Chao Chen

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

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.

LT-RNet: A Hybrid BILSTM-Transformer Network for sEMG Hand Gesture Recognition

Individual Calibration for Mental Fatigue-Related State Recognition Using Five Frontal Dry-Electrode EEG Channels

This study investigated whether five frontal dry-electrode electroencephalography (EEG) channels can support recognition of mental fatigue-related states after individual calibration. Thirteen healthy adult men completed pre- and post-rest recordings, N-back, Stroop, and a 15-min sustained attention to response task (SART). EEG was recorded from FP1, FP2, AF7, FPz, and AF8. Following quality control, 12 participants were retained for EEG analyses. Spectral, Hjorth, entropy, asymmetry, and inter-channel correlation features were extracted from the early and late SART periods. A subject-dependent nested contiguous temporal-block cross-validation framework selected temporal aggregation, feature set, classifier, and feature number using training data only. KSS increased from 1.77±0.73 to 5.15±0.55 after SART (p < 0.001). No-go commission errors increased from 25.44%±16.63% to 35.87% ± 20.85% (p = 0.040), whereas Go median reaction time decreased (p < 0.001). The main model achieved a mean balanced accuracy (BA) of 0.831±0.124, a median BA of 0.850, and a mean area under the receiver-operating-characteristic curve (AUC) of 0.920±0.114. Chronological holdout testing yielded a mean BA of 0.774±0.204, whereas strict cross-subject classification remained near chance. These findings support the use of five frontal dry-electrode EEG channels for subject-dependent monitoring of mental fatigue-related states after individual calibration, but do not yet support general classification without target-subject calibration.

A Single-Flicker Spatially Encoded SSVEP Brain-Computer Interface Paradigm Based on Ring-Shaped Flickering Stimulation