AUTHOR=Xu Lichao , Xu Minpeng , Ke Yufeng , An Xingwei , Liu Shuang , Ming Dong 

TITLE=Cross-Dataset Variability Problem in EEG Decoding With Deep Learning

JOURNAL=Frontiers in Human Neuroscience

VOLUME=Volume 14 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2020.00103

DOI=10.3389/fnhum.2020.00103

ISSN=1662-5161

ABSTRACT=Cross-subject variability problem hinders practical usages of Brain-Computer Interfaces. Recently, deep learning has been introduced into the BCI community since its better generalization and feature representation abilities. However, currently most studies have only validated deep learning models on a single dataset and the generalization ability on other datasets still needs to be further verified. In this paper, we validated deep learning models on 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 strategy could significantly improve the generalization ability across datasets without any additional calibration data.