【摘要】：針對(duì)直接利用卷積神經(jīng)網(wǎng)絡(luò)(convolutional neural network,CNN)算法對(duì)多類運(yùn)動(dòng)想象腦電信號(hào)分類識(shí)別時(shí),因樣本量比較少,難以充分訓(xùn)練權(quán)值,導(dǎo)致分類效果較差的問題,結(jié)合一對(duì)多CSP算法與CNN算法對(duì)多類運(yùn)動(dòng)想象腦電信號(hào)進(jìn)行特征提取與分類。首先,利用CSP算法對(duì)多類運(yùn)動(dòng)想象腦電信號(hào)進(jìn)行特征提取,形成一維特征數(shù)據(jù),作為CNN的輸入樣本;其次,對(duì)傳統(tǒng)二維輸入樣本的CNN結(jié)構(gòu)進(jìn)行改造,使其適應(yīng)一維數(shù)據(jù)的輸入樣本,對(duì)輸入樣本進(jìn)行再次特征提取并分類;最后,使用BCI2005desc—Ⅲa的K3b數(shù)據(jù)進(jìn)行算法驗(yàn)證;并對(duì)不同參數(shù)值的確定進(jìn)行了討論。算法驗(yàn)證結(jié)果表明,單獨(dú)利用一對(duì)多CSP算法得到的分類正確率73%,單獨(dú)使用CNN算法得到正確率為75%,新算法取得了91.46%的正確率,相比兩種原始方法有較大提升。
[Abstract]:In order to solve the problem of classifying and recognizing multiple motion imaginary EEG signals directly using convolutional neural network (convolutional neural network) algorithm, it is difficult to fully train the weights due to the small sample size, which leads to the poor classification effect. Combined with one-to-many CSP algorithm and CNN algorithm, the feature extraction and classification of multi-class motion imaginary EEG signals are carried out. Firstly, we use CSP algorithm to extract the features of multi-class motion imaginary EEG signals, and form one-dimensional feature data as the input samples of CNN. Secondly, we modify the CNN structure of traditional two-dimensional input samples. It adapts to the input samples of one-dimensional data, extracts and classifies the input samples again. Finally, the algorithm is verified by using the K3b data of BCI2005desc- 鈪，

本文編號(hào)：2122010