A Multi-Scale Inverted Spatial-Temporal Network for EEG-Based Emotion Recognition
Received: 21 January 2026 | Revised: 31 March 2026 and 22 April 2026 | Accepted: 23 April 2026 | Online: 6 June 2026
Corresponding author: Vinod R. Kokitkar
Abstract
Understanding human emotional states through Electroencephalography (EEG) signals has gained significant attention due to its applications in healthcare, human-computer interaction, and affective computing. However, existing approaches often struggle to model temporal dynamics and spatial dependencies effectively, which limits recognition accuracy. The primary research gap lies in the inability of conventional and recent models to simultaneously capture multi-scale temporal patterns while preserving channel-specific information over time. To address this limitation, this study proposes a Multi-Scale Inverted Spatial-Temporal Network (MIST-E) for EEG-based emotion recognition. MIST-E constructs multi-scale representations and employs an inverted embedding strategy to maintain temporal continuity and spatial channel relationships. In addition, a newly designed CNN is used to extract discriminative features for reliable classification. Experimental results on the DEAP dataset demonstrate that MIST-E effectively captures complex spatial-temporal dependencies, achieving 90.56±1.02% accuracy for valence and 91.12±0.98% for arousal. These findings indicate that MIST-E provides improved accuracy compared to existing methods.
Keywords:
EEG signals, emotion recognition, deep learning, multi-scale learning, inverted embeddingReferences
M. V. Cruz, S. Jamal, and S. C. Sethuraman, "A Comprehensive Survey of Brain–Computer Interface Technology in Health care: Research Perspectives," Journal of Medical Signals & Sensors, vol. 15, no. 6, June 2025.
N. Babu, U. Satija, J. Mathew, and A. P. Vinod, "Emotion recognition in virtual and non-virtual environments using EEG signals: Dataset and evaluation," Biomedical Signal Processing and Control, vol. 106, Aug. 2025, Art. no. 107674.
A. Raza and M. Z. Yusoff, "Development of a CNN-LSTM Deep Learning Model for Motor Imagery EEG Classification for BCI Applications," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 22705–22711, June 2025.
M. A. Mahmood, K. Alsalem, M. K. Elbashir, S. A. El-Ghany, and A. A. A. El-Aziz, "Segmentation-enhanced approach for emotion detection from EEG signals using the fuzzy C-mean and SVM," Scientific Reports, vol. 15, no. 1, Aug. 2025, Art. no. 31956.
K. Sutijirapan, S. Auephanwiriyakul, and N. Theera-Umpon, "Emotion Detection from Electroencephalography Signals Using String Grammar K-Nearest Neighbors," in 2024 21st International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), May 2024, pp. 1–4.
F. Yan, Z. Guo, A. M. Iliyasu, and K. Hirota, "Multi-branch convolutional neural network with cross-attention mechanism for emotion recognition," Scientific Reports, vol. 15, no. 1, Feb. 2025, Art. no. 3976.
K. Devarajan, S. Ponnan, and S. Perumal, "Hybrid CNN-transformer architecture for enhanced EEG-based emotion recognition: capturing local and global dependencies with self-attention mechanisms," Discover Computing, vol. 28, no. 1, May 2025, Art. no. 87.
M. Li, P. Yu, and Y. Shen, "A spatial and temporal transformer-based EEG emotion recognition in VR environment," Frontiers in Human Neuroscience, vol. 19, Feb. 2025, Art. no. 1517273.
M. M. Alam, M. A. Dini, D.-S. Kim, and T. Jun, "TMNet: Transformer-fused multimodal framework for emotion recognition via EEG and speech," ICT Express, vol. 11, no. 4, pp. 657–665, Aug. 2025.
L. Liu, Q. Zhao, L. Liu, Y. Qiao, and J. Gao, "A Lightweight Network Based on Multi‐Scale Convolutional Neural Network and Gated Transformer for EEG Emotion Classification," International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, vol. 38, no. 4, July 2025, Art. no. e70087.
Y. R. Veeranki, N. Ganapathy, R. Swaminathan, and H. F. Posada-Quintero, "Comparison of Electrodermal Activity Signal Decomposition Techniques for Emotion Recognition," IEEE Access, vol. 12, pp. 19952–19966, 2024.
D. Li, L. Xie, Z. Wang, and H. Yang, "Brain Emotion Perception Inspired EEG Emotion Recognition With Deep Reinforcement Learning," IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 9, pp. 12979–12992, Sept. 2024.
P. Gao, X. Zheng, T. Wang, and Y. Zhang, "Graph Convolutional Neural Network Based Emotion Recognition with Brain Functional Connectivity Network," International Journal of Crowd Science, vol. 8, no. 4, pp. 195–204, Sept. 2024.
S. Banik, H. Kumar, N. Ganapathy, and R. Swaminathan, "Assessment of Emotion Elicitation Using Multimodal Physiological Sensors and Phase Synchronization," IEEE Sensors Letters, vol. 8, no. 8, pp. 1–4, Aug. 2024.
S. Dai et al., "Contrastive Learning of EEG Representation of Brain Area for Emotion Recognition," IEEE Transactions on Instrumentation and Measurement, vol. 74, pp. 1–13, 2025.
Z. Cai, H. Gao, M. Wu, J. Li, and C. Liu, "A Unified Physiological Signal Interaction Network for Cross-Dataset Emotion Recognition," IEEE Transactions on Cognitive and Developmental Systems, vol. 17, no. 6, pp. 1447–1460, Dec. 2025.
X. Zhou, D. Huang, X. Peng, and L. Yin, "miMamba: EEG-Based Emotion Recognition With Multi-Scale Inverted Mamba Models," IEEE Transactions on Affective Computing, vol. 16, no. 4, pp. 3266–3278, Oct. 2025.
L. Qiu, Z. Ying, X. Song, W. Feng, C. Zhou, and J. Pan, "MTADA: A Multi-Task Adversarial Domain Adaptation Network for EEG-Based Cross-Subject Emotion Recognition," IEEE Transactions on Affective Computing, vol. 16, no. 4, pp. 3354–3368, Oct. 2025.
Y. Wang et al., "Hierarchical Transformer With Auxiliary Learning for Subject-Independent Respiration Emotion Recognition," IEEE Sensors Journal, vol. 25, no. 16, pp. 31290–31301, Aug. 2025.
S. Koelstra et al., "DEAP: A Database for Emotion Analysis ;Using Physiological Signals," IEEE Transactions on Affective Computing, vol. 3, no. 1, pp. 18–31, Jan. 2012.
S. Koelstra, "DEAP: A Dataset for Emotion Analysis using Physiological and Audiovisual Signals," 2011. https://www.eecs.qmul.ac.uk/mmv/datasets/deap/.
Downloads
How to Cite
License
Copyright (c) 2026 Vinod Kokitkar, Anand Ghuli
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
