SSVEP-DAN: Cross-Domain Data Alignment for SSVEP-Based Brain-Computer Interfaces

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 32; pp. 2027 - 2037
• Main Authors: Chen, Sung-Yu, Chang, Chi-Min, Chiang, Kuan-Jung, Wei, Chun-Shu
• Format: Journal Article
• Language: English
• Published: United States IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Adult; Algorithms; Brain-Computer Interfaces; brain–computer interface (BCI); Calibration; Data acquisition; data alignment; Data models; Decoding; domain adaptation; Electroencephalogram (EEG); Electroencephalography; Evoked Potentials, Visual - physiology; Female; Human-computer interface; Humans; Interfaces; Male; Neural networks; Neural Networks, Computer; Reproducibility of Results; Source code; Spatial filters; steady-state visual-evoked potentials (SSVEPs); Training; Visual evoked potentials; Visualization; Young Adult
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2024.3404432

Steady-state visual-evoked potential (SSVEP)-based brain-computer interfaces (BCIs) offer a non-invasive means of communication through high-speed speller systems. However, their efficiency is highly dependent on individual training data acquired during time-consuming calibration sessions. To address the challenge of data insufficiency in SSVEP-based BCIs, we introduce SSVEP-DAN, the first dedicated neural network model designed to align SSVEP data across different domains, encompassing various sessions, subjects, or devices. Our experimental results demonstrate the ability of SSVEP-DAN to transform existing source SSVEP data into supplementary calibration data. This results in a significant improvement in SSVEP decoding accuracy while reducing the calibration time. We envision SSVEP-DAN playing a crucial role in future applications of high-performance SSVEP-based BCIs. The source code for this work is available at: https://github.com/CECNL/SSVEP-DAN .