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. 脑图谱与类脑智能实验室
  5. 神经计算及脑机交互
Dynamic Domain Adaptation for Class-Aware Cross-Subject and Cross-Session EEG Emotion Recognition

文献类型：期刊论文

作者Li, Zhunan3,4; Zhu, Enwei3,4; Jin, Ming3,4; Fan, Cunhang2; He, Huiguang1; Cai, Ting3,4; Li, Jinpeng3,4
刊名IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
出版日期2022-12-01
卷号26期号:12页码:5964-5973
关键词Brain-computer interface emotion recognition transfer learning domain adaptation
ISSN号2168-2194
DOI10.1109/JBHI.2022.3210158
通讯作者Cai, Ting(caiting@ucas.ac.cn)
英文摘要It is vital to develop general models that can be shared across subjects and sessions in the real-world deployment of electroencephalogram (EEG) emotion recognition systems. Many prior studies have exploited domain adaptation algorithms to alleviate the inter-subject and inter-session discrepancies of EEG distributions. However, these methods only aligned the global domain divergence, but overlooked the local domain divergence with respect to each emotion category. This degenerates the emotion-discriminating ability of the domain invariant features. In this paper, we argue that aligning the EEG data within the same emotion categories is important for generalizable and discriminative features. Hence, we propose the dynamic domain adaptation (DDA) algorithm where the global and local divergences are disposed by minimizing the global domain discrepancy and local subdomain discrepancy, respectively. To tackle the absence of emotion labels in the target domain, we introduce a dynamic training strategy where the model focuses on optimizing the global domain discrepancy in the early training steps, and then gradually switches to the local subdomain discrepancy. The DDA algorithm is formally implemented as an unsupervised version and a semi-supervised version for different experimental settings. Based on the coarse-to-fine alignment, our model achieves the average peak accuracy of 91.08%, 92.89% on SEED, and 81.58%, 80.82% on SEED-IV in the cross-subject and cross-session scenarios, respectively.
资助项目National Natural Science Foundation of China[62106248] ; Zhejiang Provincial Natural Science Foundation of China[LQ20F030013] ; Ningbo Public Service Technology Foundation, China[202002N3181] ; Ningbo Public Service Technology Foundation, China[2021S152] ; Ningbo Science and Technology Service Industry Demonstration Project, China[2020F041] ; Medical Scientific Research Foundation of Zhejiang Province, China[2021KY1028]
WOS研究方向Computer Science ; Mathematical & Computational Biology ; Medical Informatics
语种英语
WOS记录号WOS:000894943300020
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Zhejiang Provincial Natural Science Foundation of China ; Ningbo Public Service Technology Foundation, China ; Ningbo Science and Technology Service Industry Demonstration Project, China ; Medical Scientific Research Foundation of Zhejiang Province, China
源URL[http://ir.ia.ac.cn/handle/173211/50982]  
专题类脑智能研究中心_神经计算及脑机交互
通讯作者Cai, Ting
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100045, Peoples R China
2.Anhui Univ, Sch Comp Sci & Technol, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230093, Anhui, Peoples R China
3.Univ Chinese Acad Sci, Ningbo Inst Life & Hlth Ind, Ningbo 101408, Zhejiang, Peoples R China
4.Univ Chinese Acad Sci, HwaMei Hosp, Ningbo 101408, Zhejiang, Peoples R China
推荐引用方式
GB/T 7714		 Li, Zhunan,Zhu, Enwei,Jin, Ming,et al. Dynamic Domain Adaptation for Class-Aware Cross-Subject and Cross-Session EEG Emotion Recognition[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2022,26(12):5964-5973.
APA Li, Zhunan.,Zhu, Enwei.,Jin, Ming.,Fan, Cunhang.,He, Huiguang.,...&Li, Jinpeng.(2022).Dynamic Domain Adaptation for Class-Aware Cross-Subject and Cross-Session EEG Emotion Recognition.IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,26(12),5964-5973.
MLA Li, Zhunan,et al."Dynamic Domain Adaptation for Class-Aware Cross-Subject and Cross-Session EEG Emotion Recognition".IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 26.12(2022):5964-5973.

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。