ScaleSpecter: a frequency-aware multi-scale patch framework for robust physiological classification under non-stationarity
Frontiers in Human Neuroscience · 27.07.2026 · 20
DOI: 10.3389/fnhum.2026.1856803 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Human Neuroscience, online erschienen am 27.07.2026. Verfasst von Zhouyang Xu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computing, Harbin Institute of Technology, Harbin, China. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Introduction
Early detection and intervention for cognitive impairment associated with neurodegenerative diseases are important for slowing disease progression and improving quality of life. Electroencephalography provides high temporal resolution and sensitivity to neural oscillations, making it a promising tool for early disease identification. However, weak and transient pathological abnormalities are often obscured by diffuse, non-stationary low-frequency background rhythms, making robust feature extraction challenging.
Methods
We propose ScaleSpecter, a frequency-aware multiscale patch framework for neurodegenerative disease-related EEG classification. ScaleSpecter first constructs temporal representations at multiple scales to jointly capture transient local abnormalities and long-term rhythmic variations. A lightweight cross-scale attention mechanism then enables interaction between fine-grained temporal tokens and coarse scale-level summaries. Finally, an amplitude-phase-aware spectral modulation module uses learnable complex-valued weights to recalibrate spectral responses and provide frequency-domain guidance for temporal feature aggregation.
Results
Extensive experiments were conducted on three public EEG datasets: the Alzheimer's Disease and Frontotemporal Dementia (ADFTD) dataset, the Alzheimer's Patients' Relatives Association of Valladolid (APAVA) dataset, and the Two Decades-Brainclinics Research Archive for Insights in Neurophysiology (TDBRAIN) database. These datasets cover classification tasks related to Alzheimer's disease, frontotemporal dementia, and Parkinson's disease. ScaleSpecter achieved competitive and generally favorable performance on most key evaluation metrics. The ablation and visualization results further demonstrated the complementary contributions of multiscale temporal modeling, cross-scale interaction, and spectral modulation.
Discussion
The results suggest that integrating frequency-domain guidance with multiscale temporal representations can improve the discriminative capability and robustness of EEG classification under non-stationary conditions. ScaleSpecter provides a potentially generalizable framework for neurodegenerative disease-related physiological signal analysis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Computing, Harbin Institute of Technology, Harbin, China.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xu, Z., Li, H., Liu, W., & Li, H. (2026). ScaleSpecter: a frequency-aware multi-scale patch framework for robust physiological classification under non-stationarity. Frontiers in Human Neuroscience, 20. https://doi.org/10.3389/fnhum.2026.1856803
Vancouver
Xu Z, Li H, Liu W, Li H. ScaleSpecter: a frequency-aware multi-scale patch framework for robust physiological classification under non-stationarity. Frontiers in Human Neuroscience. 2026;20. doi:10.3389/fnhum.2026.1856803
BibTeX
@article{Xu2026,
author = {Xu, Zhouyang and Li, Hongwei and Liu, Wenchao and Li, Haifeng},
title = {ScaleSpecter: a frequency-aware multi-scale patch framework for robust physiological classification under non-stationarity},
journal = {Frontiers in Human Neuroscience},
year = {2026},
volume = {20},
doi = {10.3389/fnhum.2026.1856803}
}
EUVIMED