【摘要】：腦機接口系統(tǒng)的核心問題之一是信號分類。本文針對腦電信號的異構(gòu)融合特征的分類問題提出了一種新方法:封裝式彈性網(wǎng)特征選擇和分類。首先,對預(yù)處理后的腦電(EEG)信號聯(lián)合應(yīng)用時域統(tǒng)計、功率譜、共空間模式和自回歸模型方法提取高維異構(gòu)融合特征。其次,采用封裝方式進行特征選擇:對訓(xùn)練數(shù)據(jù)采用彈性網(wǎng)罰邏輯回歸擬合模型,通過坐標下降法估計模型參數(shù),運用10倍交叉驗證選擇出最優(yōu)特征子集。最后采用已訓(xùn)練的最優(yōu)模型對測試樣本進行分類。實驗中采用國際BCI競賽Ⅳ的EEG數(shù)據(jù),結(jié)果表明,該方法適用于高維融合特征的最優(yōu)特征子集選擇問題,對于EEG信號的識別不僅效果好、速度快,而且能夠選出與分類更相關(guān)的子集,獲得相對簡單的模型,平均測試正確率達到了81.78%。
[Abstract]:One of the core problems of BCI system is signal classification. In this paper, a new method for the classification of heterogeneous fusion features of EEG signals is proposed: feature selection and classification of encapsulated elastic networks. Firstly, time domain statistics, power spectrum, common space model and autoregressive model are used to extract the features of high dimensional heterogeneous fusion for pretreated (EEG) signals. Secondly, the feature selection is carried out by encapsulation: the training data is fitted with elastic net penalty logic regression model, the parameters of the model are estimated by coordinate descent method, and the optimal feature subset is selected by 10 times cross validation. Finally, the trained optimal model is used to classify the test samples. In the experiment, the EEG data of international BCI competition 鈪，

本文編號：2363453