Golden subject is everyone: A subject transfer neural network for motor imagery-based brain computer interfaces

Electroencephalographic measurement of cortical activity subserving motor behavior varies among different individuals, restricting the potential of brain computer interfaces (BCIs) based on motor imagery (MI). How to deal with this variability and thereby improve the accuracy of BCI classification remains a key issue. This paper proposes a deep learning-based approach to transfer the data distribution from BCI-friendly - golden subjectsto the data from more typical BCI-illiterate users. In this work, we use the perceptual loss to align the dimensionality-reduced BCI-illiterate data with the data of golden subjects in low dimensions, by which a subject transfer neural network (STNN) is proposed. The network consists of two parts: 1) a generator, which generates the transferred BCIilliterate features, and 2) a CNN classifier, which is used for the classification of the transferred features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Electroencephalography (EEG) signals from 25 healthy subjects performing MI of the right hand and foot were classified with an average accuracy of 88.2% +/- 5.1%. The proposed model was further validated on the BCI Competition IV dataset 2b, and was demonstrated to be robust to inter-subject variations. The advantages of STNN allow it to bridge the gap between the golden subjects and the BCI-illiterate ones, paving the way to real-time BCI applications. (c) 2022 Elsevier Ltd. All rights reserved.

Automated summary

This paper proposes a deep learning-based method to improve the accuracy of brain computer interfaces (BCIs) by transferring the data distribution from golden subjects to BCI-illiterate users. By aligning the dimensionality-reduced BCI-illiterate data with the data of golden subjects using a generator and a CNN classifier, this method outperforms traditional classification methods in terms of accuracy and robustness. The results demonstrate the effectiveness of this approach in identifying EEG signals and its robustness to inter-subject variations.