High-frequency SSVEP-BCI system for detecting intermodulation frequency components using task-discriminant component analysis

• Published in: Biomedical signal processing and control Vol. 99; p. 106868
• Main Authors: Cui, Hongyan, Li, Meng, Ma, Xiaodong, Chen, Xiaogang
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2025
• Subjects: Brain-computer interface; High frequency steady-state visual evoked potential; Intermodulation frequencies; Task-discriminant component analysis; Brain-computer interface; Intermodulation frequencies; Task-discriminant component analysis; High frequency steady-state visual evoked potential
• ISSN: 1746-8094
• DOI: 10.1016/j.bspc.2024.106868

•A novel BCI paradigm using five high-frequency flicker frequencies and eight scaling frequencies to encode forty visual stimulus targets.•An extended version of a task-discriminant component analysis was proposed to detect the intermodulation components.•Ten subjects successfully completed the online free-spell task. Recently, steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) has significantly progressed and is moving from the laboratory to practical application. However, the system performance and comfort of SSVEP-BCIs still need to be improved. In this study, five flicker frequencies (i.e., 30–34 Hz with an interval of 1 Hz) and eight scaling frequencies (i.e., 0.4–1.8 Hz with an interval of 0.2 Hz) were adopted to jointly encode forty visual stimulus targets using evoked intermodulation (IM) frequency components. Both luminance and shape changes are implemented by sinusoidal sampling stimulus coding methods. High-frequency flicker frequencies and green visual stimuli were chosen to improve the comfort of the proposed system. An extended version of a training algorithm named task-discriminant component analysis (TDCA) was proposed to detect the IM components of SSVEP signals. The average recognition accuracy of eleven subjects is 96.82 ± 0.01 % in the offline experiments for a data length of 5 s. Online validation experiments was constructed from the optimized parameters of offline analysis, and the average accuracy and ITR were 94.37 ± 1.17 % and 113.47 ± 2.60 bits/min, respectively. Furthermore, ten subjects who participated in the validation part also completed the online free-spell task successfully. These results showed that it is feasible to expand the number of stimulus targets by using IM frequency components of SSVEP signals for target coding, and that the system performance is superior.