Emotion recognition based on convolutional gated recurrent units with attention

Studying brain activity and deciphering the information in electroencephalogram (EEG) signals has become an emerging research field, and substantial advances have been made in the EEG-based classification of emotions. However, using different EEG features and complementarity to discriminate other em...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhu Ye, Yuan Jing, Qinghua Wang, Pengrui Li, Zhihong Liu, Mingjing Yan, Yongqing Zhang, Dongrui Gao
Format: Article
Language:English
Published: Taylor & Francis Group 2023-12-01
Series:Connection Science
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/09540091.2023.2289833
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850237383666040832
author Zhu Ye
Yuan Jing
Qinghua Wang
Pengrui Li
Zhihong Liu
Mingjing Yan
Yongqing Zhang
Dongrui Gao
author_facet Zhu Ye
Yuan Jing
Qinghua Wang
Pengrui Li
Zhihong Liu
Mingjing Yan
Yongqing Zhang
Dongrui Gao
author_sort Zhu Ye
collection DOAJ
description Studying brain activity and deciphering the information in electroencephalogram (EEG) signals has become an emerging research field, and substantial advances have been made in the EEG-based classification of emotions. However, using different EEG features and complementarity to discriminate other emotions is still challenging. Most existing models extract a single temporal feature from the EEG signal while ignoring the crucial temporal dynamic information, which, to a certain extent, constrains the classification capability of the model. To address this issue, we propose an Attention-Based Depthwise Parameterized Convolutional Gated Recurrent Unit (AB-DPCGRU) model and validate it with the mixed experiment on the SEED and SEED-IV datasets. The experimental outcomes revealed that the accuracy of the model outperforms the existing state-of-the-art methods, which confirmed the superiority of our approach over currently popular emotion recognition models.
format Article
id doaj-art-34a31ee1aec2456ca38c172fdb7b79e9
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2023-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-34a31ee1aec2456ca38c172fdb7b79e92025-08-20T02:01:45ZengTaylor & Francis GroupConnection Science0954-00911360-04942023-12-0135110.1080/09540091.2023.2289833Emotion recognition based on convolutional gated recurrent units with attentionZhu Ye0Yuan Jing1Qinghua Wang2Pengrui Li3Zhihong Liu4Mingjing Yan5Yongqing Zhang6Dongrui Gao7Chengdu University of Information Technology, Chengdu, People’s Republic of ChinaChengdu University of Information Technology, Chengdu, People’s Republic of ChinaHubi Wuhan Public Security Bureau, Wuhan City, People’s Republic of ChinaChengdu University of Information Technology, Chengdu, People’s Republic of ChinaChengdu University of Information Technology, Chengdu, People’s Republic of ChinaChengdu University of Information Technology, Chengdu, People’s Republic of ChinaChengdu University of Information Technology, Chengdu, People’s Republic of ChinaChengdu University of Information Technology, Chengdu, People’s Republic of ChinaStudying brain activity and deciphering the information in electroencephalogram (EEG) signals has become an emerging research field, and substantial advances have been made in the EEG-based classification of emotions. However, using different EEG features and complementarity to discriminate other emotions is still challenging. Most existing models extract a single temporal feature from the EEG signal while ignoring the crucial temporal dynamic information, which, to a certain extent, constrains the classification capability of the model. To address this issue, we propose an Attention-Based Depthwise Parameterized Convolutional Gated Recurrent Unit (AB-DPCGRU) model and validate it with the mixed experiment on the SEED and SEED-IV datasets. The experimental outcomes revealed that the accuracy of the model outperforms the existing state-of-the-art methods, which confirmed the superiority of our approach over currently popular emotion recognition models.https://www.tandfonline.com/doi/10.1080/09540091.2023.2289833EEGemotion recognitionattention mechanismdepthwise parameterised convolutionalgate recurrent neural unit
spellingShingle Zhu Ye
Yuan Jing
Qinghua Wang
Pengrui Li
Zhihong Liu
Mingjing Yan
Yongqing Zhang
Dongrui Gao
Emotion recognition based on convolutional gated recurrent units with attention
Connection Science
EEG
emotion recognition
attention mechanism
depthwise parameterised convolutional
gate recurrent neural unit
title Emotion recognition based on convolutional gated recurrent units with attention
title_full Emotion recognition based on convolutional gated recurrent units with attention
title_fullStr Emotion recognition based on convolutional gated recurrent units with attention
title_full_unstemmed Emotion recognition based on convolutional gated recurrent units with attention
title_short Emotion recognition based on convolutional gated recurrent units with attention
title_sort emotion recognition based on convolutional gated recurrent units with attention
topic EEG
emotion recognition
attention mechanism
depthwise parameterised convolutional
gate recurrent neural unit
url https://www.tandfonline.com/doi/10.1080/09540091.2023.2289833
work_keys_str_mv AT zhuye emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention
AT yuanjing emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention
AT qinghuawang emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention
AT pengruili emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention
AT zhihongliu emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention
AT mingjingyan emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention
AT yongqingzhang emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention
AT dongruigao emotionrecognitionbasedonconvolutionalgatedrecurrentunitswithattention