基于通道选择和多维特征融合的脑电信号分类

EEG classification based on channel selection and multi-dimensional feature fusion

针对多通道脑电信号(EEG)相互干扰、存在个体差异性导致分类结果不同和单域特征识别率低等问题,提出一种通道选择和特征融合的方法。首先,对获取到的EEG进行预处理,使用梯度提升决策树(GBDT)选出重要通道;其次,采用广义预测控制(GPC)模型构建重要通道的预测信号,辨析多维相关信号之间的细微差别,再使用SE-TCNTA(Squeeze and Excitation block-Temporal Convolutional Network-Temporal Attention)模型提取不同帧之间的时序特征;然后,使用皮尔逊相关系数计算通道间的关系,提取EEG的频域特征和预测信号的控制量作为输入,建立空间图结构,并采用图卷积网络(GCN)提取频域、空域的特征;最后,将上述二者特征输入全连接层进行特征融合,实现EEG的分类。在公共数据集BCICIV_2a上的实验结果表明,在进行通道选择的情况下,与首个用于ERP检测的EEGInception模型以及同样采用双分支提取特征的DSCNN(Shallow Double-branch Convolutional Neural Network)模型方法相比,所提方法的分类准确率分别提升了1.47%和1.69%,Kappa值分别提升了1.25%和2.53%。所提方法能够提高EGG的分类精度,同时减少冗余数据对特征提取的影响,因此更适用于脑机接口(BCI)系统。

To solve the problems of the mutual interference of multi-channel ElectroEncephaloGraphy(EEG),the different classification results caused by individual differences,and the low recognition rate of single domain features,a method of channel selection and feature fusion was proposed.Firstly,the acquired EEG was preprocessed,and the important channels were selected by using Gradient Boosting Decision Tree(GBDT).Secondly,the Generalized Predictive Control(GPC)model was used to construct the prediction signals of important channels and distinguish the subtle differences among multi-dimensional correlation signals,then the SE-TCNTA(Squeeze and Excitation block-Temporal Convolutional Network-Temporal Attention)model was used to extract temporal features between different frames.Thirdly,the Pearson correlation coefficient was used to calculate the relationship between channels,the frequency domain features of EEG and the control values of prediction signals were extracted as inputs,the spatial graph structure was established,and the Graph Convolutional Network(GCN)was used to extract the features of frequency domain and spatial domain.Finally,the above two features were input to the fully connected layer for feature fusion in order to realize the classification of EEG.Experimental results on public dataset BCICIV_2a show that in the case of channel selection,compared with the first EEGinception model for ERP detection and DSCNN(Shallow Double-branch Convolutional Neural Network)model that also uses double branch feature extraction,the proposed method has the classification accuracy increased by 1.47%and 1.69% respectively,and has the Kappa value increased by 1.25% and 2.53% respectively.The proposed method can improve the classification accuracy of EEG and reduce the influence of redundant data on feature extraction,so it is more suitable for Brain-Computer Interface(BCI)systems.