摘要
近年来基于脑电信号的情绪识别研究取得了显著的进展,然而标签的标注需要大量的人力,实际应用中难以快速获取大量带标签的数据。高效利用有限的标签进行情绪识别研究逐渐成为了一个新的应用瓶颈。为了解决这个问题,本研究提出了一种基于双流孪生网络的模型架构,由两个相互作用、相互学习的卷积神经网络分支组成。首先,将模型进行预训练,将输入信号的扩增视图分别输入到孪生网络的两个分支,在分别经过分支中的卷积模块和全连接模块提取特征后进行对比学习,使模型在过程中学习到脑电信号的通用表征;然后,保留训练分支的编码器部分,对模型进行微调,得到分类结果。使用公开数据集SEED和SEED-IV中的数据样本进行模型分类效果的验证评估,在全标签数据下,分别实现了93.92%和89.71%的分类准确率。在50%的标签使用率下,实现了三分类92.68%的平均准确率,比使用全部标签只减少了1.24%准确率。所提出的模型能够有效提取脑电数据的通用表征,并在使用少量标签的情况下达到较高的识别准确率。
In recent years,the research of emotion recognition based on EEG signals has gradually made remarkable progress.However,the labeling of labels requires a lot of manpower,and it is difficult to quickly obtain a large number of labeled data in practical applications.Therefore,how to utilize limited labels efficiently in the emotion recognition research become one bottleneck problem to overcome.In this work,a model architecture based on self⁃supervised double⁃flow twin network was proposed,which consisted of two interacting and learning branches of convolutional neural networks.First,the model was pre⁃trained.The amplified data of the input signal after two random signal transformations were input into the training branch and the target branch of the twin network.After extracting features from the convolutional module and the fully connected module in the branch,the model learned the general representation of the EEG signal in the process.Finally,the encoder part of the training branch was retained,and then the fully connected layer was used to fine⁃tune the model with labeled data,and the classification results are obtained.Data samples from public data sets SEED and SEED⁃IV were used to verify and evaluate the model classification effect.Under the fully labeled data,the classification accuracy of 93.92% and 89.71%were achieved,respectively.Under 50% label usage,the average accuracy of the three categories was 92.68%,which was only 1.24%less than that using all labels.The results showed that the model effectively extracted the general representation of EEG data,and achieved high recognition accuracy with relatively less labels.
作者
马玉良
谢昀臻
孟明
高云园
佘青山
Ma Yuliang;Xie Yunzhen;Meng Ming;Gao Yunyuan;She Qingshan(School of Automation,Hangzhou Dianzi University,Hangzhou 310018,China;International Joint Research Laboratory for Autonomous Robotic Systems,Hangzhou 310018,China)
出处
《中国生物医学工程学报》
北大核心
2025年第4期385-392,共8页
Chinese Journal of Biomedical Engineering
基金
国家自然科学基金(62271181,62371171,62371172)。
关键词
情绪识别
自监督学习
脑机接口
双流网络
emotion recognition
self⁃supervised learning
brain⁃computer interface
two-flow network
