北京生物醫(yī)學(xué)工程

基于PCA及SVM的運(yùn)動(dòng)想象腦電信號(hào)識(shí)別研究

Classification of Motor Imagery EEG Based on PCA and SVM

作者：關(guān)俊強(qiáng) 楊幫華馬世偉袁玲

單位：上海大學(xué)機(jī)電工程與自動(dòng)化學(xué)院自動(dòng)化系，上海市電站自動(dòng)化技術(shù)重點(diǎn)實(shí)驗(yàn)室（上海200072）

關(guān)鍵詞：腦機(jī)接口；主成分分析；支持向量機(jī);希爾伯特-黃變換

分類號(hào)：

出版年·卷·期（頁(yè)碼）：2010·29·3（261-265）

摘要：

為了解決腦機(jī)接口（BCI）中不同意識(shí)任務(wù)下運(yùn)動(dòng)想象腦電信號(hào)的分類問題，提出了一種基于PCA及SVM的識(shí)別方法。針對(duì)Hilbert-Huang變換和AR模型提取的腦電信號(hào)特征，首先采用主成分分析PCA對(duì)高維特征向量進(jìn)行降維處理，然后用支持向量機(jī)進(jìn)行分類。最后將本方法分類結(jié)果和Fisher線性分類、概率神經(jīng)網(wǎng)絡(luò)分類結(jié)果進(jìn)行比較。實(shí)驗(yàn)結(jié)果表明，該方法分類正確率較高，復(fù)雜度低，具有一定的有效性，可用于腦機(jī)接口中。

In order to solve the problem of the electroencephalogram (EEG) classification under different imagery task in brain computer interfaces (BCI),a new recognition method based on principle component analysis (PCA) and support vector machine (SVM) is presented in this paper.Four features of motor imagery EEG signals extracted by combining the HHT with AR model,first,PCA was utilized to reduce dimensions of the high dimensional feature vectors.Then,SVM was used to classify different EEG patterns of motor imagery.Finally,this method was compared with Fisher LDA (linear discriminant analysis) and probabilistic neural network (PNN).Experimental results showed that the proposed method could classify different EEG patterns of motor imagery effectively due to its higher classification accuracy and lower complexity so as to be utilized in online BCI system.

參考文獻(xiàn)：

［1］Mason SG,Birch GE.A general framework for brain-computer interface design ［J］.IEEE Transactions,Neural System and Rehabilitation Engineering,2003,11(1):70-85.
［2］徐寶國(guó)，宋愛國(guó).單次運(yùn)動(dòng)想象腦電的特征提取和分類［J］.東南大學(xué)學(xué)報(bào)，2007,37（4）:629-631.
［3］Penga ZK,Tse PW,Chu FL.A comparison study of improved Hilbert-Huang transform and wavelet transform:Application to fault diagnosis for rolling bearing［J］.Mechanical Systems and Signal Processing,2005:974-988.
［4］Huang ML,Wu PD,Liu Ying,et al.Application and Contrast in Brain-Computer Interface between Hilbert-Huang Transform and Wavelet Transform［C］.The 9th International Conference for Young Computer Scientists,2008:1706-1710.
［5］Bashashati A,Fatourechi M,Ward RK,et al.TOPICAL REVIEW:A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals［J］.Journal of Neural Engineering,2007,4:R32- R57.
［6］Guyon I,Elisseeff A.An introduction to variable and feature selection［J］.Journal of Machine Learning Research (S0885-6125),2003,3(1):1157-1182.
［7］Lotte F,Congedo M,Lecuyer A,et al.TOPICAL REVIEW:A review of classification algorithms for EEG-based brain-computer interfaces［J］.Journal of Neural Engineering,2007,4:R1-R13.
［8］孫見青，汪榮貴，胡韋偉，等.一種新的基于NGA/PCA 和SVM 的特征提取方法［J］.系統(tǒng)仿真學(xué)報(bào)，2007，19（20）：4823-4825.
［9］Benjamin Blankertz,Guido Dornhege,Matthias Krauledat,et al.The non-invasive Berlin Brain-Computer Interface:Fast acquisition of effective performance in untrained subjects.NeuroImage［J］,2007,37:539-550.
［10］Huang NE,Zheng S,Long SR.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis［C］//Proceedings of the Royal Society of London，1998，454（A）：903-995.
［11］Pfurtscheller G,Neuper C,Flotzinger D,et al.EEG based discrimination between imagination of right and left hand movement［J］.Electroenceph Clin Neurophysiol,1997,103:642-651.
［12］Duda RO,Hart PE,Stock DG.Pattern Classification［M］.北京：機(jī)械工業(yè)出版社，2003:94-96.
［13］張學(xué)工.關(guān)于統(tǒng)計(jì)學(xué)習(xí)理論與支持向量機(jī)［J］.自動(dòng)化學(xué)報(bào),2000,26(1):33-34.
［14］謝松云,張海軍.基于SVM的腦功能分類與識(shí)別方法研究［J］.中國(guó)醫(yī)學(xué)影像技術(shù),2007,23(1):125-128.
［15］李鋼，王蔚，張勝.支持向量機(jī)在腦電信號(hào)分類中的應(yīng)用［J］.計(jì)算機(jī)應(yīng)用,2006,26(6):1432-1433.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频