樹復(fù)小波變換的局域自適應(yīng)圖像去噪[J];光學(xué)精密工程;2009年05期
8 宋恒,張楊;基于模式識別技術(shù)的股票市場技術(shù)分析研究[J];計算機仿真;2004年07期
9 汪洪橋;孫富春;蔡艷寧;陳寧;丁林閣;;多核學(xué)習(xí)方法[J];自動化學(xué)報;2010年08期
10 楊新亮;羅志增;;OGWE算法及其在表面肌電信號中的應(yīng)用[J];華中科技大學(xué)學(xué)報(自然科學(xué)版);2011年S2期
相關(guān)博士學(xué)位論文 前3條
1 周鵬;基于運動想象的腦機接口的研究[D];天津大學(xué);2007年
2 趙啟斌;EEG時空特征分析及其在BCI中的應(yīng)用[D];上海交通大學(xué);2008年
3 劉美春;基于運動想象的腦—機接口系統(tǒng)模式識別算法研究[D];華南理工大學(xué);2009年
本文編號：2241759
本文鏈接：http://www.sikaile.net/kejilunwen/wltx/2241759.html
最近更新
教材專著
