燕山大学学报2025，Vol.49Issue(1)：66-73,8.DOI:10.3969/j.issn.1007-791X.2025.01.007
基于2D-3D卷积神经网络的情绪识别模型
Emotion recognition model based on 2D-3D convolutional neural network
摘要
Abstract
Emotion recognition based on EEG signals is an important part of human-computer interaction.This paper combines two-dimensional convolutional neural network,three-dimensional convolutional neural network and depth-wise separable convolution,and proposes a 2D-3D convolutional neural network(2-3DCNN)model to extract features from three aspects:time,space and frequency.SE ResNet network,deep residual shrinkage network,and Xception network are introduced into the network to explore spatial,temporal,and frequency information in EEG signals that can more significantly reflect emotional changes.Experiments are conducted on the DEAP public sentiment dataset using the 2-3DCNN model,and the results show that the recognition accuracy of this method in arousal and valence classification tasks reached 97.59% and 97.21%,2.36% and 1.34% higher than the current state-of-the-art models.关键词
情绪识别/脑电信号/卷积神经网络/深度残差收缩网络/深度可分离卷积Key words
emotion recognition/EEG/convolutional neural network/deep residual shrinkage network/depthwise seperable convolution分类
信息技术与安全科学引用本文复制引用
杨朋辉,杨长青,刘静,崔冬..基于2D-3D卷积神经网络的情绪识别模型[J].燕山大学学报,2025,49(1):66-73,8.基金项目
国家自然科学基金资助项目(62173291,62072394) （62173291,62072394）
河北省自然科学基金资助项目(F2021203019) （F2021203019）
河北省重点实验室项目(202250701010046) （202250701010046）
