Citation :

Raju Ramakrishna Gondkar, Surekha R Gondkar, Ramkumar Sivasakthivel, R. Gobinath, Manikandan Rajagopal, "A Deep Learning-Based BCI System for Emotion Classification Using EEG Signals," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 1, pp. 65-84, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I1P105

Abstract

Electroencephalography-based Brain-Computer Interfacing (EEG-BCI) technologies allow for effortless interaction between external hardware and the human brain through monitoring its electric signals. These systems rely on EEG recordings, which provide non-invasive and real-time neural information through electrodes placed on the scalp. To advance emotion recognizing efficiency and accuracy, this study proposes a deep learning-based method that can extract valuable temporal and spatial information from EEG signals. The proposed model includes the use of a Graph Convolution Network (GCN) for learning spatial relationships between different EEG channels to model the data in graph form and gain features through that modelling. A Convolutional Autoencoder (CAE) is then used to compress data to low dimensions and to reconstruct it so that major features are not ignored. Furthermore, the model uses an Attention-based Bidirectional Gated Recurrent Unit (ABiGRU) for temporal classification, which can emphasize the most important time steps in both backwards and forward directions. Two standard datasets are employed to test the developed approach. The DEAP dataset is used for emotion recognition with a binary response, and SEED is used with multi-class classification. The model attains great results of 98.12% accuracy on DEAP and 97.58% on SEED datasets. The very high performances show the efficacy of the model for decoding emotional states from EEG signals and very strong potential for real-time emotion recognition in affective computing and BCI.

Keywords

Graph Convolutional Network, Convolutional Autoencoder, Attention-Based Bidirectional Gated Recurrent Unit, DEAP, SEED.

References

[1] Yilu Xu et al., “Improved Motor Imagery Training for Subject Self-Modulations in EEG-based Brain-Computer Interfaces,” Frontiers in Human Neurosciences, vol. 18, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Yanxiao Chen et al., “Several Inaccurate or Erroneous Conceptions and Misleading Propaganda about Brain-Computer Interfaces,” Frontiers in Human Neuroscience, vol. 18, pp. 1-12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Walaa H. Elashmawi et al., “A Comprehensive Review on Brain-Computer Interface (BCI)-based Machine and Deep Learning Algorithms for Stroke Rehabilitation,” Applied Sciences, vol. 14, no. 14, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Chirag Ahuja, and Divyashikha Sethia, “Harnessing Few-Shot Learning for EEG Signal Classification: A Survey of State-of-the-Art Techniques and Future Directions,” Frontiers in Human Neuroscience, vol. 18, pp. 1-33, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Dominik Klepl, Min Wu, and Fei He, “Graph Neural Network-based EEG Classification: A Survey,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 32, pp. 493-503, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Xueyuan Xu et al., “Embedded EEG Features Selections for Multi-Dimensional Emotions Recognitions via Local and Global Labels Relevance,” IEEE Transaction on Neural System and Rehabilitation Engineering, vol. 32, pp. 514-526, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Ildar Rakhmatulin et al., “Exploring Convolutional Neural Network Architectures for EEG Feature Extraction,” Sensors, vol. 24, no. 3, pp. 1-39, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Jagdeep Rahul et al., “A Systematic Review of EEG based Automated Schizophrenia Classification through Machine Learning and Deep Learning,” Frontiers in Human Neuroscience, vol. 18, pp. 1-12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Yuri Gordienko et al., “Effect of Natural and Synthetic Noise Data Augmentation on Physical Action Classification by Brain-Computer Interface and Deep Learning,” Frontiers in Neuroinformatics, vol. 19, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Poraneepan Tantawanich et al., “A Systematic Review of Bimanual Motor Coordination in Brain-Computer Interface,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 33, pp. 266-285, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Kosmas Glavas et al., “Brain-Computer Interface Controlled Drones: A Systematic Review,” IEEE Access, vol. 12, pp. 61279-61300, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Yingyi Qiu, Han Liu, and Mengyuan Zhao, “A Review of Brain-Computer Interface-based Language Decoding: from Signal Interpretation to Intelligent Communication,” Applied Sciences, vol. 15, no. 1, pp. 1-31, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Rand Alibrahim, and Heba Kurdi, “GANN: EEG-based Emotion Classification using Context-Aware Gated Attention Neural Network,” Procedia Computer Science, vol. 241, pp. 234-241, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Miguel Alejandro Blanco-Rios et al., “Real-Time EEG-based Emotions Recognitions for Neuro-Humanities: Perspective from Principal Components Analyses and Trees-based Algorithm,” Frontier in Human Neurosciences, vol. 18, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Wei Chen et al., “EEG-based Emotion Recognition using Graph Convolutional Neural Network with Dual Attention Mechanism,” Frontiers in Computational Neuroscience, vol. 18, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Khadidja Henni et al., “An Effective Deep Neural Networks Architecture for EEG-based Recognitions of Emotion,” IEEE Access, vol. 13, pp. 4487-4498, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Yuxiao Du et al., “MES-CTNet: A Novel Capsule Transformer Network base on a Multi-Domain Feature Map for Electroencephalogram-based Emotion Recognition,” Brain Sciences, vol. 14, no. 4, pp. 1-20, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Wenxu Wang et al., “A Random Forests Weight and 4-Dimension Convolution Recurrent Neural Networks for EEG based Emotions Recognitions,” IEEE Access, vol. 12, pp. 39549-39563, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Kasthuri Devarajan, Suresh Ponnan, and Sundresan 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, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Khushboo Singh, Mitul Kumar Ahirwal, and Manish Pandey, “Selected Channel based Multiclass Emotion Classification from Wearable Human Brain EEG Signal,” Measurement: Sensors, vol. 39, pp. 1-7, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Songül Erdem Güler, and Fatma Patlar Akbulut, “Multimodal Emotion Recognition: Emotion Classification through the Integration of EEG and Facial Expressions,” IEEE Access, vol. 13, pp. 24587-24603, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Longxin Yao et al., “High-Accuracy Classification of Multiple Distinct Human Emotions using EEG Differential Entropy Features and ResNet18,” Applied Sciences, vol. 14, no. 14, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Wei Gan et al., “TSF-MDD: A Deep Learning Approach for Electroencephalography-based Diagnoses of Major Depressive Disorders with Temporal-Spatial-Frequency Features Fusions,” Bioengineering, vol. 12, no. 2, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Nabil I. Ajali-Hernández, and Carlos M. Travieso-González, “Emotions for Everyone: A Low-Cost, High-Accuracy Method for Emotion Classification,” Cognitive Computation, vol. 17, no. 3, pp. 1-15, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[25] F. Kebire Bardak, M. Nuri Seyman, and Feyzullah Temurtaş, “Adaptive Neuro-Fuzzy based Hybrid Classifications Model for Emotions Recognitions from EEG Signal,” Neural Computing and Application, vol. 36, no. 16, pp. 9189-9202, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Xiangyu Ju et al., “Domain Adversarial Learning with Multiple Adversarial Tasks for EEG Emotion Recognition,” Expert Systems with Applications, vol. 266, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Wei Lu et al., “Domains Adaptations Spatial Features Perceptions Neural Networks for Cross-Subjects EEG Emotions Recognitions,” Frontiers in Human Neurosciences, vol. 18, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Sheetal Patil et al., “Review on Music Emotion Analysis using Machine Learning: Technologies, Methods, Datasets, and Challenges,” Discover Applied Sciences, vol. 7, no. 7, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Asad Ur Rehman et al., “Advanced EEG Signal Processing and Deep Q-Learning for Accurate Student Attention Monitoring,” IEEE Access, vol. 13, pp. 47260-47270, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Jiange Jiang et al., “Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 3108-3122, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Yuxia Wang et al., “Combining EEG Features and Convolutional Autoencoder for Neonatal Seizure Detection,” International Journal of Neural Systems, vol. 34, no. 8, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Nima Khodadadi et al., “Predicting Normalized Difference Vegetation Index using a Deep Attention Network with Bidirectional GRU: A Hybrid Parametric Optimization Approach,” International Journal of Data Science and Analytics, vol. 20, no. 4, pp. 3119-3146, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Xiuzhen Yao et al., “Emotion Classification based on Transformer and CNN for EEG Spatial-Temporal Feature Learning,” Brain Sciences, vol. 14, no. 3, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]