A High-Frequency SSVEP-BCI System Based on Simultaneous Modulation of Luminance and Motion Using Intermodulation Frequencies

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 31; pp. 2603 - 2611
• Main Authors: Li, Meng, Chen, Xiaogang, Cui, Hongyan
• Format: Journal Article
• Language: English
• Published: United States IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Brain-computer interface; Comfort; Correlation analysis; Electroencephalography; Encoding; Fatigue; filter bank canonical correlation analysis; Filter banks; Frequency modulation; high frequency; Human-computer interface; Intermodulation; intermodulation frequencies; Luminance; Modulation; Performance evaluation; Sensory stimulation; Steady-state; steady-state visual evoked potential; Task analysis; Visual evoked potentials; Visualization
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2023.3281416

The low-frequency steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) tend to induce visual fatigue in the subjects. In order to enhance the comfort of SSVEP-BCIs, a novel SSVEP-BCI encoding method based on simultaneous modulation of luminance and motion is proposed. In this work, sixteen stimulus targets are simultaneously flickered and radially zoomed using a sampled sinusoidal stimulation method. The flicker frequency is set to a 30 Hz for all the targets, while assigning different radial zoom frequencies (ranging from 0.4 Hz to 3.4 Hz, with an interval of 0.2 Hz) are assigned to each target separately. Accordingly, an extended vision of the filter bank canonical correlation analysis (eFBCCA) is proposed to detect the intermodulation (IM) frequencies and classify the targets. In addition, we adopt the comfort level scale to evaluate the subjective comfort experience. By optimizing the combination of IM frequencies for the classification algorithm, the average recognition accuracy of the offline and online experiments reaches 92.74 ± 1.53% and 93.33 ± 0.01%, respectively. Most importantly, the average comfort scores are above 5. These results demonstrate the feasibility and comfort of the proposed system using IM frequencies, which provides new ideas for the further development of highly comfortable SSVEP-BCIs.