Align and Pool for EEG Headset Domain Adaptation (ALPHA) to Facilitate Dry Electrode Based SSVEP-BCI

• Published in: IEEE transactions on biomedical engineering Vol. 69; no. 2; pp. 795 - 806
• Main Authors: Liu, Bingchuan, Chen, Xiaogang, Li, Xiang, Wang, Yijun, Gao, Xiaorong, Gao, Shangkai
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Algorithms; Brain; Brain-computer interface; Brain-Computer Interfaces; Computer applications; Correlation analysis; domain adaptation; Domains; EEG; Electrodes; Electroencephalography; Evoked Potentials, Visual; Headphones; Headsets; Human-computer interface; Humans; Implants; Learning; Signal to noise ratio; steady-state visual evoked potential; subspace learning; Task analysis; Transfer learning; Visual evoked potentials; Visualization
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2021.3105331

Objective: The steady-state visual evoked potential based brain-computer interface (SSVEP-BCI) implemented in dry electrodes is a promising paradigm for alternative and augmentative communication in real-world applications. To improve its performance and reduce the calibration effort for dry-electrode systems, we utilize cross-device transfer learning by exploiting auxiliary individual wet-electrode electroencephalogram (EEG). Methods: We proposed a novel transfer learning framework named AL ign and P ool for EEG H eadset domain A daptation (ALPHA), which aligns the spatial pattern and the covariance for domain adaptation. To evaluate its efficacy, 75 subjects performed an experiment of 2 sessions involving a 12-target SSVEP-BCI task. Results: ALPHA significantly outperformed a baseline approach (canonical correlation analysis, CCA) and two competing transfer learning approaches (transfer template CCA, ttCCA and least square transformation, LST) in two transfer directions. When transferring from wet to dry EEG headsets, ALPHA significantly outperformed the fully-calibrated approach of task-related component analysis (TRCA). Conclusion: ALPHA advances the frontier of recalibration-free cross-device transfer learning for SSVEP-BCIs and boosts the performance of dry electrode based systems. Significance: ALPHA has methodological and practical implications and pushes the boundary of dry electrode based SSVEP-BCI toward real-world applications.