{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T16:36:54Z","timestamp":1785515814797,"version":"3.56.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"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. Comput. Neurosci."],"abstract":"<jats:p>Electroencephalography (EEG)-based emotion recognition faces challenges such as signal noise, non-stationarity, inter-subject variability, and class imbalance, limiting its practical application in affective computing and clinical diagnostics. This study introduces the Attentive Wavelet-Transformer Network (AWT-Net), a novel framework integrating Hierarchical Wavelet Packet Decomposition (HWPD), Empirical Wavelet Transform with Kalman filtering (EWT-Kalman), Multi-Head Self-Attention (MHSA), and a Hybrid Spatio-Temporal Transformer (HSTT) to address these issues. The proposed work is evaluated on a custom EEG dataset (2,132 samples, 14 channels, 28 subjects) and the DEAP dataset (1,280 trials, 40 channels, 32 subjects), AWT-Net achieves window-level, subject-dependent accuracy of 99.61% on DEAP and 99.34% on custom EEG. Under stricter evaluation protocols, accuracy is 99.30% (trial-wise grouped) and 97.23% (subject-independent LOSO) on DEAP, demonstrating robust generalization across varying validation conditions. Comparisons with baseline models (LSTM: 89.42%, CNN-LSTM: 91.75%) are provided under equivalent subject-dependent protocols, while LOSO comparisons (Elrefaiy et al.: &amp;gt;97.00%, Bagherzadeh et al.: ~77.75%) highlight cross-subject performance. Error rates are significantly reduced to 0.70% (EEG) and 0.39% (DEAP), compared to 6.69\u201310.58% for baselines, with statistical validation confirming large effect sizes (Cohen\u2019s d: 1.82\u20132.14). AWT-Net\u2019s adaptive focal loss mitigates class imbalance, while HWPD and EWT-Kalman enhance noise robustness. These results demonstrate AWT-Net\u2019s potential for real-time emotion recognition, advancing applications in healthcare and human-computer interaction.<\/jats:p>","DOI":"10.3389\/fncom.2026.1775449","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T05:44:08Z","timestamp":1780983848000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Modeling multiscale neural dynamics for EEG-based emotion recognition using an attentive wavelet\u2013transformer framework"],"prefix":"10.3389","volume":"20","author":[{"given":"R. S.","family":"Soundariya","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Bannari Amman Institute of Technology","place":["Sathyamangalam, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P.","family":"Thangaraj","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Kangeyam Institute of Technology","place":["Kangeyam, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"105875","DOI":"10.1016\/j.bspc.2023.105875","article-title":"A subject-independent portable emotion recognition system using synchrosqueezing wavelet transform maps of EEG signals and ResNet-18","volume":"90","author":"Bagherzadeh","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"9282","DOI":"10.3390\/s22239282","article-title":"Feature selection for continuous within- and cross-user EEG-based emotion recognition","volume":"22","author":"Bendrich","year":"2022","journal-title":"Sensors"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"102073","DOI":"10.1016\/j.bspc.2020.102073","article-title":"Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification","volume":"62","author":"Carvalho","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"113478","DOI":"10.1016\/j.asoc.2025.113478","article-title":"Advances in EEG-based emotion recognition: challenges, methodologies, and future directions","volume":"180","author":"Chen","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"114097","DOI":"10.1016\/j.asoc.2025.114097","article-title":"Driver fatigue detection using EEG-based graph attention convolutional neural networks: an end-to-end learning approach with mutual information-driven connectivity","volume":"186","author":"Chen","year":"2026","journal-title":"Appl. Soft Comput."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2025.116751","article-title":"Decoding driving states based on normalized mutual information features and hyperparameter self-optimized Gaussian kernel-based radial basis function extreme learning machine","volume":"199","author":"Chen","year":"2025","journal-title":"Chaos Solitons Fractals"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"4270","DOI":"10.3390\/jcm14124270","article-title":"Advancements and challenges of artificial intelligence-assisted electroencephalography in epilepsy management","volume":"14","author":"Chen","year":"2025","journal-title":"J. Clin. Med."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"109284","DOI":"10.1016\/j.bspc.2025.109284","article-title":"Brain power mapping with optimized deep learning for EEG-based pilot fatigue detection","volume":"114","author":"Chen","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"106624","DOI":"10.1016\/j.neunet.2024.106624","article-title":"Emotion recognition using hierarchical spatial\u2013temporal learning transformers from regional to global brain","volume":"179","author":"Cheng","year":"2024","journal-title":"Neural Netw."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"031001","DOI":"10.1088\/1741-2552\/ab0ab5","article-title":"Deep learning for electroencephalogram (EEG) classification tasks: a review","volume":"16","author":"Craik","year":"2019","journal-title":"J. Neural Eng."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"17892","DOI":"10.1038\/s41598-025-02470-5","article-title":"EnsembleEdgeFusion: advancing semantic segmentation in microvascular decompression imaging with innovative ensemble techniques","volume":"15","author":"Dhiyanesh","year":"2025","journal-title":"Sci. Rep."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1007\/s10044-025-01501-1","article-title":"Subject-independent multi-channel voting for EEG-based emotion recognition using wavelet scattering deep network and advanced signal metrics","volume":"28","author":"Elrefaiy","year":"2025","journal-title":"Pattern. Anal. Applic."},{"key":"ref13","first-page":"200","article-title":"Computational efficiency in deep learning for EEG processing","volume":"17","author":"Garcia","year":"2023","journal-title":"Front. Comput. Neurosci."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"14646","DOI":"10.1109\/TIE.2025.3585028","article-title":"Neurodynamics-based visual servo predictive control for improving smooth movement of logistics omnidirectional robots","volume":"72","author":"He","year":"2025","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2025.121542","article-title":"Mitigating choice overload: the interactive effects of set size and overall preference revealed by hierarchical drift diffusion modeling and electroencephalography","volume":"321","author":"Huang","year":"2025","journal-title":"NeuroImage"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"122704","DOI":"10.1016\/j.ins.2025.122704","article-title":"3WD-DRT: a three-way decision enhanced dynamic routing transformer for cost-sensitive multimodal sentiment analysis","volume":"725","author":"Jiang","year":"2026","journal-title":"Inf. Sci."},{"key":"ref17","article-title":"UniEEG: Advancing Universal EEG Representation with Electrode-Wise Time-Frequency Pretraining","volume-title":"In Proceedings of the 13th International Conference on Learning Representations (ICLR)","author":"Jin","year":"2024"},{"key":"ref18","first-page":"1200","article-title":"Cross-validation strategies for EEG-based affect recognition","volume":"30","author":"Johnson","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/j.procs.2022.12.053","article-title":"A subset scaling recursive feature collection-based DDoS detection using behavioural based ideal neural network for security in a cloud environment","volume":"215","author":"Karthick","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref20","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":"2011","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref21","first-page":"150","article-title":"CNN-LSTM architectures for emotion recognition from DEAP","volume":"400","author":"Lee","year":"2020","journal-title":"Neurocomputing"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s12984-024-01369-y","article-title":"Exploration of a machine learning approach for diagnosing sarcopenia among Chinese community-dwelling older adults using sEMG-based data","volume":"21","author":"Li","year":"2024","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"5755","DOI":"10.1109\/JBHI.2024.3395622","article-title":"Attention-based temporal graph representation learning for EEG-based emotion recognition","volume":"28","author":"Li","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TAFFC.2025.3585599","article-title":"MLM-EOE: automatic depression detection via sentimental annotation and multi-expert ensemble","volume":"16","author":"Lin","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref25","first-page":"185","author":"Naveenkumar","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1186\/s12984-024-01497-5","article-title":"Detecting muscle fatigue among community-dwelling senior adults with shape features of the probability density function of sEMG","volume":"21","author":"Ou","year":"2024","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e0000290","DOI":"10.1371\/journal.pdig.0000290","article-title":"Imbalanced class distribution and performance evaluation metrics: a systematic review of prediction accuracy for determining model performance in healthcare systems","volume":"2","author":"Owusu-Adjei","year":"2023","journal-title":"PLOS Digital Health"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2819","DOI":"10.36922\/bh.2819","article-title":"Recognition predictive modeling using electroencephalogram","volume":"2","author":"Sangeetha","year":"2024","journal-title":"Brain Heart"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1109\/TNSRE.2023.3346955","article-title":"B2-ViT net: broad vision transformer network with broad attention for seizure prediction","volume":"32","author":"Shi","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e14080","DOI":"10.1111\/psyp.14080","article-title":"A systematic data-driven approach to analyze sensor-level EEG connectivity: identifying robust phase-synchronized network components using surface Laplacian with spectral-spatial PCA","volume":"59","author":"Smith","year":"2022","journal-title":"Psychophysiology"},{"key":"ref31","first-page":"103","article-title":"Physiological variability in EEG datasets: challenges and solutions","volume":"115","author":"Smith","year":"2021","journal-title":"J. Biomed. Inform."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"7397","DOI":"10.1109\/TVCG.2024.3456213","article-title":"Expressive 3D facial animation generation based on local-to-global latent diffusion","volume":"30","author":"Song","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref33","first-page":"2100","article-title":"Real-time constraints in EEG-based systems","volume":"25","author":"Taylor","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"117292","DOI":"10.1016\/j.chaos.2025.117292","article-title":"Field and delay effects on synchronization in a multilayer memristive neuronal network with a hub","volume":"201","author":"Tian","year":"2025","journal-title":"Chaos, Solitons Fractals"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1252","DOI":"10.3390\/sym17081252","article-title":"Dynamical analysis, feedback control circuit implementation, and fixed-time sliding mode synchronization of a novel 4D chaotic system","volume":"17","author":"Tian","year":"2025","journal-title":"Symmetry"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2025.1665590","article-title":"Enhanced Parkinson's disease prediction using LDEFS feature selection and Mamdani fuzzy neural network","volume":"17","author":"Vijayalakshmi","year":"2025","journal-title":"Front. Aging Neurosci."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"103961","DOI":"10.1016\/j.ipm.2024.103961","article-title":"Fusion of generative adversarial networks and non-negative tensor decomposition for depression fMRI data analysis","volume":"62","author":"Wang","year":"2025","journal-title":"Inf. Process. Manag."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"4120","DOI":"10.1109\/.JSEN.2025.3644160","article-title":"Nonlinear feature decomposition and deep temporal\u2013spatial learning for single-channel sEMG-based lower limb motion recognition","volume":"26","author":"Wei","year":"2026","journal-title":"IEEE Sensors J."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"016022","DOI":"10.1088\/1741-2552\/acae06","article-title":"DAGAM: a domain adversarial graph attention model for subject-independent EEG-based emotion recognition","volume":"20","author":"Xu","year":"2023","journal-title":"J. Neural Eng."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"32366","DOI":"10.1109\/JIOT.2025.3576735","article-title":"Blockchain-based verifiable decentralized identity for intelligent flexible manufacturing","volume":"12","author":"Xu","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"105213","DOI":"10.1016\/j.bspc.2023.105213","article-title":"An application of the Kalman filter for EEG\/ERP signal enhancement with the autoregressive realisation","volume":"86","author":"Yadav","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"268","DOI":"10.3390\/brainsci14030268","article-title":"Emotion classification based on transformer and CNN for EEG spatial\u2013temporal feature learning","volume":"14","author":"Yao","year":"2024","journal-title":"Brain Sci."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"436","DOI":"10.3390\/brainsci14050436","article-title":"Research on fatigue driving detection technology based on CA-ACGAN","volume":"14","author":"Ye","year":"2024","journal-title":"Brain Sci."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"106986","DOI":"10.1016\/j.bspc.2024.106986","article-title":"Fusing temporal-frequency information with contrast learning on graph convolution network to decoding EEG","volume":"100","author":"Yu","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"112456","DOI":"10.1016\/j.jbiomech.2024.112456","article-title":"Differences between two maximal principal strain rate calculation schemes in traumatic brain analysis with in-vivo and in-silico datasets","volume":"179","author":"Zhan","year":"2025","journal-title":"J. Biomech."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"13491","DOI":"10.1038\/s41598-024-62990-4","article-title":"TPRO-NET: an EEG-based emotion recognition method reflecting subtle changes in emotion","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1775449\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T05:44:10Z","timestamp":1780983850000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1775449\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":46,"alternative-id":["10.3389\/fncom.2026.1775449"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2026.1775449","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]},"article-number":"1775449"}}