计算机工程与应用2019，Vol.55Issue(18)：103-110,8.DOI:10.3778/j.issn.1002-8331.1901-0400
基于深度卷积神经网络的脑电信号情感识别
EEG-Based Emotion Recognition Using Deep Convolutional Neural Network
摘要
Abstract
In order to improve the accuracy of emotional recognition by end-to-end automatic learning of emotional fea-tures in spatial and temporal dimensions of electroencephalogram(EEG), an EEG emotional feature learning and classifi-cation method using deep Convolution Neural Network(CNN)models is proposed based on temporal features, frequen-tial features and their combination features of EEG signals in DEAP dataset. The shallow machine learning models includ-ing Bagging Tree(BT), Support Vector Machine(SVM), Linear Discriminant Analysis(LDA)and Bayesian Linear Dis-criminant Analysis(BLDA)models and deep CNN models are used to make emotional binary classification experiments on DEAP datasets in valence and arousal dimensions. The experimental results show that the deep CNN models achieve the best recognition performance on temporal and frequency combined features in both valence and arousal dimensions, which is 3.58% higher than the performance of the best traditional BT classifier in valence dimension and 3.29% higher than that of BT classifier in arousal dimension.关键词
脑电信号/卷积神经网络/深度学习/情感识别/组合特征Key words
electroencephalogram(EEG)/Convolution Neural Network(CNN)/deep learning/emotion recognition/combined features分类
信息技术与安全科学引用本文复制引用
陈景霞,王丽艳,贾小云,张鹏伟..基于深度卷积神经网络的脑电信号情感识别[J].计算机工程与应用,2019,55(18):103-110,8.基金项目
国家自然科学基金(No.61806118,No.61806144). （No.61806118,No.61806144）
