MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence Plots

Emotion recognition based on electroencephalography (EEG) signals has garnered significant research attention in recent years due to its potential applications in affective computing and brain-computer interfaces. Despite the proposal of various deep learning-based methods for extracting emotional f...

Full description

Saved in:
Bibliographic Details
Main Authors: Zihan Zhang, Zhiyong Zhou, Jun Wang, Hao Hu, Jing Zhao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11095664/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849245972130955264
author Zihan Zhang
Zhiyong Zhou
Jun Wang
Hao Hu
Jing Zhao
author_facet Zihan Zhang
Zhiyong Zhou
Jun Wang
Hao Hu
Jing Zhao
author_sort Zihan Zhang
collection DOAJ
description Emotion recognition based on electroencephalography (EEG) signals has garnered significant research attention in recent years due to its potential applications in affective computing and brain-computer interfaces. Despite the proposal of various deep learning-based methods for extracting emotional features from EEG signals, most existing models struggle to effectively capture both long-term and short-term dependencies within the signals, failing to fully integrate features across different temporal scales. To address these challenges, we propose a deep learning model that combines multi-temporal-scale fusion, termed MT-EfficientNetV2. This model segments one-dimensional EEG signals using combinations of varying window sizes and fixed step lengths. The Recursive Plot (RP) algorithm is then employed to transform these segments into RGB images that intuitively represent the dynamic characteristics of the signals, facilitating the capture of complex emotional features. Additionally, a three-branch input feature fusion module has been designed to effectively integrate features across different scales within the same temporal domain. The model architecture incorporates DEconv and the SimAM attention mechanism with EfficientNetV2. This integration enhances the global fusion and expression of multi-scale features while strengthening the extraction of key emotional features at the local level, thereby suppressing redundant information. Experiments conducted on the public datasets SEED and SEED-IV yielded accuracies of 98.67% and 96.89%, respectively, surpassing current mainstream methods and validating the feasibility and effectiveness of the proposed approach.
format Article
id doaj-art-8a3c948f1dca4c2dbd002f47bc77f03c
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8a3c948f1dca4c2dbd002f47bc77f03c2025-08-20T03:58:39ZengIEEEIEEE Access2169-35362025-01-011313207913209610.1109/ACCESS.2025.359233611095664MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence PlotsZihan Zhang0https://orcid.org/0009-0000-3713-2435Zhiyong Zhou1https://orcid.org/0009-0006-9046-3333Jun Wang2https://orcid.org/0000-0001-9115-3755Hao Hu3https://orcid.org/0009-0000-5557-2266Jing Zhao4School of Electronic Information Engineering, Shanghai Dianji University, Shanghai, ChinaSchool of Art and Design, Shanghai Dianji University, Shanghai, ChinaSchool of Computer and Computing Science, Hangzhou City University, Hangzhou, ChinaSchool of Mechanical, Shanghai Dianji University, Shanghai, ChinaSchool of Electronic Information Engineering, Shanghai Dianji University, Shanghai, ChinaEmotion recognition based on electroencephalography (EEG) signals has garnered significant research attention in recent years due to its potential applications in affective computing and brain-computer interfaces. Despite the proposal of various deep learning-based methods for extracting emotional features from EEG signals, most existing models struggle to effectively capture both long-term and short-term dependencies within the signals, failing to fully integrate features across different temporal scales. To address these challenges, we propose a deep learning model that combines multi-temporal-scale fusion, termed MT-EfficientNetV2. This model segments one-dimensional EEG signals using combinations of varying window sizes and fixed step lengths. The Recursive Plot (RP) algorithm is then employed to transform these segments into RGB images that intuitively represent the dynamic characteristics of the signals, facilitating the capture of complex emotional features. Additionally, a three-branch input feature fusion module has been designed to effectively integrate features across different scales within the same temporal domain. The model architecture incorporates DEconv and the SimAM attention mechanism with EfficientNetV2. This integration enhances the global fusion and expression of multi-scale features while strengthening the extraction of key emotional features at the local level, thereby suppressing redundant information. Experiments conducted on the public datasets SEED and SEED-IV yielded accuracies of 98.67% and 96.89%, respectively, surpassing current mainstream methods and validating the feasibility and effectiveness of the proposed approach.https://ieeexplore.ieee.org/document/11095664/EEGemotion recognitionaffective computingrecursive plotDEconvSimAM attention mechanism
spellingShingle Zihan Zhang
Zhiyong Zhou
Jun Wang
Hao Hu
Jing Zhao
MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence Plots
IEEE Access
EEG
emotion recognition
affective computing
recursive plot
DEconv
SimAM attention mechanism
title MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence Plots
title_full MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence Plots
title_fullStr MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence Plots
title_full_unstemmed MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence Plots
title_short MT-EfficientNetV2: A Multi-Temporal Scale Fusion EEG Emotion Recognition Method Based on Recurrence Plots
title_sort mt efficientnetv2 a multi temporal scale fusion eeg emotion recognition method based on recurrence plots
topic EEG
emotion recognition
affective computing
recursive plot
DEconv
SimAM attention mechanism
url https://ieeexplore.ieee.org/document/11095664/
work_keys_str_mv AT zihanzhang mtefficientnetv2amultitemporalscalefusioneegemotionrecognitionmethodbasedonrecurrenceplots
AT zhiyongzhou mtefficientnetv2amultitemporalscalefusioneegemotionrecognitionmethodbasedonrecurrenceplots
AT junwang mtefficientnetv2amultitemporalscalefusioneegemotionrecognitionmethodbasedonrecurrenceplots
AT haohu mtefficientnetv2amultitemporalscalefusioneegemotionrecognitionmethodbasedonrecurrenceplots
AT jingzhao mtefficientnetv2amultitemporalscalefusioneegemotionrecognitionmethodbasedonrecurrenceplots