NeuroFusion-Multimodal Emotion Recognition using EEG and Deep Learning

    The proposed NeuroFusion system presents an effective approach for emotion recognition using EEG signals by leveraging deep learning techniques. The integration of preprocessing, feature extraction, and classification enables the model to capture complex patterns in brain activity and achieve higher accuracy compared to traditional methods. The experimental results demonstrate that the proposed model outperforms conventional machine learning algorithms in terms of classification performance. The use of deep learning allows the system to learn both temporal and spatial features, resulting in improved prediction accuracy. Although the model shows promising results, challenges such as variability in EEG signals and computational complexity still exist. Future work can focus on optimizing the model for real-time applications and improving generalization across different datasets. The implementation of the proposed system is made publicly available to support reproducibility and further research in the field of emotion recognition.   The implementation and source code of the proposed system are available at: https://github.com/apex-parzival/NeuroFusion.git  

[1]     J. A. Miranda-Correa, M. K. Abadi, N. Sebe, and I. Patras, “AMIGOS: a dataset for affect, personality and mood research on individuals and groups,” IEEE Transactions on Affective Computing, vol. 12, no. 2, pp. 479–493, Nov. 2018, doi: 10.1109/taffc.2018.2884461. [2]     P. Zhong, D. Wang, and C. Miao, “EEG-Based emotion recognition using regularized graph neural networks,” IEEE Transactions on Affective Computing, vol. 13, no. 3, pp. 1290–1301, May 2020, doi: 10.1109/taffc.2020.2994159. [3]     M. P. Kalashami, M. M. Pedram, and H. Sadr, “EEG feature extraction and data augmentation in emotion recognition,” Computational Intelligence and Neuroscience, vol. 2022, pp. 1–16, Mar. 2022, doi: 10.1155/2022/7028517. [4]     D. Saraswat et al., “Explainable AI for Healthcare 5.0: Opportunities and Challenges,” IEEE Access, vol. 10, pp. 84486–84517, Jan. 2022, doi: 10.1109/access.2022.3197671. [5]     J. Xie et al., “A Transformer-Based approach combining deep learning network and Spatial-Temporal information for raw EEG classification,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30, pp. 2126–2136, Jan. 2022, doi: 10.1109/tnsre.2022.3194600. [6]     T. N. Alotaiby, S. A. Alshebeili, F. M. Alotaibi, and S. R. Alrshoud, “Epileptic seizure prediction using CSP and LDA for scalp EEG signals,” Computational Intelligence and Neuroscience, vol. 2017, pp. 1–11, Jan. 2017, doi: 10.1155/2017/1240323. [7]     S. Sakhavi, C. Guan, and S. Yan, “Learning temporal information for Brain-Computer interface using convolutional neural networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 11, pp. 5619–5629, Mar. 2018, doi: 10.1109/tnnls.2018.2789927. [8]     R. W. Picard, “Affective Computing,” MIT Press, 1997. [9]     S. Koelstra et al., “DEAP Dataset for Emotion Analysis,” IEEE Transactions, 2012.