Crosstalk Characteristics Analysis and Spatial Coding Optimization of Partitioned Backlight-Based SSVEP-BCI

Steady-state visual evoked potential-based brain–computer interfaces (SSVEP-BCIs) are widely applied in non-invasive brain–computer interaction, yet traditional single-frequency coding suffers from scarce frequency resources and degraded accuracy in multi-target tasks. The partitioned backlight mode (PB-M) supports SSVEP spatial coding, while systematic investigations on its inherent backlight crosstalk are still lacking. This study develops a PB-M-based SSVEP-BCI system to explore crosstalk mechanisms. Each participant completed 90 valid trials with 18 stimuli and five repetitions each. The results verify inter-partition crosstalk, which can reduce recognition accuracy under narrow frequency intervals and non-isolated layouts, and gaze position can modulate non-target SSVEP responses. Classification accuracy was calculated by valid correct trial ratios, and the information transfer rate (ITR) was computed using standard BCI formulas, yielding 87.50% accuracy and 48.75 bits/min ITR. Full exhaustive classification testing across all 18 stimulus targets was not implemented, where core classification validation was performed on partially selected targets. The proposed frequency reuse strategy shows promising potential to improve SSVEP-BCI performance based on empirical experimental data, providing valid references for multi-target BCI design.