混合腦機(jī)接口在康復(fù)機(jī)器人上的應(yīng)用
發(fā)布時(shí)間：2018-11-05 10:46
【摘要】：腦機(jī)接口(Brain-computer interface,BCI)通過(guò)借助計(jì)算機(jī)或其他外部電子設(shè)備,旨在建立一種不依賴人體神經(jīng)和肌肉組織等正常傳輸通道,而直接進(jìn)行人腦與外界之間信息交流的新途徑。在助殘康復(fù)、智能生活、娛樂等領(lǐng)域有著廣泛的應(yīng)用前景。本文從實(shí)現(xiàn)對(duì)康復(fù)訓(xùn)練機(jī)器人的控制來(lái)進(jìn)行康復(fù)訓(xùn)練出發(fā),以運(yùn)動(dòng)想象和P300腦電信號(hào)為切入點(diǎn),并結(jié)合他們各自的優(yōu)勢(shì)構(gòu)建混合BCI系統(tǒng)。本文主要做了以下工作:(1)經(jīng)典的共同空間模式(Common spatial pattern,CSP)用于兩類運(yùn)動(dòng)想象的特征提取,通過(guò)對(duì)CSP進(jìn)行擴(kuò)展將其用于多類問(wèn)題上。本文首先對(duì)多類CSP方法一對(duì)多CSP(One versus rest CSP,OVR-CSP)進(jìn)行了研究。由于OVR-CSP濾波器的性能依賴于其選擇的頻帶,當(dāng)在不合適的頻率段進(jìn)行濾波的特征上執(zhí)行分類時(shí),其分類精度一般很差。在此基礎(chǔ)上進(jìn)一步的研究了對(duì)頻帶進(jìn)行固定劃分的Filter bank共同空間模式方法,通過(guò)頻帶的劃分雖然能夠進(jìn)一步提高分類正確率,但卻還是遠(yuǎn)低于兩類問(wèn)題。(2)針對(duì)常用多類CSP算法在BCI信號(hào)處理方面存在識(shí)別率較低的問(wèn)題,通過(guò)引入堆疊降噪自動(dòng)編碼器(Stacked denoising autoencoders,SDA),提出了一種多類變頻帶運(yùn)動(dòng)想象腦電信號(hào)的兩級(jí)特征提取方法。首先將原始信號(hào)通過(guò)變化頻率段帶通濾波器得到不同頻段的信號(hào),其次利用OVR-CSP將不同頻段信號(hào)變換到使信號(hào)方差區(qū)別最大的低維空間,然后通過(guò)SDA網(wǎng)絡(luò)提取其中可以更好表達(dá)類別屬性的高層抽象特征,接著將獲得的特征使用Relief F方法進(jìn)行特征選擇,選擇出最大權(quán)值所對(duì)應(yīng)頻帶的特征,最后使用Softmax分類器進(jìn)行分類。在對(duì)BCI競(jìng)賽IV中Datasets 2a的4類運(yùn)動(dòng)想象任務(wù)進(jìn)行的分類實(shí)驗(yàn)中,平均Kappa系數(shù)達(dá)到0.70,表明了所提出的特征提取方法的有效性和魯棒性。(3)通過(guò)對(duì)現(xiàn)有P300范式的研究,提出了一種基于變概率的刺激范式(Variable probability paradigm,VPP)。在該范式中,字符呈現(xiàn)不均勻分布,其密度從中間向兩邊依次減小。字符識(shí)別分為兩步進(jìn)行,先進(jìn)行隨機(jī)行閃爍確定字符所在行,然后所選行中的字符再進(jìn)行隨機(jī)閃爍以確定目標(biāo)字符。使用該范式和基于區(qū)域的范式進(jìn)行數(shù)據(jù)采集及處理,結(jié)果表明VPP的信息傳輸率比基于區(qū)域的范式提高約10%,證明了該范式的可行性。(4)為了實(shí)現(xiàn)對(duì)康復(fù)機(jī)器人的多維控制,本文設(shè)計(jì)了一種基于運(yùn)動(dòng)想象(Motor imagery,MI)和P300信號(hào)的混合BCI控制策略。使用P300信號(hào)作為兩種信號(hào)間切換的“開關(guān)”,選擇以游戲圖標(biāo)組成的VPP作為游戲菜單的控制面板,MI作為機(jī)器人的控制信號(hào)來(lái)實(shí)現(xiàn)患者康復(fù)訓(xùn)練。通過(guò)離線數(shù)據(jù)采集實(shí)驗(yàn)進(jìn)行模擬控制,結(jié)果表明了該系統(tǒng)的可行性。
[Abstract]:The brain-computer interface (Brain-computer interface,BCI) aims to establish a new way to directly communicate information between human brain and the outside world by means of computer or other external electronic devices, which is independent of normal transmission channels such as human nerve and muscle tissue. In the disability rehabilitation, intelligent life, entertainment and other fields have a wide range of applications. In order to control the rehabilitation training robot, this paper starts from the exercise imagination and P300 EEG signal as the starting point, and combines their respective advantages to construct a hybrid BCI system. The main work of this paper is as follows: (1) the classical common space model (Common spatial pattern,CSP) is used to extract the feature of two kinds of motion imagination, and the CSP is extended to multi-class problems. In this paper, one-to-many CSP (One versus rest CSP,OVR-CSP of multi-class CSP methods are studied. Because the performance of OVR-CSP filter depends on its selected frequency band, the classification accuracy is generally very poor when the classification is performed on the characteristics of the filter in an inappropriate frequency band. On this basis, we further study the Filter bank common space pattern method for the fixed division of the frequency band. Though the classification of the frequency band can further improve the classification accuracy, But it is still far lower than two kinds of problems. (2) aiming at the problem of low recognition rate in BCI signal processing of common multi-class CSP algorithm, the stack noise reduction automatic encoder (Stacked denoising autoencoders,SDA is introduced. A two-stage feature extraction method for multi-frequency band motion imagination EEG signals is proposed. First, the original signal is obtained by the bandpass filter in the variable frequency band, and then the signal in different frequency bands is transformed into a low-dimensional space in which the variance of the signal is the most different by using OVR-CSP. Then the high-level abstract features which can better express the category attributes are extracted by SDA network, and then the features obtained are selected by Relief F method, and the features corresponding to the frequency band corresponding to the maximum weights are selected. Finally, Softmax classifier is used to classify. In the classification experiment of four kinds of motion imagination tasks of Datasets 2a in BCI competition IV, the average Kappa coefficient is 0.70, which indicates the effectiveness and robustness of the proposed feature extraction method. (3) by studying the existing P300 normal form, In this paper, we propose a variable probabilistic stimulus normal form (Variable probability paradigm,VPP). In this paradigm, characters are distributed unevenly, and their density decreases from middle to both sides. Character recognition is divided into two steps: the random line flashes to determine the line of the character, and then the character in the selected line is flashed randomly to determine the target character. The results show that the information transfer rate of VPP is about 10% higher than that of region based paradigm. The feasibility of this paradigm is proved. (4) in order to realize multidimensional control of rehabilitation robot, a hybrid BCI control strategy based on motion imagination (Motor imagery,MI) and P300 signal is designed in this paper. The P300 signal is used as the switch between the two signals. The VPP composed of game icons is chosen as the control panel of the game menu and MI is used as the control signal of the robot to realize the rehabilitation training of patients. The simulation control is carried out by off-line data acquisition experiment, and the results show that the system is feasible.
【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)】：TP242
[Abstract]:The brain-computer interface (Brain-computer interface,BCI) aims to establish a new way to directly communicate information between human brain and the outside world by means of computer or other external electronic devices, which is independent of normal transmission channels such as human nerve and muscle tissue. In the disability rehabilitation, intelligent life, entertainment and other fields have a wide range of applications. In order to control the rehabilitation training robot, this paper starts from the exercise imagination and P300 EEG signal as the starting point, and combines their respective advantages to construct a hybrid BCI system. The main work of this paper is as follows: (1) the classical common space model (Common spatial pattern,CSP) is used to extract the feature of two kinds of motion imagination, and the CSP is extended to multi-class problems. In this paper, one-to-many CSP (One versus rest CSP,OVR-CSP of multi-class CSP methods are studied. Because the performance of OVR-CSP filter depends on its selected frequency band, the classification accuracy is generally very poor when the classification is performed on the characteristics of the filter in an inappropriate frequency band. On this basis, we further study the Filter bank common space pattern method for the fixed division of the frequency band. Though the classification of the frequency band can further improve the classification accuracy, But it is still far lower than two kinds of problems. (2) aiming at the problem of low recognition rate in BCI signal processing of common multi-class CSP algorithm, the stack noise reduction automatic encoder (Stacked denoising autoencoders,SDA is introduced. A two-stage feature extraction method for multi-frequency band motion imagination EEG signals is proposed. First, the original signal is obtained by the bandpass filter in the variable frequency band, and then the signal in different frequency bands is transformed into a low-dimensional space in which the variance of the signal is the most different by using OVR-CSP. Then the high-level abstract features which can better express the category attributes are extracted by SDA network, and then the features obtained are selected by Relief F method, and the features corresponding to the frequency band corresponding to the maximum weights are selected. Finally, Softmax classifier is used to classify. In the classification experiment of four kinds of motion imagination tasks of Datasets 2a in BCI competition IV, the average Kappa coefficient is 0.70, which indicates the effectiveness and robustness of the proposed feature extraction method. (3) by studying the existing P300 normal form, In this paper, we propose a variable probabilistic stimulus normal form (Variable probability paradigm,VPP). In this paradigm, characters are distributed unevenly, and their density decreases from middle to both sides. Character recognition is divided into two steps: the random line flashes to determine the line of the character, and then the character in the selected line is flashed randomly to determine the target character. The results show that the information transfer rate of VPP is about 10% higher than that of region based paradigm. The feasibility of this paradigm is proved. (4) in order to realize multidimensional control of rehabilitation robot, a hybrid BCI control strategy based on motion imagination (Motor imagery,MI) and P300 signal is designed in this paper. The P300 signal is used as the switch between the two signals. The VPP composed of game icons is chosen as the control panel of the game menu and MI is used as the control signal of the robot to realize the rehabilitation training of patients. The simulation control is carried out by off-line data acquisition experiment, and the results show that the system is feasible.
【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)】：TP242
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 汪彩霞;魏雪云;王彪;;基于堆棧降噪自動(dòng)編碼模型的動(dòng)態(tài)紋理分類方法[J];現(xiàn)代電子技術(shù);2015年06期
2 馬玉良;許明珍;佘青山;高云園;孫曜;楊家強(qiáng);;基于自適應(yīng)閾值的腦電信號(hào)去噪方法[J];傳感技術(shù)學(xué)報(bào);2014年10期
3 徐守晶;韓立新;曾曉勤;;基于改進(jìn)型SDA的自然圖像分類與檢索[J];模式識(shí)別與人工智能;2014年08期
4 劉斌;魏夢(mèng)然;羅聰;;基于腦電BCI的研究綜述[J];電腦知識(shí)與技術(shù);2014年07期
5 劉沖;顏世玉;趙海濱;王宏;;多類運(yùn)動(dòng)想象任務(wù)腦電信號(hào)的KNN分類研究[J];儀器儀表學(xué)報(bào);2012年08期
6 劉廣權(quán);黃淦;朱向陽(yáng);;共空域模式方法在多類別分類中的應(yīng)用[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2009年06期
7 李明愛;劉凈瑜;郝冬梅;;基于改進(jìn)CSP算法的運(yùn)動(dòng)想象腦電信號(hào)識(shí)別方法[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2009年02期
8 馬，
本文編號(hào)：2311821
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2311821.html
最近更新
教材專著
