대한의용생체공학회:의공학회지 (Journal of Biomedical Engineering Research)

  • 제45권4호
  • /
  • Pages.179-186
  • /
  • 2024
  • /
  • 1229-0807(pISSN)
  • /
  • 2288-9396(eISSN)
대한의용생체공학회 (The Korean Society of Medical and Biological Engineering)
권호 표지
DOI QR코드

DOI QR Code

EEG 기반 SPD-Net에서 리만 프로크루스테스 분석에 대한 연구

Research of Riemannian Procrustes Analysis on EEG Based SPD-Net

  • 방윤석 (인하대학교 전기컴퓨터공학과) ;
  • 김병형 (인하대학교 전기컴퓨터공학과)
  • 투고 : 2024.07.01
  • 심사 : 2024.08.14
  • 발행 : 2024.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper investigates the impact of Riemannian Procrustes Analysis (RPA) on enhancing the classification performance of SPD-Net when applied to EEG signals across different sessions and subjects. EEG signals, known for their inherent individual variability, are initially transformed into Symmetric Positive Definite (SPD) matrices, which are naturally represented on a Riemannian manifold. To mitigate the variability between sessions and subjects, we employ RPA, a method that geometrically aligns the statistical distributions of these matrices on the manifold. This alignment is designed to reduce individual differences and improve the accuracy of EEG signal classification. SPD-Net, a deep learning architecture that maintains the Riemannian structure of the data, is then used for classification. We compare its performance with the Minimum Distance to Mean (MDM) classifier, a conventional method rooted in Riemannian geometry. The experimental results demonstrate that incorporating RPA as a preprocessing step enhances the classification accuracy of SPD-Net, validating that the alignment of statistical distributions on the Riemannian manifold is an effective strategy for improving EEG-based BCI systems. These findings suggest that RPA can play a role in addressing individual variability, thereby increasing the robustness and generalization capability of EEG signal classification in practical BCI applications.

키워드

과제정보

본 연구는 인하대학교의 지원과 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원(No. 2021R1C1C2012437)과 정보통신기획평가원의 지원(RS-2023-00229074)을 받아 수행된 연구임.

참고문헌

  1. Kothe CA, Makeig S. BCILAB: a platform for brain-computer interface development. Journal of Neural Engineering. 2013;10(5):056014. 
  2. Yger F, Berar M, Lotte F. Riemannian approaches in brain-computer interfaces: a review. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2016;25(10):1753-62.  https://doi.org/10.1109/TNSRE.2016.2627016
  3. Congedo M, Barachant A, Bhatia R. Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review. Brain-Computer Interfaces. 2017;4(3):155-74.  https://doi.org/10.1080/2326263X.2017.1297192
  4. Rodrigues PLC, Jutten C, Congedo M. Riemannian Procrustes analysis: transfer learning for brain-computer interfaces. IEEE Transactions on Biomedical Engineering. 2018;66(8):2390-2401.  https://doi.org/10.1109/TBME.2018.2889705
  5. Huang Z, Van Gool L. A Riemannian network for SPD matrix learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2017;31(1):1-10. 
  6. Bhatia R. Positive definite matrices. Princeton: Princeton University Press; 2009. pp. 1-200. 
  7. Gower JC, Dijksterhuis GB. Procrustes problems. Oxford: Oxford University Press; 2004. pp. 1-10. 
  8. Duan RN, Zhu JY, Lu BL. Differential entropy feature for EEG-based emotion classification. Proceedings of the 6th International IEEE EMBS Conference on Neural Engineering. 2013;81-84. 
  9. Koelstra S, Muehl C, Soleymani M, Lee JS, Yazdani A, Ebrahimi T, Pun T, Nijholt A, Patras I. DEAP: A database for emotion analysis using physiological signals. IEEE Transactions on Affective Computing. 2011;3(1):18-31. 
  10. Cho H, Ahn M, Ahn S, Kwon M, Jun SC. EEG datasets for motor imagery brain-computer interface. GigaScience. 2017;6(7):gix034. 
  11. Graf AB, Bousquet O, Ratsch G, Scholkopf B. Prototype classification: insights from machine learning. Neural Computation. 2009;21(1):272-300.  https://doi.org/10.1162/neco.2009.01-07-443
  12. Rodrigues PLC, Congedo M, Jutten C. "When does it work?": An exploratory analysis of transfer learning for BCI. Proceedings of the BCI 2019-8th International Brain-Computer Interface Conference. 2019;1-6. 
  13. Gwon D, Hwang MJ, Kwon JH, Shin Y, Ahn MK. A Comparative Analysis of Motor Imagery, Execution, and Observation for Motor Imagery-based Brain-Computer Interface. Journal of Biomedical Engineering Research, 2022;43(6):375-381.  https://doi.org/10.9718/JBER.2022.43.6.375
  14. Kim BH, Choi JW, Lee H, Jo S. A discriminative SPD feature learning approach on Riemannian manifolds for EEG classification. Pattern Recognition. 2023;143:109751. 
  15. Brooks D, Schwander O, Barbaresco F, Schneider JY, Cord M. Riemannian batch normalization for SPD neural networks. Advances in Neural Information Processing Systems. 2019;32:1-10. 
  16. Flamary R, Courty N, Tuia D, Rakotomamonjy A. Optimal transport for domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016;39(9):1853-65