An Intersubject Brain-Computer Interface Based on Domain-Adversarial Training of Convolutional Neural Network

• Published in: IEEE transactions on biomedical engineering Vol. 71; no. 10; pp. 2956 - 2967
• Main Authors: Chen, Di, Huang, Haiyun, Guan, Zijing, Pan, Jiahui, Li, Yuanqing
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adult; Adversarial machine learning; Algorithms; Artificial neural networks; Attention; attention decoding; Biochips; Brain; Brain - physiology; Brain-Computer Interfaces; Computer applications; Convolutional neural networks; Decoding; domain-adversarial training neural network (DANN); EEG; Electroencephalography; Electroencephalography (EEG); Electroencephalography - methods; Experiments; Feature extraction; Female; Human-computer interface; Humans; Implants; Internet; intersubject; Male; Neural networks; Neural Networks, Computer; offline analysis; online brain-computer interface (BCI); Signal Processing, Computer-Assisted; Training; Young Adult
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2024.3404131

Objective: Attention decoding plays a vital role in daily life, where electroencephalography (EEG) has been widely involved. However, training a universally effective model for everyone is impractical due to substantial interindividual variability in EEG signals. To tackle the above challenge, we propose an end-to-end brain-computer interface (BCI) framework, including temporal and spatial one-dimensional (1D) convolutional neural network and domain-adversarial training strategy, namely DA-TSnet. Method: Specifically, DA-TSnet extracts temporal and spatial features of EEG, while it is jointly supervised by task loss and domain loss. During training, DA-TSnet aims to maximize the domain loss while simultaneously minimizing the task loss. We conduct an offline analysis, simulate online experiments on a self-collected dataset of 85 subjects, and real online experiments on 22 subjects. Main results: DA-TSnet achieves a leave-one-subject-out (LOSO) cross-validation (CV) classification accuracy of 89.40% <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 9.96%, outperforming several state-of-the-art attention EEG decoding methods. In simulated online experiments, DA-TSnet achieves an outstanding accuracy of 88.07% <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 11.22%. In real online experiments, it achieves an average accuracy surpassing 86%. Significance: An end-to-end network framework does not rely on elaborate preprocessing and feature extraction steps, which saves time and human workload. Moreover, our framework utilizes domain-adversarial training neural network (DANN) to tackle the challenge posed by the high interindividual variability in EEG signals, which has significant reference value for handling other EEG signal decoding issues. Last, the performance of the DA-TSnet framework in offline and online experiments underscores its potential to facilitate more reliable applications.