Improving inter-session performance via relevant session-transfer for multi-session motor imagery classification.

Motor imagery (MI)-based brain-computer interfaces (BCIs) using electroencephalography (EEG) have found practical applications in external device control. However, the non-stationary nature of EEG signals remains to obstruct BCI performance across multiple sessions, even for the same user. In this study, we aim to address the impact of non-stationarity, also known as inter-session variability, on multi-session MI classification performance by introducing a novel approach, the relevant session-transfer (RST) method. Leveraging the cosine similarity as a benchmark, the RST method transfers relevant EEG data from the previous session to the current one. The effectiveness of the proposed RST method was investigated through performance comparisons with the self-calibrating method, which uses only the data from the current session, and the whole-session transfer method, which utilizes data from all prior sessions. We validated the effectiveness of these methods using two datasets: a large MI public dataset (Shu Dataset) and our own dataset of gait-related MI, which includes both healthy participants and individuals with spinal cord injuries. Our experimental results revealed that the proposed RST method leads to a 2.29 % improvement (p < 0.001) in the Shu Dataset and up to a 6.37 % improvement in our dataset when compared to the self-calibrating method. Moreover, our method surpassed the performance of the recent highest-performing method that utilized the Shu Dataset, providing further support for the efficacy of the RST method in improving multi-session MI classification performance. Consequently, our findings confirm that the proposed RST method can improve classification performance across multiple sessions in practical MI-BCIs.

Differentiating changes in movement-related EEG response induced by transcranial direct current stimulation using convolutional neural network.

Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique that can modulate neuronal excitability and induce brain plasticity. Although tDCS has been studied with various methods, more research is needed on the movement-related electroencephalography (EEG) changes induced by tDCS. Moreover, it is necessary to investigate whether these changes can be distinguished through a convolutional neural network (CNN)-based classifier. In this study, we measured the EEG during the voluntary foot-tapping task of participants who received tDCS or sham stimulation and evaluated the classification performance. As a result, significantly higher classification accuracy was shown using the ß band (88.7±9.4%), which is more related to motor function, than in the other bands (71.4±10.6% for δ band, 64.1±13.4% for θ band, and 65.7±10.9% for α band). Consequently, EEG changes during the voluntary foot-tapping task induced by tDCS appeared large in the ß band, implying that it is effective in classifying whether tDCS was given or not, and plays an important role in identifying the effect of tDCS.