OSCR

A dual-branch network with brain region-constrained attention for EEG emotion recognition.

Overview

Authors: Chengyu Hua1, Hui Cao2, Zhaolong Li1, Zhiqiang Huang1
  1. Key Laboratory of Linguistic and Cultural Computing, Ministry of Education, ‘National Languages Information Technology, Northwest Minzu University, Lanzhou, China
  2. Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, “National Languages Information Technology, Northwest Minzu University, Lanzhou, China
Institutions: Northwest Minzu University (China)
Journal: Frontiers in neuroscience, volume 20, article 1810609
Dates: received 13 February 2026; accepted 15 June 2026; published online 7 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3389/fnins.2026.1810609 · PMID 42483225 · PMCID PMC13385186 · OpenAlex W7167623324
Open access: gold, a free copy (OpenAlex)
Categories: EEG (modality), cognitive (subfield)
Methods: Spectral & time-frequency, Machine learning
Keywords: channel attention calculation, deep learning, electroencephalography (EEG), emotion recognition, multi-domain feature, multi-scale
Topic: Emotion and Mood Recognition (Artificial Intelligence, Computer Science), according to OpenAlex
Citations: not cited yet (Europe PMC); 61 references in the paper

Abstract

Introduction: Electroencephalography (EEG)-based emotion recognition provides an objective avenue for affective computing. However, the complexity of EEG signals across temporal, frequency, and spatial domains makes any single dimension inadequate.

Methods: To overcome these limitations, we propose the Brain Region-Constrained Attention Dual-Branch Network (BRAD-Net). This network adopts a parallel Spatio-Temporal and Spectral-Spatial dual-branch architecture to achieve synergistic multi-domain EEG feature learning. Within the spatio-temporal branch, we introduce a novel Brain Region-Constrained Attention mechanism, which strictly confines self-attention computation to channels belonging to the same brain region. This design not only suppresses irrelevant cross-region interference but also incorporates neuroanatomical priors of brain parcellation, thereby enabling effective and interpretable representation learning.

Results: In subject-dependent experiments using 10-fold cross-validation on DEAP and DREAMER datasets, BRAD-Net achieves high accuracies of 97.44%, 97.70%, and 97.97% for valence, arousal, and dominance on DEAP, and 99.66%, 99.78%, and 99.80% on DREAMER, respectively. Leave-one-subject-out validation on DREAMER dataset achieves accuracies of 72.80% and 75.66% for arousal and dominance, respectively. Additionally, the BRAD-Net demonstrates strong cross-paradigm adaptability, achieving 98.21% accuracy on a depression classification dataset.

Conclusions: These findings confirm that integrating neuroanatomical priors into a dual-branch multi-dimensional learning framework effectively extracts robust and interpretable neural representations. BRAD-Net not only advances high-performance EEG emotion recognition but also provides a novel, biologically-constrained design paradigm for developing more interpretable brain-computer interface models. By demonstrating that restricting attention to within-brain-region interactions suffices for accurate emotion recognition, our work offers a new theoretical perspective on the application of brain parcellation knowledge in classification models.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data availability statement

Publicly available datasets were analyzed in this study. The DEAP dataset used in this study was introduced in https://doi.org/10.1109/T-AFFC.2011.15; the DREAMER dataset is available at https://zenodo.org/records/546113; and the depression detection dataset is available at https://figshare.com/articles/dataset/EEG_Data_New/4244171.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 4 authors, 6 keywords, 59 references.

Cite

This paper

Hua, C., Cao, H., Li, Z., & Huang, Z. (2026). A dual-branch network with brain region-constrained attention for EEG emotion recognition. Frontiers in neuroscience, 20, 1810609. https://doi.org/10.3389/fnins.2026.1810609

BibTeX

@article{hua2026dual,
author = {Hua, Chengyu and Cao, Hui and Li, Zhaolong and Huang, Zhiqiang},
title = {{A dual-branch network with brain region-constrained attention for EEG emotion recognition}},
journal = {Frontiers in neuroscience},
year = {2026},
month = jul,
volume = {20},
pages = {1810609},
publisher = {Frontiers Media SA},
issn = {1662-4548},
doi = {10.3389/fnins.2026.1810609},
url = {https://doi.org/10.3389/fnins.2026.1810609},
pmid = {42483225},
pmcid = {PMC13385186}
}

RIS

TY - JOUR
AU - Hua, Chengyu
AU - Cao, Hui
AU - Li, Zhaolong
AU - Huang, Zhiqiang
TI - A dual-branch network with brain region-constrained attention for EEG emotion recognition
T2 - Frontiers in neuroscience
J2 - Front Neurosci
PY - 2026
DA - 2026/07/07
VL - 20
SP - 1810609
SN - 1662-4548
PB - Frontiers Media SA
DO - 10.3389/fnins.2026.1810609
UR - https://doi.org/10.3389/fnins.2026.1810609
LA - en
ER -

CSL-JSON

{
"id": "10.3389/fnins.2026.1810609",
"type": "article-journal",
"title": "A dual-branch network with brain region-constrained attention for EEG emotion recognition",
"container-title": "Frontiers in neuroscience",
"author": [
{
"family": "Hua",
"given": "Chengyu"
},
{
"family": "Cao",
"given": "Hui"
},
{
"family": "Li",
"given": "Zhaolong"
},
{
"family": "Huang",
"given": "Zhiqiang"
}
],
"container-title-short": "Front Neurosci",
"volume": "20",
"page": "1810609",
"DOI": "10.3389/fnins.2026.1810609",
"PMID": "42483225",
"PMCID": "PMC13385186",
"ISSN": "1662-4548",
"publisher": "Frontiers Media SA",
"URL": "https://doi.org/10.3389/fnins.2026.1810609",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
7
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.12688/f1000research.171170.2
A Review of Deep Learning Techniques for EEG-Based Emotion Recognition: Models, Methods, and Datasets.
Journal: F1000Research
In common: EEG, cognitive, 22 references
[2] doi:10.3390/s24061979
FC-TFS-CGRU: A Temporal-Frequency-Spatial Electroencephalography Emotion Recognition Model Based on Functional Connectivity and a Convolutional Gated Recurrent Unit Hybrid Architecture.
Journal: Sensors (Basel, Switzerland)
In common: Zenodo 546113, EEG, cognitive, 11 references
[3] doi:10.3390/brainsci16040377 [code]
Method for Emotion Recognition of EEG Signals Based on Recursive Graph and Spatiotemporal Attention Mechanism.
Journal: Brain sciences
In common: EEG, cognitive, 8 references
[4] doi:10.3390/s26175327 [code]
Subject Identity Confounds qEEG Emotion Recognition on DEAP and DREAMER.
Journal: Sensors (Basel, Switzerland)
In common: Zenodo 546113, EEG, cognitive, 5 references
[5] doi:10.3389/fnins.2024.1320645 [code]
ERTNet: an interpretable transformer-based framework for EEG emotion recognition.
Journal: Frontiers in neuroscience
In common: EEG, cognitive, 7 references
[6] doi:10.1038/s41598-025-34211-z
A multi-task EEG emotion recognition method based on emotion-dimension coupling constraints.
Journal: Scientific reports
In common: Zenodo 546113, EEG, cognitive, 4 references
[7] doi:10.3390/s25072029
MSDSANet: Multimodal Emotion Recognition Based on Multi-Stream Network and Dual-Scale Attention Network Feature Representation.
Journal: Sensors (Basel, Switzerland)
In common: Zenodo 546113, EEG, cognitive, 4 references
[8] doi:10.3390/brainsci16070716
RGB-Style Input Representations for EEG: Evaluating Spatial Concatenation Versus Band-Wise Stacking in Deep Emotion Recognition.
Journal: Brain sciences
In common: Zenodo 546113, EEG, cognitive, 4 references
[9] doi:10.1038/s41598-021-00812-7
EEG-based detection of emotional valence towards a reproducible measurement of emotions.
Journal: Scientific reports
In common: Zenodo 546113, EEG, cognitive, 4 references
[10] doi:10.3390/bios16080400
EEG and ECG Wearable Biosensor-Based Affective State Analysis Using Deep Learning over 6G IoT Healthcare Networks.
Journal: Biosensors
In common: EEG, 7 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.