Objective. The fidelity of neural representations learned by large EEG foundation models depends on how raw brain signals are tokenized. Existing methods suffer from arbitrary temporal boundaries misaligned with neural state transitions, neglecting inter-channel spatial information, and fixed segmentation criteria that fail to generalize across heterogeneous EEG paradigms. Approach. This study proposes the squeeze-and-excitation (SE)-data-adaptive Gaussian average filtering (DAGAF) adaptive tokenizer (SEDAT), a hybrid framework integrating SE-based spatial aggregation, DAGAF-based signal decomposition, instantaneous-frequency-guided adaptive segmentation, and Fourier-domain resampling into a single computationally efficient pipeline. SEDAT is evaluated across 10 heterogeneous EEG datasets spanning motor imagery, mental imagery, P300, slow cortical potentials, sleep staging, epilepsy, emotions recognition and Alzheimer diagnosis paradigms, using four large foundation models: LaBraM, EEGFormer, EEGPT, and NeuroGPT. It is benchmarked against five competitive baselines: fixed-length windowing (FLW), context segmentation, linear predictive coding-based tokenization, TFM-Tokenizer, and source informed segmentation. Main results. SEDAT achieves classification improvements of up to 15.3% over FLW and 1.2%–4.6% over the second-best method, with all comparisons reaching p<0.001 after Benjamini–Hochberg correction. Token quality analysis confirms substantially improved feature separability, with Silhouette scores of 0.81–0.85 versus 0.33–0.48 for rigid baselines. Significance. With O(CN+KNlogN) complexity, SEDAT explores new applications for SE and DAGAF as tokenizers and provides a physiologically grounded and computationally practical tokenization solution for large-scale EEG foundation models.
Muhammad Zulkifal Aziz, Yue Zhuo, Binwen Huang et al.· Journal of Neural Engineerin...· 0 citations
Background Cognitive impairment (CI) is highly prevalent among older adults with hypertension and imposes substantial burdens on individuals, families, and healthcare systems. Identifying factors associated with CI is essential for developing targeted prevention strategies, yet evidence from tropical regions of China remains limited. Objective To examine the prevalence of CI and factors associated with CI among community-dwelling older adults with hypertension in tropical China. Methods This community-based cross-sectional study included 735 older adults aged ≥60 years with self-reported, physician-diagnosed hypertension recruited from community health centers in Haikou, China, between 2023 and 2025. Cognitive function was assessed using the Chinese Mini-Mental Status with education-adjusted cutoff values. Multivariable logistic regression was performed to identify factors associated with CI. Age- and sex-stratified analyses, interaction analyses, and sensitivity analyses were conducted to evaluate the robustness of the findings. Results Among the 735 participants (mean age, 72.3 ± 7.7 years; 57.6% women), 223 (30.3%) had CI. In the fully adjusted model, participants aged ≥80 years had significantly higher odds of CI than those aged 60–69 years (OR = 2.21, 95% CI: 1.34–3.64). Depressive symptoms were also associated with increased odds of CI (OR = 1.87, 95% CI: 1.03–3.39), whereas higher educational attainment, medium monthly income, and higher BMI were associated with lower odds of CI. Stratified analyses suggested potential sex differences in the association between marital status and CI, and formal interaction analysis demonstrated a significant interaction between sex and marital status (P for interaction = 0.015). Sensitivity analyses generally supported the robustness of the primary findings. Conclusion CI was common among community-dwelling older adults with hypertension in tropical China. Older age and depressive symptoms were associated with higher odds of CI, whereas higher educational attainment, moderate income, and higher BMI were associated with lower odds. The observed sex differences in the association between marital status and CI highlight the importance of considering social determinants and sex-specific approaches when developing community-based cognitive health strategies for older adults with hypertension.
Li Peng, Xiuru Wang, Wenting Cao et al.· Frontiers in Public Health· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
