A temporal–spectral fusion transformer with subject-specific adapter for enhancing RSVP-BCI decoding

• Published in: Neural networks Vol. 181; p. 106844
• Main Authors: Li, Xujin, Wei, Wei, Qiu, Shuang, He, Huiguang
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2025
• Subjects: Adapter-based fine-tuning; Adult; Algorithms; Brain - physiology; Brain-Computer Interfaces; Brain–Computer Interface (BCI); Electroencephalography - methods; Humans; Male; Multi-view learning; Photic Stimulation - methods; Rapid Serial Visual Presentation (RSVP); Signal Processing, Computer-Assisted; Transformer; Visual Perception - physiology; Rapid Serial Visual Presentation (RSVP); Adapter-based fine-tuning; Transformer; Brain–Computer Interface (BCI); Multi-view learning

The Rapid Serial Visual Presentation (RSVP)-based Brain–Computer Interface (BCI) is an efficient technology for target retrieval using electroencephalography (EEG) signals. The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subje...