Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BDAN: Mitigating Temporal Difference Across Electrodes in Cross-Subject Motor Imagery Classification via Generative Bridging Domain (2404.10494v1)

Published 16 Apr 2024 in cs.HC and cs.LG

Abstract: Because of "the non-repeatability of the experiment settings and conditions" and "the variability of brain patterns among subjects", the data distributions across sessions and electrodes are different in cross-subject motor imagery (MI) studies, eventually reducing the performance of the classification model. Systematically summarised based on the existing studies, a novel temporal-electrode data distribution problem is investigated under both intra-subject and inter-subject scenarios in this paper. Based on the presented issue, a novel bridging domain adaptation network (BDAN) is proposed, aiming to minimise the data distribution difference across sessions in the aspect of the electrode, thus improving and enhancing model performance. In the proposed BDAN, deep features of all the EEG data are extracted via a specially designed spatial feature extractor. With the obtained spatio-temporal features, a special generative bridging domain is established, bridging the data from all the subjects across sessions. The difference across sessions and electrodes is then minimized using the customized bridging loss functions, and the known knowledge is automatically transferred through the constructed bridging domain. To show the effectiveness of the proposed BDAN, comparison experiments and ablation studies are conducted on a public EEG dataset. The overall comparison results demonstrate the superior performance of the proposed BDAN compared with the other advanced deep learning and domain adaptation methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. A. M. Azab, L. Mihaylova, K. K. Ang, and M. Arvaneh, “Weighted transfer learning for improving motor imagery-based brain–computer interface,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, no. 7, pp. 1352–1359, 2019.
  2. Y. Cai, Q. She, J. Ji, Y. Ma, J. Zhang, and Y. Zhang, “Motor imagery EEG decoding using manifold embedded transfer learning,” Journal of Neuroscience Methods, vol. 370, p. 109489, 2022.
  3. M. C. Camacho, A. N. Nielsen, D. Balser, E. Furtado, D. C. Steinberger, L. Fruchtman, J. P. Culver, C. M. Sylvester, and D. M. Barch, “Large-scale encoding of emotion concepts becomes increasingly similar between individuals from childhood to adolescence,” Nature Neuroscience, pp. 1–11, 2023.
  4. H. Chen, C. Li, M. Mafarja, A. A. Heidari, Y. Chen, and Z. Cai, “Slime mould algorithm: A comprehensive review of recent variants and applications,” International Journal of Systems Science, vol. 54, no. 1, pp. 204–235, 2023.
  5. P. Chen, Z. Gao, M. Yin, J. Wu, K. Ma, and C. Grebogi, “Multiattention adaptation network for motor imagery recognition,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 52, no. 8, pp. 5127–5139, 2021.
  6. Y. Chen, R. Yang, M. Huang, Z. Wang, and X. Liu, “Single-source to single-target cross-subject motor imagery classification based on multisubdomain adaptation network,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30, pp. 1992–2002, 2022.
  7. Z. Chen, R. Yang, M. Huang, Z. Wang, and X. Liu, “Electrode domain adaptation network: Minimizing the difference across electrodes in single-source to single-target motor imagery classification,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2023.
  8. M. Cheng, Z. Lu, and H. Wang, “Regularized common spatial patterns with subject-to-subject transfer of EEG signals,” Cognitive Neurodynamics, vol. 11, pp. 173–181, 2017.
  9. S.-S. Dong, Y.-G. Li, and L. An, “Optimal strictly stealthy attacks in cyber-physical systems with multiple channels under the energy constraint,” International Journal of Systems Science, vol. 54, no. 13, pp. 2608–2625, 2023.
  10. G. Dornhege, B. Blankertz, G. Curio, and K.-R. Muller, “Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms,” IEEE Transactions on Biomedical Engineering, vol. 51, no. 6, pp. 993–1002, 2004.
  11. W. Hang, W. Feng, R. Du, S. Liang, Y. Chen, Q. Wang, and X. Liu, “Cross-subject EEG signal recognition using deep domain adaptation network,” IEEE Access, vol. 7, pp. 128 273–128 282, 2019.
  12. H. He and D. Wu, “Transfer learning for brain–computer interfaces: A Euclidean space data alignment approach,” IEEE Transactions on Biomedical Engineering, vol. 67, no. 2, pp. 399–410, 2019.
  13. X. Hong, Q. Zheng, L. Liu, P. Chen, K. Ma, Z. Gao, and Y. Zheng, “Dynamic joint domain adaptation network for motor imagery classification,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 29, pp. 556–565, 2021.
  14. R. Hu, X. Zhou, Z. Xu, Z. Liao, H. Wu, H. Qu, and Z.-R. Tang, “Cross-subject federated transfer learning with quanvolutional layer for motor imagery classification,” in 2021 China Automation Congress (CAC).   IEEE, 2021, pp. 5736–5741.
  15. V. J. Lawhern, A. J. Solon, N. R. Waytowich, S. M. Gordon, C. P. Hung, and B. J. Lance, “EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces,” Journal of Neural Engineering, vol. 15, no. 5, p. 056013, 2018.
  16. P. Li, Y. Meng, M. Li, X. Xuan, S. Xu, and H. Li, “An electroencephalography electrode based on a few-layer graphene/Tio2 nanotube nanoarchitecture for application in robot arm control,” Sensors and Actuators A: Physical, vol. 354, p. 114293, 2023.
  17. X. Li, X. Tang, S. Qiu, X. Deng, H. Wang, and Y. Tian, “Subdomain adversarial network for motor imagery EEG classification using graph data,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2023.
  18. Y. Liang and Y. Ma, “Calibrating EEG features in motor imagery classification tasks with a small amount of current data using multisource fusion transfer learning,” Biomedical Signal Processing and Control, vol. 62, p. 102101, 2020.
  19. J. Liao, H.-K. Lam, S. Gulati, and B. Hayee, “Improved computer-aided diagnosis system for nonerosive reflux disease using contrastive self-supervised learning with transfer learning,” International Journal of Network Dynamics and Intelligence, 2023.
  20. C. Liu, R. J. Downey, Y. Mu, N. Richer, J. Hwang, V. A. Shah, S. D. Sato, D. J. Clark, C. J. Hass, T. M. Manini et al., “Comparison of EEG source localization using simplified and anatomically accurate head models in younger and older adults,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023.
  21. W. Liu, C. Guo, and C. Gao, “A cross-session motor imagery classification method based on Riemannian geometry and deep domain adaptation,” Expert Systems with Applications, vol. 237, p. 121612, 2024.
  22. S. Ma and Y. Li, “Adaptive fuzzy fault-tolerant control for active seat suspension systems with full-state constraints,” Systems Science & Control Engineering, vol. 11, no. 1, p. 2153391, 2023.
  23. M. Naeem, C. Brunner, R. Leeb, B. Graimann, and G. Pfurtscheller, “Seperability of four-class motor imagery data using independent components analysis,” Journal of Neural Engineering, vol. 3, no. 3, p. 208, 2006.
  24. O. Özdenizci, Y. Wang, T. Koike-Akino, and D. Erdoğmuş,“Learning invariant representations from EEG via adversarial inference,” IEEE Access, vol. 8, pp. 27 074–27 085, 2020.
  25. S. Pérez-Velasco, E. Santamaria-Vazquez, V. Martinez-Cagigal, D. Marcos-Martinez, and R. Hornero, “EEGSym: Overcoming inter-subject variability in motor imagery based BCIs with deep learning,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30, pp. 1766–1775, 2022.
  26. C. Qin, R. Yang, M. Huang, W. Liu, and Z. Wang, “Spatial variation generation algorithm for motor imagery data augmentation: Increasing the density of sample vicinity,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023.
  27. X. Qin, L. Du, X. Jiao, J. Wang, S. Tong, T. Yuan, and J. Sun, “Evaluation of brain source localization methods based on test-retest reliability with multiple session EEG data,” IEEE Transactions on Biomedical Engineering, 2023.
  28. T. P. Reber, S. Mackay, M. Bausch, M. S. Kehl, V. Borger, R. Surges, and F. Mormann, “Single-neuron mechanisms of neural adaptation in the human temporal lobe,” Nature Communications, vol. 14, no. 1, p. 2496, 2023.
  29. R. T. Schirrmeister, J. T. Springenberg, L. D. J. Fiederer, M. Glasstetter, K. Eggensperger, M. Tangermann, F. Hutter, W. Burgard, and T. Ball, “Deep learning with convolutional neural networks for EEG decoding and visualization,” Human Brain Mapping, vol. 38, no. 11, pp. 5391–5420, 2017.
  30. Q. She, T. Chen, F. Fang, J. Zhang, Y. Gao, and Y. Zhang, “Improved domain adaptation network based on Wasserstein distance for motor imagery EEG classification,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, pp. 1137–1148, 2023.
  31. B. Shi, Z. Yue, S. Yin, W. Wang, H. Yu, Z. Huang, and J. Wang, “Adaptive binary multi-objective harmony search algorithm for channel selection and cross-subject generalization in motor imagery-based BCI,” Journal of Neural Engineering, vol. 19, no. 4, p. 046022, 2022.
  32. B. P. Staresina, J. Niediek, V. Borger, R. Surges, and F. Mormann, “How coupled slow oscillations, spindles and ripples coordinate neuronal processing and communication during human sleep,” Nature Neuroscience, vol. 26, no. 8, pp. 1429–1437, 2023.
  33. X. Tang, X. Li, W. Li, B. Hao, Y. Xie, and X. Dang, “Transfer learning: rotation alignment with Riemannian mean for brain-computer interfaces and wheelchair control,” IEEE Transactions on Cognitive and Developmental Systems, 2023.
  34. E. Tzeng, J. Hoffman, N. Zhang, K. Saenko, and T. Darrell, “Deep domain confusion: Maximizing for domain invariance,” ArXiv Preprint ArXiv:1412.3474, 2014.
  35. Y. Wang, W. Liu, C. Wang, F. Fadzil, S. Lauria, and X. Liu, “A novel multi-objective optimization approach with flexible operation planning strategy for truck scheduling,” International Journal of Network Dynamics and Intelligence, 2023.
  36. Y. Xu, X. Long, J. Feng, and P. Gong, “Interacting spiral wave patterns underlie complex brain dynamics and are related to cognitive processing,” Nature Human Behaviour, pp. 1–20, 2023.
  37. T. Zhang, Q. Liu, J. Liu, Z. Wang, and H. Li, “Multiple-bipartite consensus for networked Lagrangian systems without using neighbours’ velocity information in the directed graph,” Systems Science & Control Engineering, vol. 11, no. 1, p. 2210185, 2023.
  38. X. Zhang, Z. Miao, C. Menon, Y. Zheng, M. Zhao, and D. Ming, “Priming cross-session motor imagery classification with a universal deep domain adaptation framework,” Neurocomputing, vol. 556, p. 126659, 2023.
  39. H. Zhao, Q. Zheng, K. Ma, H. Li, and Y. Zheng, “Deep representation-based domain adaptation for nonstationary EEG classification,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp. 535–545, 2020.
  40. X. Zhao, J. Zhao, C. Liu, and W. Cai, “Deep neural network with joint distribution matching for cross-subject motor imagery brain-computer interfaces,” BioMed Research International, vol. 2020, 2020.
  41. M. Zheng, B. Yang, and Y. Xie, “EEG classification across sessions and across subjects through transfer learning in motor imagery-based brain-machine interface system,” Medical & Biological Engineering & Computing, vol. 58, pp. 1515–1528, 2020.
  42. X.-C. Zhong, Q. Wang, D. Liu, J.-X. Liao, R. Yang, S. Duan, G. Ding, and J. Sun, “A deep domain adaptation framework with correlation alignment for EEG-based motor imagery classification,” Computers in Biology and Medicine, vol. 163, p. 107235, 2023.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets