摘要
脑电情感识别是一个复杂程度高、信息密度大、海量数据的多通道时序信号分类问题。为在保持现有分类精度的情况下减少计算参数量,实现脑电情感识别的精度与性能最优,提出了一种基于双流结构缩放和多重注意力机制的轻量级网络(LDM-EEG)。该网络以基于脑电信号的微分熵特征构造的时域-空域图谱和频域-空域图谱作为输入,采用对称的双流结构对上述两种特征分别处理,通过节约参数的新型残差模块和网络缩放机制来实现轻量化,并利用新型的通道-时/频-空多重注意力机制和后注意力机制提升模型特征聚合能力。实验结果表明,在参数量明显减小的情况下,模型在SEED数据集上实现了95.18%的准确率,达到了领域的最优结果。进一步地,在略低于现有模型准确率的基础上,其将参数量缩减了98%。
EEG emotion recognition is a multi-channel time-series signal classification problem with high complexity,high information density and massive data.In order to achieve optimal accuracy and performance of EEG emotion recognition with fewer computational parameters while maintaining the existing classification accuracy,this paper proposes a lightweight network(LDM-EEG)based on dual-stream structural scaling and multiple attention mechanisms.The network takes the time-space and frequency-space maps constructed based on the differential entropy features of EEG signals as the input,processes the two features separately using a symmetric dual-stream structure,achieves lightweighting through a novel parameter-saving residual module and a network scaling mechanism,and enhances the model feature aggregation capability using a novel channel-time/frequency-space multiple attention mechanism and a post-attention mechanism.Experimental results show that the accuracy of the model is 95.18%with significantly reduced number of parameters,which achieves the optimal result in the domain.Further,about 98%reduction in the number of parameters has been achieved with slightly lower accuracy than the existing models.
作者
雷颖
刘峰
LEI Ying;LIU Feng(School of Computer Science and Technology,East China Normal University,Shanghai 200062,China;Institute of Artificial Intelligence and Change Management,Shanghai University of International Business and Economics,Shanghai 201620,China;Institute of AI for Education,East China Normal University,Shanghai 200062,China;Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention,School of Psychology and Cognitive Science,East China Normal University,Shanghai 200062,China)
出处
《计算机科学》
CSCD
北大核心
2023年第S01期229-237,共9页
Computer Science
基金
上海市科技计划项目
中央高校基本科研业务费专项资金(20DZ2260300)。
关键词
脑电情感识别
时频双流
多重注意力
轻量级
结构缩放
可计算情感
EEG emotion recognition
Time-frequency dual streaming
Multiple attention
Lightweight
Structural scaling
Computational affection
