电子学报2025，Vol.53Issue(12)：4337-4348,12.DOI:10.12263/DZXB.20250435
一种融合连续小波卷积与图嵌入的注意力网络
An Attention Network with Continuous Wavelet Convolution and Graph Embedding
摘要
Abstract
Decoding motor imagery electroencephalogram(MI-EEG)signals based on deep learning models is one of the hot research topics in the field of brain-computer interface(BCI)technology.Aiming at the time-frequency characteris⁃tics and individual differences of MI-EEG,numerous studies have conducted time-frequency analysis on MI-EEG and wide⁃ly applied its time-frequency representations to MI-EEG decoding.However,most existing methods ignore the spatial distri⁃bution characteristics of multi-electrode MI-EEG and fail to fully explore and utilize the topological relationships between different electrodes,thereby affecting the integrity of feature information and limiting the further improvement of decoding performance.To adaptively learn the topological information between multi-electrode MI-EEG and effectively enhance its time-frequency-spatial feature information,this paper proposes an attention network with continuous wavelet convolution and graph embedding(CWC-GEAN).The network consists of five modules:a multi-branch continuous wavelet convolu⁃tion module(MCWCM),a multi-branch dynamic graph embedding module(MGEM),a multi-branch feature channel atten⁃tion module(MFCAM),a multi-branch feature channel-time attention module(MFCTAM),and a feature fusion and classifi⁃cation block(FFCB).First,the original multi-electrode MI-EEG signals are input into the MCWCM,where continuous wavelet convolution is performed based on four sub-bands(1 Hz to 8 Hz,9 Hz to 16 Hz,17 Hz to 24 Hz,25 Hz to 32 Hz)in four branches respectively,and the optimal multi-scale frequency-spatial-temporal feature representations are obtained through dynamic learning of scale factors.Then,a prior adjacency matrix containing topological information between elec⁃trodes is constructed based on mutual information,and the prior adjacency matrix is adaptively learned and adjusted from different sub-bands via the MGEM,which is embedded into the frequency-spatial-temporal feature representations of corre⁃sponding branches to obtain graph structure features containing topological information between electrodes.Furthermore,the MFCAM and the MFCTAM further extract deep features from the graph structure features of each branch,and succes⁃sively complete the automatic acquisition of feature channel attention vectors and feature channel-time attention matrices as well as feature weighting to obtain multi-branch discriminative features.Finally,the FFCB fuses the multi-branch discrimi⁃native features to obtain the final classification results.In this paper,the performance of CWC-GEAN is evaluated based on the public BCI Competition IV 2a dataset and High-Gamma Dataset,with average classification accuracies of 85.45%and 95.09%,and average Kappa values of 0.806 and 0.934,respectively.The results show that CWC-GEAN has the ability to adaptively learn and capture the time-frequency information and electrode topological information of MI-EEG,as well as enhance time-frequency-spatial features,and exhibits good model robustness and consistency of classification results,with certain performance advantages over popular methods.关键词
脑电信号/运动想象/连续小波卷积/拓扑信息/注意力/时频空特征Key words
electroencephalogram/motor imagery/continuous wavelet convolution/topological information/atten⁃tion/frequency-spatial-temporal feature分类
信息技术与安全科学引用本文复制引用
张璐,李明爱..一种融合连续小波卷积与图嵌入的注意力网络[J].电子学报,2025,53(12):4337-4348,12.基金项目
国家自然科学基金(No.62173010) National Natural Science Foundation of China(No.62173010) （No.62173010）
