本文選題：模擬閱讀　切入點：腦-機接口　出處：《計算機工程與應(yīng)用》2017年11期 　論文類型：期刊論文

【摘要】：針對腦-機接口的特征提取問題,提出了一種基于非監(jiān)督學(xué)習(xí)的稀疏降噪自編碼器,對刺激誘發(fā)的腦電信號進行自主學(xué)習(xí),構(gòu)建原始數(shù)據(jù)的深層特征表達。該編碼器引用稀疏自編碼神經(jīng)網(wǎng)絡(luò),通過加入噪聲,增強其學(xué)習(xí)的泛化能力,增加了神經(jīng)網(wǎng)絡(luò)的魯棒性。首先對多導(dǎo)聯(lián)信號進行重新拼接,輸入稀疏降噪自編碼器,得到原始數(shù)據(jù)的稀疏特征表達;然后,采用支持向量機將學(xué)習(xí)到的特征進行分類;最后,同直接使用最優(yōu)單通道相對比。實驗結(jié)果為:稀疏降噪自編碼器的分類準(zhǔn)確率要優(yōu)于單通道,表明該方法能夠更好地學(xué)習(xí)到特征,并提高了"模擬閱讀"腦-機接口的識別正確率,為腦-機接口系統(tǒng)的特征提取和分類提供了新思路。
[Abstract]:To solve the problem of feature extraction of brain-computer interface, a sparse de-noising self-encoder based on unsupervised learning is proposed, which can be used for autonomous learning of stimulus-induced EEG signals. The encoder uses sparse self-coding neural network to enhance its learning generalization ability and enhance the robustness of neural network by adding noise. Firstly, the multi-lead signal is reassembled. Input sparse denoising self-encoder to obtain sparse feature representation of the original data; then, support vector machine will be used to classify the features learned; finally, The experimental results show that the classification accuracy of sparse noise reduction self-encoder is better than that of single channel. The recognition accuracy of "simulated reading" brain-computer interface is improved, which provides a new idea for feature extraction and classification of brain-computer interface system.
【作者單位】： 中南民族大學(xué)醫(yī)學(xué)信息分析及腫瘤診療湖北省重點實驗室;中南民族大學(xué)認知科學(xué)國家民委重點實驗室;
【基金】：國家自然科學(xué)基金(No.91120017,No.81271659) 中央高校基本科研業(yè)務(wù)費資助項目(No.CZY13031)
【分類號】：TN762;TN911.7;TP18
，

本文編號：1589349