AN EFFICIENT TRANSFORMER-BASED APPROACH FOR EEG SIGNAL ENCODING
Keywords
DOI:
https://doi.org/10.34238/tnu-jst.15633Abstract
Electroencephalography signal encoding is a central task in the field of brain-computer interfaces, aiming to learn an effective representation space for image recognition and reconstruction tasks. However, brain signals are characterized by high noise, significant variability, and limited labeled data, which make feature extraction with traditional deep neural networks challenging and heavily dependent on labeled data. To address these challenges, this study proposes a new signal-encoding method based on the Transformer architecture and contrastive learning techniques. Specifically, the model utilizes the multi-head self-attention mechanism to comprehensively capture global dependencies within time-series data. At the same time, it integrates the Triplet Semi-Hard loss function and a semi-hard mining strategy to optimize a highly discriminative representation space without requiring pre-training on external data. Experimental results on the ThoughtViz dataset demonstrate the effectiveness of this method, achieving a clustering accuracy of 0.75, which significantly outperforms current state-of-the-art models. This research enhances the quality of image reconstruction from brain signals and promotes the potential for practical application in non-invasive communication support systems.Downloads
References
H. Yadav and S. Maini, “Decoding brain signals: A comprehensive review of EEG-Based BCI paradigms, signal processing and applications,” Comput. Biol. Med., vol. 196, Pt. C, 2025, doi: 10.1016/j.compbiomed.2025.110937.
L. Hallal, J. Rhinelander, R. Venkat, and A. Newman, “Efficient Feature Extraction for EEG-Based Classification: A Comparative Review of Deep Learning Models,” AI, vol. 7, no. 2, 2026, doi: 10.3390/ai7020050.
P. Tirupattur, Y. S. Rawat, C. Spampinato, and M. Shah, "ThoughtViz: Visualizing Human Thoughts Using Generative Adversarial Network," In Proceedings of the 26th ACM International Conference on Multimedia (MM '18), 2018, pp. 950-958, doi: 10.1145/3240508.3240641.
P. Singh, P. Pandey, K. Miyapuram, and S. Raman, "EEG2Image: Image Reconstruction from EEG Brain Signals," In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10096587.
F. Schroff, D. Kalenichenko, and J. Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering," In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 815-823, doi: 10.1109/CVPR.2015.7298682.
P. Singh, D. Dalal, G. Vashishtha, K. Miyapuram, and S. Raman, "Learning Robust Deep Visual Representations from EEG Brain Recordings," in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 7553-7562, doi: 10.1109/WACV57701.2024.00738.
D. Li, C. Wei, S. Li, J. Zou, and Q. Liu, "Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion," in Advances in Neural Information Processing Systems 37 (NeurIPS 2024), 2024, doi: 10.52202/079017-3266.
X. Liu, F. Zhang, Z. Hou, L. Mian, Z. Wang, J. Zhang, and J. Tang, "Self-Supervised Learning: Generative or Contrastive," IEEE Transactions on Knowledge and Data Engineering 35, no. 1, pp. 857-876, 2021, doi: 10.1109/TKDE.2021.3090866.
T. Gao, X. Yao, and D. Chen, "SimCSE: Simple Contrastive Learning of Sentence Embeddings," in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021, pp. 6894-6910.
A. Baevski, W.-N. Hsu, Q. Xu, A. Babu, J. Gu, and M. Auli, "data2vec: A General Framework for Self-Supervised Learning in Speech, Vision and Language," In International Conference on Machine Learning (ICML), PMLR, 2022, pp. 1298-1312.
T. Lin, Y. Wang, X. Liu, and X. Qiu, "A Survey of Transformers," AI Open, vol. 3, pp. 111-132, 2022. doi: 10.1016/j.aiopen.2022.10.001.
W.-B. Jiang, L.-M. Zhao, and B.-L. Lu, "Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI," In Proceedings of the International Conference on Learning Representations (ICLR), 2024, pp. 16405-16426.
G. Wang, W. Liu, Y. He, C. Xu, L. Ma, and H. Li, "EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals," In Advances in Neural Information Processing Systems 37, 2024, pp. 39249-39280, doi: 10.52202/079017-1239.
O. Russakovsky, J. Deng, H. Su, et al., "ImageNet Large Scale Visual Recognition Challenge," International Journal of Computer Vision, vol. 115, no. 3, pp. 211-252, 2015.
H. W. Kuhn, "The Hungarian Method for the Assignment Problem," Naval Research Logistics Quarterly, vol. 2, no. 1-2, pp. 83-97, 1955, doi: 10.1002/nav.3800020109.
L. Van der Maaten and G. Hinton, "Visualizing Data Using t-SNE," Journal of Machine Learning Research, vol. 9, no. 86, pp. 2579-2605, 2008.
