A High-Frequency SSaVEP-Based BCI Paradigm Using Simultaneous Luminance–Motion Modulation and Sequential Dual-Block Decoding

Abstract

To improve target discriminability and user comfort in high-frequency visual stimulation brain–computer interface (BCI) systems, this study proposes a high-frequency steady-state asymmetric visual evoked potential (SSaVEP)-based BCI paradigm using simultaneous luminance and motion modulation, together with a corresponding decoding framework. The proposed paradigm adopts a 16-target spelling interface in which all targets employ a 30 Hz high-frequency luminance flicker combined with target-specific radial zooming motion frequencies to enhance inter-target discriminability. In addition, a sequential dual-block stimulation structure is designed so that each trial contains two consecutive temporal stages, thereby introducing stable temporal-structural differences and complementary neural response information.To fully exploit these temporal characteristics, a Filter-Bank Sequential Dual-Block Joint-Fusion TRCA (FB-SDB-JFTRCA) decoding method is proposed under a filter-bank framework. The method jointly models cross-trial consistency in both the original EEG domain and the differential domain constructed from the front and rear temporal windows, and further integrates the discriminative scores from dual branches during classification to effectively extract temporally complementary features. Offline experiments involving eight healthy subjects demonstrated that the proposed paradigm combined with FB-SDB-JFTRCA achieved an average classification accuracy of 83.20±3.38% and an information transfer rate (ITR) of 32.35±2.54 bits/min in a 16-target task. These findings verify the effectiveness of simultaneous luminance–motion modulation and the sequential dual-block structure in improving the performance of high-frequency SSaVEP-BCI systems, providing a feasible solution for constructing visual BCI systems with both high recognition performance and user comfort.