Subject adaptation network for EEG data analysis

• Published in: Applied soft computing Vol. 84; p. 105689
• Main Authors: Ming, Yurui, Ding, Weiping, Pelusi, Danilo, Wu, Dongrui, Wang, Yu-Kai, Prasad, Mukesh, Lin, Chin-Teng
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2019
• Subjects: Brain–computer interface (BCI); Clustering; Deep learning; Domain adaptation (DA); Electroencephalograph (EEG); Sample selection; Subject adaptation network (SAN); Deep learning; Sample selection; Domain adaptation (DA); Electroencephalograph (EEG); Subject adaptation network (SAN); Clustering; Brain–computer interface (BCI)
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2019.105689

Biosignals tend to display manifest intra- and cross-subject variance, which generates numerous challenges for electroencephalograph (EEG) data analysis. For instance, in the context of classification, the discrepancy between EEG data can make the trained model generalising poorly for new test subjects. In this paper, a subject adaptation network (SAN) inspired by the generative adversarial network (GAN) to mitigate different variances is proposed for analysing EEG data. First the challenges faced by traditional approaches employed for EEG signal processing are emphasised. Then the problem is formulated from mathematical perspective to highlight the key points in resolving such discrepancies. Third, the motivation behind and design principle of the SAN are described in an intuitive manner to reflect its suitability for analysing EEG data. Then after depicting the overall architecture of the SAN, several experiments are used to justify the practicality and efficiency of using the proposed model from different perspectives. For instance, an EEG dataset captured during a stereotypical neurophysiological experiment called the VEP oddball task is utilised to demonstrate the performance improvement achieved by running the SAN. •A theoretical basis is formalised to guide the model design.•A subject adversarial network is proposed to mitigate EEG data variance.•Various experiments are provided to show the model’s effectiveness.•Tricks from the implementation perspective are discussed.