CASIA OpenIR  > 学术期刊  > 自动化学报
基于RCNN-LSTM的脑电情感识别研究
柳长源; 李文强; 毕晓君
Source Publication自动化学报
ISSN0254-4156
2022
Volume48Issue:3Pages:917-925
Abstract情感作为人脑的高级功能,对人们的个性特征和心理健康有很大的影响,利用网上公开的脑电情感数据库(DEAP (Database for emotion analysis using physiological signals)数据库),根据心理效价和激励唤醒度等级进行情感划分,对压力和平静等5种情感进行研究分析.针对脑电信号时空特征结合的特点,把深度学习中的卷积神经网络(Convolutional neural network, CNN)和长短期记忆网络(Long short term memory, LSTM)两者作为基本前提,并在此基础之上设计了一个RCNN-LSTM的脑电情感信号分类模型.利用循环卷积神经网络(Recurrent convolutional neural network, RCNN)自动提取脑电信号中的抽象特征,省去了人工选择与降维的过程,然后结合LSTM网络对脑电情感信号进行分类识别.实验结果表明,利用该方法对5种情感类别的平均分类识别率达到了96.63%,证明了该方法的有效性.
Keyword脑电信号 情感识别 循环卷积神经网络 长短期记忆神经网络
DOI10.16383/j.aas.c190357
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/56401
Collection学术期刊_自动化学报
Recommended Citation
GB/T 7714
柳长源,李文强,毕晓君. 基于RCNN-LSTM的脑电情感识别研究[J]. 自动化学报,2022,48(3):917-925.
APA 柳长源,李文强,&毕晓君.(2022).基于RCNN-LSTM的脑电情感识别研究.自动化学报,48(3),917-925.
MLA 柳长源,et al."基于RCNN-LSTM的脑电情感识别研究".自动化学报 48.3(2022):917-925.
Files in This Item: Download All
File Name/Size DocType Version Access License
AAS-CN-2019-0357.pdf(1199KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[柳长源]'s Articles
[李文强]'s Articles
[毕晓君]'s Articles
Baidu academic
Similar articles in Baidu academic
[柳长源]'s Articles
[李文强]'s Articles
[毕晓君]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[柳长源]'s Articles
[李文强]'s Articles
[毕晓君]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: AAS-CN-2019-0357.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.