基于注意力机制和深度学习的群体语言想象脑电信号分类  

Classification of group speech imagined EEG signals based on attention mechanism and deep learning

作　　者：周逸凡 张灵维 周正东[1] 蔡智 袁梦瑶 袁晓曦 杨泽毅 ZHOU Yifan;ZHANG Lingwei;ZHOU Zhengdong;CAI Zhi;YUAN Mengyao;YUAN Xiaoxi;YANG Zeyi(State Key Laboratory of Mechanics and Control for Aerospace Structures,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China;VeriSilicon Holdings(Nanjing)Co.Ltd,Nanjing 210000,China)

机构地区：[1]南京航空航天大学航空航天结构力学及控制国家重点实验室,江苏南京210016 [2]芯原微电子(南京)有限公司,江苏南京210000

出　　处：《浙江大学学报（工学版）》2024年第12期2540-2546,共7页Journal of Zhejiang University：Engineering Science

基　　金：中国航空研究院首批揭榜挂帅项目(F2021109);上海航天科技创新基金资助项目(SAST2019-121);南京航空航天大学科研与实践创新计划资助项目(xcxjh20210104);江苏高校优势学科建设工程资助项目(PAPD)。

摘　　要：为了提高群体语言想象脑电信号的分类准确率,提出基于卷积块注意力模块(CBAM)和Inception-V4卷积神经网络的分类方法,其中CBAM被用于关注重要的局部区域,从卷积神经网络(CNN)输出的特征图中提取更加独特的特征,从而提升群体语言想象脑电信号的分类性能.该方法首先利用短时傅里叶变换将群体语言想象脑电信号转换为时频图,然后使用这些图片对融合了CBAM机制的Inception-V4网络进行训练.开源数据集上的实验结果表明,所提出的方法使得6类短词的分类准确率达到了52.2%,与基于Inception-V4的分类方法相比,分类准确率提高了4.1个百分点,与基于VGG-16的分类方法相比,分类准确率提高了5.9个百分点.使用迁移学习也能够大幅缩短训练所需的时间.A classification method based on convolutional block attention module(CBAM)and Inception-V4 convolutional neural network was proposed to improve the classification accuracy of group EEG signals of imagined speech.CBAM was used to emphasize significant localized areas and extract distinctive features from the output feature map of convolutional neural network(CNN),so as to improve the classification performance of group EEG signals of imagined speech.The group EEG signals of imagined speech were converted into time-frequency images by short-time Fourier transform,then the images were used to train the Inception-V4 network incorporating with CBAM.Experiments on an open-accessed dataset showed that the proposed method achieved an accuracy of 52.2%in classifying six types of short words,which was 4.1 percentage points higher than that with Inception-V4 and was 5.9 percentage points higher than that with VGG-16.Furthermore,the training time can be reduced greatly with transfer learning.

关 键 词：脑-机接口 脑电图 语言想象 深度学习 注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]