Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition

In recent years, transfer learning methods have found widespread applications in emotion recognition, especially in domains with limited labeled data. The significant distribution disparity between source and target domains in transfer learning often leads to detrimental negative transfer phenomena....

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Deng, Xinyi Hong, LiJiao Ai, Xingchen Li, Chenhui Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11016662/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467745248215040
author Xin Deng
Xinyi Hong
LiJiao Ai
Xingchen Li
Chenhui Li
author_facet Xin Deng
Xinyi Hong
LiJiao Ai
Xingchen Li
Chenhui Li
author_sort Xin Deng
collection DOAJ
description In recent years, transfer learning methods have found widespread applications in emotion recognition, especially in domains with limited labeled data. The significant distribution disparity between source and target domains in transfer learning often leads to detrimental negative transfer phenomena. To mitigate this issue, the judicious selection of source domain data has proven to be an effective strategy. However, traditional training data selection methods typically require predefined thresholds, which are not easy to set, and the model is trained separately from the training data selection process. In an effort to address this gap, we introduce the Multi-Source Reinforced Selective Domain Adaptation (MSRSDA) model. The MSRSDA model comprises three components: a data augmentation module, a data selector based on the actor-critic framework, and a domain adaptation module. The data augmentation module generates new samples for the data selector to consider. The data selector, acting as an actor, performs actions to select high-quality source domain data for optimization of the domain adaptation model. Additionally, we propose an innovative domain adaptation model that provides rewards to update the data selector. To the best of our knowledge, our work represents an initial attempt to apply reinforcement learning to EEG-based data selection. Extensive experiments on both the public SEED dataset and our in-house dataset demonstrate that the MSRSDA model achieves competitive performance for emotion recognition tasks.
format Article
id doaj-art-33376bd6997f4baf92284df74b3deeaf
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-33376bd6997f4baf92284df74b3deeaf2025-08-20T03:26:05ZengIEEEIEEE Access2169-35362025-01-0113948229483310.1109/ACCESS.2025.357451511016662Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion RecognitionXin Deng0https://orcid.org/0000-0003-1257-694XXinyi Hong1https://orcid.org/0009-0008-8032-3446LiJiao Ai2Xingchen Li3https://orcid.org/0000-0002-3691-9516Chenhui Li4Chongqing Key Laboratory of Germplasm Innovation and Utilization of Native Plants, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Germplasm Innovation and Utilization of Native Plants, Chongqing, ChinaSchool of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaIn recent years, transfer learning methods have found widespread applications in emotion recognition, especially in domains with limited labeled data. The significant distribution disparity between source and target domains in transfer learning often leads to detrimental negative transfer phenomena. To mitigate this issue, the judicious selection of source domain data has proven to be an effective strategy. However, traditional training data selection methods typically require predefined thresholds, which are not easy to set, and the model is trained separately from the training data selection process. In an effort to address this gap, we introduce the Multi-Source Reinforced Selective Domain Adaptation (MSRSDA) model. The MSRSDA model comprises three components: a data augmentation module, a data selector based on the actor-critic framework, and a domain adaptation module. The data augmentation module generates new samples for the data selector to consider. The data selector, acting as an actor, performs actions to select high-quality source domain data for optimization of the domain adaptation model. Additionally, we propose an innovative domain adaptation model that provides rewards to update the data selector. To the best of our knowledge, our work represents an initial attempt to apply reinforcement learning to EEG-based data selection. Extensive experiments on both the public SEED dataset and our in-house dataset demonstrate that the MSRSDA model achieves competitive performance for emotion recognition tasks.https://ieeexplore.ieee.org/document/11016662/Transfer learningdomain adaptationelectroencephalogram (EEG)reinforcement learningemotion recognitionbrain-computer interface
spellingShingle Xin Deng
Xinyi Hong
LiJiao Ai
Xingchen Li
Chenhui Li
Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition
IEEE Access
Transfer learning
domain adaptation
electroencephalogram (EEG)
reinforcement learning
emotion recognition
brain-computer interface
title Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition
title_full Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition
title_fullStr Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition
title_full_unstemmed Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition
title_short Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition
title_sort multi source reinforced selective domain adaptation for cross subject and cross session eeg based emotion recognition
topic Transfer learning
domain adaptation
electroencephalogram (EEG)
reinforcement learning
emotion recognition
brain-computer interface
url https://ieeexplore.ieee.org/document/11016662/
work_keys_str_mv AT xindeng multisourcereinforcedselectivedomainadaptationforcrosssubjectandcrosssessioneegbasedemotionrecognition
AT xinyihong multisourcereinforcedselectivedomainadaptationforcrosssubjectandcrosssessioneegbasedemotionrecognition
AT lijiaoai multisourcereinforcedselectivedomainadaptationforcrosssubjectandcrosssessioneegbasedemotionrecognition
AT xingchenli multisourcereinforcedselectivedomainadaptationforcrosssubjectandcrosssessioneegbasedemotionrecognition
AT chenhuili multisourcereinforcedselectivedomainadaptationforcrosssubjectandcrosssessioneegbasedemotionrecognition