Transferring Subject-Specific Knowledge Across Stimulus Frequencies in SSVEP-Based BCIs

• Published in: IEEE transactions on automation science and engineering Vol. 18; no. 2; pp. 552 - 563
• Main Authors: Wong, Chi Man, Wang, Ze, Rosa, Agostinho C., Chen, C. L. Philip, Jung, Tzyy-Ping, Hu, Yong, Wan, Feng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Brain modeling; Brain–computer interface (BCI); Calibration; Commonality; Correlation analysis; Data acquisition; Data models; Feasibility studies; Frequency ranges; Human-computer interface; Impulse response; Knowledge; Learning; Mathematical models; Medical services; Parameters; Performance enhancement; Spatial filtering; Spatial filters; Steady state; steady-state visually evoked potential (SSVEP); stimulus-to-stimulus transfer; Superposition (mathematics); Target recognition; transfer learning; Visual stimuli; Visualization

Learning from subject's calibration data can significantly improve the performance of a steady-state visually evoked potential (SSVEP)-based brain-computer interface (BCI), for example, the state-of-the-art target recognition methods utilize the learned subject-specific and stimulus-specific mo...