{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T21:38:54Z","timestamp":1789508334072,"version":"build-2803163510"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2026.1810609","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:47:50Z","timestamp":1783403270000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A dual-branch network with brain region-constrained attention for EEG emotion recognition"],"prefix":"10.3389","volume":"20","author":[{"given":"Chengyu","family":"Hua","sequence":"first","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing, Ministry of Education, \u2018National Languages Information Technology, Northwest Minzu University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Cao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, \u201cNational Languages Information Technology, Northwest Minzu University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaolong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing, Ministry of Education, \u2018National Languages Information Technology, Northwest Minzu University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing, Ministry of Education, \u2018National Languages Information Technology, Northwest Minzu University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"105312","DOI":"10.1016\/j.bspc.2023.105312","article-title":"A novel caps-EEGNet combined with channel selection for EEG-based emotion recognition","volume":"86","author":"Chen","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B2","doi-asserted-by":"publisher","first-page":"107267","DOI":"10.1016\/j.neunet.2025.107267","article-title":"A novel deep learning model combining 3DCNN-CapsNet and hierarchical attention mechanism for EEG emotion recognition","volume":"186","author":"Chen","year":"2025","journal-title":"Neural Netw"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1416494","DOI":"10.3389\/fncom.2024.1416494","article-title":"EEG-based emotion recognition using graph convolutional neural network with dual attention mechanism","volume":"18","author":"Chen","year":"2024","journal-title":"Front. Comput. Neurosci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"14378","DOI":"10.1038\/s41598-022-18502-3","article-title":"EEG temporal-spatial transformer for person identification","volume":"12","author":"Du","year":"2022","journal-title":"Sci. Rep"},{"key":"B5","doi-asserted-by":"publisher","first-page":"102522","DOI":"10.1016\/j.aei.2024.102522","article-title":"Light-weight residual convolution-based capsule network for EEG emotion recognition","volume":"61","author":"Fan","year":"","journal-title":"Adv. Eng. Inf"},{"key":"B6","doi-asserted-by":"publisher","first-page":"105422","DOI":"10.1016\/j.bspc.2023.105422","article-title":"ICaps-ResLSTM: improved capsule network and residual LSTM for EEG emotion recognition","volume":"87","author":"Fan","year":"","journal-title":"Biomed. Signal Process. Control"},{"key":"B7","doi-asserted-by":"publisher","first-page":"726","DOI":"10.3390\/app14020726","article-title":"EEG emotion classification based on graph convolutional network","volume":"14","author":"Fan","year":"","journal-title":"Appl. Sci"},{"key":"B8","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.aej.2025.09.035","article-title":"Dynamic learning of auditory attention patterns under combinatorial space","volume":"130","author":"Gao","year":"","journal-title":"Alexandria Eng. J"},{"key":"B9","doi-asserted-by":"publisher","first-page":"108856","DOI":"10.1016\/j.neunet.2026.108856","article-title":"An efficient brain-heart coupling learning system for emotion recognition","volume":"200","author":"Gao","year":"2026","journal-title":"Neural Netw"},{"key":"B10","doi-asserted-by":"publisher","first-page":"107457","DOI":"10.1016\/j.neunet.2025.107457","article-title":"A multi-domain constraint learning system inspired by adaptive cognitive graphs for emotion recognition","volume":"188","author":"Gao","year":"","journal-title":"Neural Netw"},{"key":"B11","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","article-title":"\u201cLong short-term memory,\u201d","author":"Graves","year":"2012","journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3428607","article-title":"Mecam: a novel multi-axis EEG channel attention model for emotion recognition","volume":"73","author":"Hou","year":"2024","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B13","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1109\/TAFFC.2025.3611173","article-title":"STRFLNet: spatio-temporal representation fusion learning network for EEG-based emotion recognition","volume":"17","author":"Hu","year":"2025","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B14","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3390\/electronics15010039","article-title":"A SimAm-enhanced multi-resolution CNN with BiGRU for EEG emotion recognition: 4D-MRSimNet","volume":"15","author":"Huang","year":"2026","journal-title":"Electronics"},{"key":"B15","doi-asserted-by":"publisher","first-page":"945024","DOI":"10.3389\/fnagi.2022.945024","article-title":"Electroencephalogram signals emotion recognition based on convolutional neural network-recurrent neural network framework with channel-temporal attention mechanism for older adults","volume":"14","author":"Jiang","year":"2022","journal-title":"Front. Aging Neurosci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"627892","DOI":"10.1155\/2014\/627892","article-title":"EEG-based emotion recognition using deep learning network with principal component based covariate shift adaptation","volume":"2014","author":"Jirayucharoensak","year":"2014","journal-title":"Sci. World J"},{"key":"B17","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/JBHI.2017.2688239","article-title":"Dreamer: a database for emotion recognition through EEG and ECG signals from wireless low-cost off-the-shelf devices","volume":"22","author":"Katsigiannis","year":"2018","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B18","article-title":"\u201cAdam: a method for stochastic optimization,\u201d","volume-title":"2015 3rd International Conference on Learning Representations (ICLR)","author":"Kingma","year":"2015"},{"key":"B19","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","article-title":"Deap: a database for emotion analysis using physiological signals","volume":"3","author":"Koelstra","year":"2012","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B20","doi-asserted-by":"publisher","first-page":"105303","DOI":"10.1016\/j.compbiomed.2022.105303","article-title":"Emotion recognition from EEG based on multi-task learning with capsule network and attention mechanism","volume":"143","author":"Li","year":"","journal-title":"Comput. Biol. Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"108228","DOI":"10.1016\/j.neunet.2025.108228","article-title":"An adaptive decoupling learning system informed by the brain functional structure for EEG decoding","volume":"195","author":"Li","year":"2026","journal-title":"Neural Netw"},{"key":"B22","doi-asserted-by":"publisher","first-page":"110613","DOI":"10.1016\/j.asoc.2023.110613","article-title":"An EEG-based brain cognitive dynamic recognition network for representations of brain fatigue","volume":"146","author":"Li","year":"","journal-title":"Appl. Soft Comput"},{"key":"B23","doi-asserted-by":"publisher","first-page":"41859","DOI":"10.1109\/ACCESS.2023.3270317","article-title":"EEG-based emotion recognition using spatial-temporal-connective features via multi-scale CNN","volume":"11","author":"Li","year":"","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1109\/TCDS.2023.3270170","article-title":"EEG-based emotion recognition using trainable adjacency relation driven graph convolutional network","volume":"15","author":"Li","year":"","journal-title":"IEEE Trans. Cogn. Dev. Syst"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3524499","article-title":"EEG based emotion recognition: a tutorial and review","volume":"55","author":"Li","year":"","journal-title":"ACM Comput. Surv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"114364","DOI":"10.1016\/j.knosys.2025.114364","article-title":"MTSL-timesnet: a multi-task self-supervised learning model based on timesnet for EEG emotion recognition","volume":"329","author":"Li","year":"2025","journal-title":"Knowl. Based Syst"},{"key":"B27","doi-asserted-by":"publisher","first-page":"87237","DOI":"10.1109\/ACCESS.2024.3417525","article-title":"Emotion recognition in EEG based on multilevel multidomain feature fusion","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Access"},{"key":"B28","doi-asserted-by":"publisher","first-page":"110077","DOI":"10.1016\/j.bspc.2026.110077","article-title":"Selective channel bypassing meets capsules: efficient and robust EEG emotion recognition","volume":"120","author":"Lin","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1481746","DOI":"10.3389\/fnbot.2024.1481746","article-title":"Directional spatial and spectral attention network (DSSA net) for EEG-based emotion recognition","volume":"18","author":"Liu","year":"2025","journal-title":"Front. Neurorobot"},{"key":"B30","doi-asserted-by":"publisher","first-page":"110372","DOI":"10.1016\/j.knosys.2023.110372","article-title":"EEG emotion recognition based on the attention mechanism and pre-trained convolution capsule network","volume":"265","author":"Liu","year":"","journal-title":"Knowl. Based Syst"},{"key":"B31","doi-asserted-by":"publisher","first-page":"104799","DOI":"10.1016\/j.bspc.2023.104799","article-title":"Glfanet: a global to local feature aggregation network for EEG emotion recognition","volume":"85","author":"Liu","year":"","journal-title":"Biomed. Signal Process. Control"},{"key":"B32","doi-asserted-by":"publisher","first-page":"103927","DOI":"10.1016\/j.compbiomed.2020.103927","article-title":"Multi-channel EEG-based emotion recognition via a multi-level features guided capsule network","volume":"123","author":"Liu","year":"2020","journal-title":"Comput. Biol. Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1109\/JBHI.2022.3232514","article-title":"Bi-CapsNet: a binary capsule network for EEG-based emotion recognition","volume":"27","author":"Liu","year":"","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B34","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/THMS.2023.3235003","article-title":"Fusion of spatial, temporal, and spectral EEG signatures improves multilevel cognitive load prediction","volume":"53","author":"Liu","year":"","journal-title":"IEEE Trans. Hum. Mach. Syst"},{"key":"B35","doi-asserted-by":"publisher","first-page":"104428","DOI":"10.1016\/j.compbiomed.2021.104428","article-title":"Automated accurate emotion recognition system using rhythm-specific deep convolutional neural network technique with multi-channel EEG signals","volume":"134","author":"Maheshwari","year":"2021","journal-title":"Comput. Biol. Med"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/DSP65409.2025.11074850","article-title":"\u201cDuMoNet: enhancing emotion recognition with a dual-modality structure from EEG and ECG,\u201d","author":"Miao","year":"2025","journal-title":"2025 25th international conference on digital signal processing (DSP)"},{"key":"B37","volume-title":"MDD Patients and Healthy Controls EEG Data (New)","author":"Mumtaz","year":"2016"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.3390\/electronics14061193","article-title":"An optimized hybrid approach to denoising of EEG signals using CNN and LMS filtering","volume":"14","author":"Nair","year":"2025","journal-title":"Electronics"},{"key":"B39","doi-asserted-by":"publisher","first-page":"106537","DOI":"10.1016\/j.compbiomed.2023.106537","article-title":"Temporal relative transformer encoding cooperating with channel attention for EEG emotion analysis","volume":"154","author":"Peng","year":"2023","journal-title":"Comput. Biol. Med"},{"key":"B40","doi-asserted-by":"publisher","first-page":"109038","DOI":"10.1016\/j.knosys.2022.109038","article-title":"Affect recognition from scalp-EEG using channel-wise encoder networks coupled with geometric deep learning and multi-channel feature fusion","volume":"250","author":"Priyasad","year":"2022","journal-title":"Knowl. Based Syst"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1016\/j.neuroimage.2009.10.003","article-title":"Complex network measures of brain connectivity: uses and interpretations","volume":"52","author":"Rubinov","year":"2010","journal-title":"NeuroImage"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/BioSMART54244.2021.9677807","article-title":"\u201cMulti-task CNN model for emotion recognition from EEG brain maps,\u201d","author":"Rudakov","year":"2021","journal-title":"2021 4th international conference on bio-engineering for smart technologies (BioSMART)"},{"key":"B43","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1007\/s11571-020-09634-1","article-title":"EEG-based emotion recognition using 4D convolutional recurrent neural network","volume":"14","author":"Shen","year":"2020","journal-title":"Cogn. Neurodyn"},{"key":"B44","doi-asserted-by":"publisher","first-page":"131749","DOI":"10.1016\/j.neucom.2025.131749","article-title":"Dynamic sparse directed graph convolutional network with attention mechanisms for EEG emotion recognition","volume":"658","author":"Shen","year":"2025","journal-title":"Neurocomputing"},{"key":"B45","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TNSRE.2022.3230250","article-title":"EEG conformer: convolutional transformer for EEG decoding and visualization","volume":"31","author":"Song","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng"},{"key":"B46","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1109\/TAFFC.2020.3025777","article-title":"EEG-based emotion recognition via channel-wise attention and self attention","volume":"14","author":"Tao","year":"2023","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B47","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Advances in neural information processing systems, Vol. 30","author":"Vaswani","year":"2017"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.3390\/s24061979","article-title":"FC-TFS-CGRU: a temporal\u2013frequency\u2013spatial electroencephalography emotion recognition model based on functional connectivity and a convolutional gated recurrent unit hybrid architecture","volume":"24","author":"Wu","year":"2024","journal-title":"Sensors"},{"key":"B49","doi-asserted-by":"publisher","first-page":"18","DOI":"10.31083\/j.jin2301018","article-title":"Fusion of multi-domain EEG signatures improves emotion recognition","volume":"23","author":"Xiaomin","year":"2024","journal-title":"J. Integr. Neurosci"},{"key":"B50","doi-asserted-by":"publisher","first-page":"23049","DOI":"10.1007\/s00521-024-10469-8","article-title":"An improved graph convolutional neural network for EEG emotion recognition","volume":"36","author":"Xu","year":"2024","journal-title":"Neural Comput. Appl"},{"key":"B51","doi-asserted-by":"publisher","first-page":"112826","DOI":"10.1016\/j.knosys.2024.112826","article-title":"The mitigation of heterogeneity in temporal scale among different cortical regions for EEG emotion recognition","volume":"309","author":"Xu","year":"2025","journal-title":"Knowl. Based Syst"},{"key":"B52","doi-asserted-by":"publisher","first-page":"131822","DOI":"10.1016\/j.neucom.2025.131822","article-title":"A hybrid SGC-transformer network for EEG emotion recognition with historical data integration","volume":"659","author":"Yang","year":"2026","journal-title":"Neurocomputing"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN.2018.8489331","article-title":"\u201cEmotion recognition from multi-channel EEG through parallel convolutional recurrent neural network,\u201d","author":"Yang","year":"2018"},{"key":"B54","doi-asserted-by":"publisher","first-page":"19489","DOI":"10.1109\/TNNLS.2022.3225855","article-title":"Hierarchical dynamic graph convolutional network with interpretability for EEG-based emotion recognition","volume":"36","author":"Ye","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B55","doi-asserted-by":"publisher","first-page":"2289833","DOI":"10.1080\/09540091.2023.2289833","article-title":"Emotion recognition based on convolutional gated recurrent units with attention","volume":"35","author":"Ye","year":"2023","journal-title":"Conn. Sci"},{"key":"B56","doi-asserted-by":"publisher","first-page":"53875","DOI":"10.52202\/075280-2344","article-title":"Learning topology-agnostic EEG representations with geometry-aware modeling","volume":"36","author":"Yi","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B57","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s11571-025-10324-z","article-title":"Emotion recognition of cnn bidirectional long short-term memory with center and softmax loss function (CNN-BILSTM-CS) EEG-based","volume":"19","author":"Zhang","year":"2025","journal-title":"Cogn. Neurodyn"},{"key":"B58","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1007\/978-3-031-72120-5_26","article-title":"\u201cFeature fusion based on mutual-cross-attention mechanism for EEG emotion recognition,\u201d","author":"Zhao","year":"2024","journal-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2024"},{"key":"B59","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1109\/TAMD.2015.2431497","article-title":"Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks","volume":"7","author":"Zheng","year":"2015","journal-title":"IEEE Trans. Auton. Ment. Dev"},{"key":"B60","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1109\/TAFFC.2020.2994159","article-title":"EEG-based emotion recognition using regularized graph neural networks","volume":"13","author":"Zhong","year":"2022","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B61","doi-asserted-by":"publisher","first-page":"15278","DOI":"10.1007\/s10489-022-04228-2","article-title":"Bi-hemisphere asymmetric attention network: recognizing emotion from EEG signals based on the transformer","volume":"53","author":"Zhong","year":"2023","journal-title":"Appl. Intell"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1810609\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:47:51Z","timestamp":1783403271000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1810609\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":61,"alternative-id":["10.3389\/fnins.2026.1810609"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1810609","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"article-number":"1810609"}}