Cross-Dataset Variability Problem in EEG Decoding With Deep Learning

• Published in: Frontiers in human neuroscience Vol. 14; p. 103
• Main Authors: Xu, Lichao, Xu, Minpeng, Ke, Yufeng, An, Xingwei, Liu, Shuang, Ming, Dong
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 21.04.2020; Frontiers Media S.A
• Subjects: Algorithms; brain-computer interface; Classification; cross-dataset variability; cross-subject variability; Datasets; Deep learning; EEG; Eigenvalues; Electroencephalography; Geometry; Human Neuroscience; Interfaces; Internet; Machine learning; Medical imaging; Signal processing; transfer learning; deep learning; transfer learning; cross-subject variability; cross-dataset variability; EEG; brain-computer interface
• DOI: 10.3389/fnhum.2020.00103
• ISSN: 1662-5161

Cross-subject variability problems hinder practical usages of Brain-Computer Interfaces. Recently, deep learning has been introduced into the BCI community due to its better generalization and feature representation abilities. However, most studies currently only have validated deep learning models for single datasets, and the generalization ability for other datasets still needs to be further verified. In this paper, we validated deep learning models for eight MI datasets and demonstrated that the cross-dataset variability problem weakened the generalization ability of models. To alleviate the impact of cross-dataset variability, we proposed an online pre-alignment strategy for aligning the EEG distributions of different subjects before training and inference processes. The results of this study show that deep learning models with online pre-alignment strategies could significantly improve the generalization ability across datasets without any additional calibration data.