EEG 기반 SPD-Net에서 리만 프로크루스테스 분석에 대한 연구 = Research of Riemannian Procrustes Analysis on EEG Based SPD-Net

다국어 초록 (Multilingual Abstract)

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 natu- rally 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 archi- tecture 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 ex- perimental 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.

참고문헌 (Reference)

1 Congedo M, "Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review" 4 (4): 155-174, 2017

2 Brooks D, "Riemannian batch normalization for SPD neural networks" 32 : 1-10, 2019

3 Yger F, "Riemannian approaches in brain-computer interfaces : a review" 25 (25): 1753-1762, 2016

4 Rodrigues PLC, "Riemannian Procrustes analysis : transfer learning for brain–computer interfaces" 66 (66): 2390-2401, 2018

5 Graf AB, "Prototype classification : insights from machine learning" 21 (21): 272-300, 2009

6 Gower JC, "Procrustes problems" Oxford University Press 1-10, 2004

7 Bhatia R, "Positive definite matrices" Princeton University Press 1-200, 2009

8 Flamary R, "Optimal transport for domain adaptation" 39 (39): 1853-1865, 2016

9 Cho H, "EEG datasets for motor imagery brain-computer interface" 6 (6): gix034-, 2017

10 Duan RN, "Differential entropy feature for EEG-based emotion classification" 81-84, 2013

11 Koelstra S, "DEAP : A database for emo-tion analysis using physiological signals" 3 (3): 18-31, 2011

12 Kothe CA, "BCILAB : a platform for brain–computer interface development" 10 (10): 056014-, 2013

13 Kim BH, "A discriminative SPD feature learning approach on Riemannian manifolds for EEG classification" 143 : 109751-, 2023

14 Huang Z, "A Riemannian network for SPD matrix learning" 31 (31): 1-10, 2017

15 권다은 ; 황민주 ; 권지현 ; 신예은 ; 안민규, "A Comparative Analysis of Motor Imagery, Execution, and Observation for Motor Imagery-based Brain-Computer Interface" 43 (43): 375-381, 2022

16 Rodrigues PLC, ""When does it work?" : An exploratory analysis of transfer learning for BCI" 1-6, 2019