Discrepancy between inter- and intra-subject variability in EEG-based motor imagery brain-computer interface: Evidence from multiple perspectives

IntroductionInter- and intra-subject variability are caused by the variability of the psychological and neurophysiological factors over time and across subjects. In the application of in Brain-Computer Interfaces (BCI), the existence of inter- and intra-subject variability reduced the generalization ability of machine learning models seriously, which further limited the use of BCI in real life. Although many transfer learning methods can compensate for the inter- and intra-subject variability to some extent, there is still a lack of clear understanding about the change of feature distribution between the cross-subject and cross-session electroencephalography (EEG) signal. MethodsTo investigate this issue, an online platform for motor-imagery BCI decoding has been built in this work. The EEG signal from both the multi-subject (Exp1) and multi-session (Exp2) experiments has been analyzed from multiple perspectives. ResultsFirstly we found that with the similar variability of classification results, the time-frequency response of the EEG signal within-subject in Exp2 is more consistent than cross-subject results in Exp1. Secondly, the standard deviation of the common spatial pattern (CSP) feature has a significant difference between Exp1 and Exp2. Thirdly, for model training, different strategies for the training sample selection should be applied for the cross-subject and cross-session tasks. DiscussionAll these findings have deepened the understanding of inter- and intra-subject variability. They can also guide practice for the new transfer learning methods development in EEG-based BCI. In addition, these results also proved that BCI inefficiency was not caused by the subject's unable to generate the event-related desynchronization/synchronization (ERD/ERS) signal during the motor imagery.

Automated summary

In this study, an online platform for motor-imagery BCI decoding was built to analyze EEG signals from both multi-subject and multi-session experiments. The findings revealed that the time-frequency response of within-subject EEG signals in multi-session experiments was more consistent compared to cross-subject results in multi-subject experiments. Additionally, different strategies for training sample selection should be applied for cross-subject and cross-session tasks. These findings deepen our understanding of inter- and intra-subject variability and can guide the development of new transfer learning methods in EEG-based BCI.