Adaptive deep feature representation learning for cross-subject EEG decoding

• Published in: BMC bioinformatics Vol. 25; no. 1; pp. 393 - 19
• Main Authors: Liang, Shuang, Li, Linzhe, Zu, Wei, Feng, Wei, Hang, Wenlong
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 31.12.2024; BioMed Central; BMC
• Subjects: Adaptation; Adaptive sampling; Algorithms; Brain-Computer Interfaces; Calibration; Classification; Clusters; Datasets; Decoders; Decoding; Deep Learning; Discriminative feature learning; Domain adaptation; EEG; Effectiveness; Electroencephalogram; Electroencephalography; Electroencephalography - methods; Electronic data processing; Entropy minimization; Euclidean space; Humans; Machine learning; Mental task performance; Methods; Motor imagery; Motor skill learning; Motor task performance; Performance evaluation; Regularization; Reinforcement learning (Machine learning); Representations; Signal Processing, Computer-Assisted; China; Domain adaptation; Motor imagery; Electroencephalogram; Discriminative feature learning; Entropy minimization
• DOI: 10.1186/s12859-024-06024-w
• ISSN: 1471-2105

The collection of substantial amounts of electroencephalogram (EEG) data is typically time-consuming and labor-intensive, which adversely impacts the development of decoding models with strong generalizability, particularly when the available data is limited. Utilizing sufficient EEG data from other subjects to aid in modeling the target subject presents a potential solution, commonly referred to as domain adaptation. Most current domain adaptation techniques for EEG decoding primarily focus on learning shared feature representations through domain alignment strategies. Since the domain shift cannot be completely removed, target EEG samples located near the edge of clusters are also susceptible to misclassification. We propose a novel adaptive deep feature representation (ADFR) framework to improve the cross-subject EEG classification performance through learning transferable EEG feature representations. Specifically, we first minimize the distribution discrepancy between the source and target domains by employing maximum mean discrepancy (MMD) regularization, which aids in learning the shared feature representations. We then utilize the instance-based discriminative feature learning (IDFL) regularization to make the learned feature representations more discriminative. Finally, the entropy minimization (EM) regularization is further integrated to adjust the classifier to pass through the low-density region between clusters. The synergistic learning between above regularizations during the training process enhances EEG decoding performance across subjects. The effectiveness of the ADFR framework was evaluated on two public motor imagery (MI)-based EEG datasets: BCI Competition III dataset 4a and BCI Competition IV dataset 2a. In terms of average accuracy, ADFR achieved improvements of 3.0% and 2.1%, respectively, over the state-of-the-art methods on these datasets. The promising results highlight the effectiveness of the ADFR algorithm for EEG decoding and show its potential for practical applications.