中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
3DCANN: A Spatio-Temporal Convolution Attention Neural Network for EEG Emotion Recognition

文献类型：期刊论文

作者Liu, Shuaiqi5,6; Wang, Xu4; Zhao, Ling4; Li, Bing5; Hu, Weiming5; Yu, Jie2,3; Zhang, Yu-Dong1
刊名IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
出版日期2022-11-01
卷号26期号:11页码:5321-5331
关键词Electroencephalography Feature extraction Emotion recognition Convolution Brain modeling Deep learning Neural networks 3D convolution attention neural network dual attention learning EEG emotion recognition spatio-temporal feature
ISSN号2168-2194
DOI10.1109/JBHI.2021.3083525
通讯作者Zhao, Ling(lingzhao_hbu@163.com) ; Zhang, Yu-Dong(yudongzhang@ieee.org)
英文摘要Since electroencephalogram (EEG) signals can truly reflect human emotional state, emotion recognition based on EEG has turned into a critical branch in the field of artificial intelligence. Aiming at the disparity of EEG signals in various emotional states, we propose a new deep learning model named three-dimension convolution attention neural network (3DCANN) for EEG emotion recognition in this paper. The 3DCANN model is composed of spatio-temporal feature extraction module and EEG channel attention weight learning module, which can extract the dynamic relation well among multi-channel EEG signals and the internal spatial relation of multi-channel EEG signals during continuous period time. In this model, the spatio-temporal features are fused with the weights of dual attention learning, and the fused features are input into the softmax classifier for emotion classification. In addition, we utilize SJTU Emotion EEG Dataset (SEED) to appraise the feasibility and effectiveness of the proposed algorithm. Finally, experimental results display that the 3DCANN method has superior performance over the state-of-the-art models in EEG emotion recognition.
WOS关键词FEATURE-EXTRACTION ; CLASSIFICATION
资助项目National Natural Science Foundation of China[61572063] ; Natural Science Foundation of Hebei Province[F2020201025] ; Natural Science Foundation of Hebei Province[F2019201151] ; Science Research Project of Hebei Province[BJ2020030] ; Open Foundation of Guangdong Key Laboratory of Digital Signal and Image Processing[2020GDDSIPL-04]
WOS研究方向Computer Science ; Mathematical & Computational Biology ; Medical Informatics
语种英语
WOS记录号WOS:000882005700010
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Natural Science Foundation of Hebei Province ; Science Research Project of Hebei Province ; Open Foundation of Guangdong Key Laboratory of Digital Signal and Image Processing
源URL[http://ir.ia.ac.cn/handle/173211/51266]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Zhao, Ling; Zhang, Yu-Dong
作者单位1.Univ Leicester, Sch Informat, Leicester LE1 7RH, Leics, England
2.Chinese Peoples Liberat Army Gen Hosp, Beijing 100853, Peoples R China
3.PLA Med Coll, Dept Intervent Ultrasound, Beijing 100853, Peoples R China
4.Hebei Univ, Coll Elect & Informat Engn, Key Lab Digital Med Engn Hebei Prov, Baoding 071002, Peoples R China
5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
6.Hebei Univ, Coll Elect & Informat Engn, Machine Vis Engn Res Ctr Hebei Prov, Baoding 071002, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Shuaiqi,Wang, Xu,Zhao, Ling,et al. 3DCANN: A Spatio-Temporal Convolution Attention Neural Network for EEG Emotion Recognition[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2022,26(11):5321-5331.
APA Liu, Shuaiqi.,Wang, Xu.,Zhao, Ling.,Li, Bing.,Hu, Weiming.,...&Zhang, Yu-Dong.(2022).3DCANN: A Spatio-Temporal Convolution Attention Neural Network for EEG Emotion Recognition.IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,26(11),5321-5331.
MLA Liu, Shuaiqi,et al."3DCANN: A Spatio-Temporal Convolution Attention Neural Network for EEG Emotion Recognition".IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 26.11(2022):5321-5331.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。