Asynchronous steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) show great potential for real-world control, yet their performance is often impaired by phase shifts between ongoing electroencephalogram (EEG) signals and fixed-phase templates. In this study, we observed and validated a phase-sliding oscillation (PSO) phenomenon: when a fixed-phase template is used, phase-sliding trajectories derived from sliding-window sequences with different initial phases exhibit stable periodic oscillations locked to the stimulus frequency. Based on this finding, we propose a phase-sliding oscillation-based asynchronous classification (PSO-AC) method. Specifically, EEG signals are reconstructed into sequences with varying initial phases and transformed into stable time-frequency representations via wavelet synchrosqueezing transform to extract phase-decoupled features. A probabilistic temporal model is then used to characterize temporal dynamics and distinguish control from non-control states. Offline experiments (n=22) showed that PSO-AC achieved a mean control/non-control accuracy of 94.2% with a 2-s data length, outperforming a state-of-the-art baseline. It also maintained superior performance in nine-class classification under different time delays. In online robotic-arm experiments , PSO-AC enabled more stable command triggering and higher control efficiency, reducing the command cost per successful trial from 4.30 to 1.14.
原文链接
分享
引用
