Related Experiment Video
Updated: May 6, 2026
10:09
Mapping the After-effects of Theta Burst Stimulation on the Human Auditory Cortex with Functional Imaging
Published on: September 12, 2012
13.8K
A temporal-spectral fusion transformer with subject-specific adapter for enhancing RSVP-BCI decoding
Xujin Li1, Wei Wei2, Shuang Qiu3
1Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China; School of Future Technology, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China.
Summary
This study introduces a new Brain-Computer Interface (BCI) method using electroencephalography (EEG) signals. The TSformer-SA model enhances target retrieval accuracy and reduces setup time for new users.
Area of Science:
- Neuroscience
- Computer Science
- Biomedical Engineering
Background:
- Brain-Computer Interfaces (BCI) leverage electroencephalography (EEG) for target retrieval.
- Traditional BCI decoding requires extensive training data from new subjects, increasing preparation time.
- Existing methods often focus on single-view EEG data and can have long training durations.
Purpose of the Study:
- To enhance BCI decoding performance.
- To reduce the preparation time for BCI systems.
- To improve the efficiency and rapid deployment of BCI technology.
Main Methods:
- Proposed Temporal-Spectral fusion transformer with Subject-specific Adapter (TSformer-SA).
- Implemented a cross-view interaction module for feature extraction from temporal and spectrogram EEG data.
- Utilized an attention-based fusion module and a multi-view consistency loss.
- Introduced a subject-specific adapter for rapid knowledge transfer to new subjects.
Main Results:
- TSformer-SA significantly outperformed existing BCI decoding methods.
- Achieved outstanding performance with limited training data from new subjects.
- Demonstrated efficient decoding and rapid deployment capabilities.
Conclusions:
- The proposed TSformer-SA model offers a significant advancement in BCI technology.
- It effectively addresses the challenges of extensive training data requirements and preparation time.
- Facilitates practical application and widespread adoption of BCI systems.
