EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DEP-TFDualNet: A Dual-Domain Attention Framework with Temporal–Frequency Fusion for Depression Recognition Using Three-Channel Frontal EEG

Haijun Lin, Jiayi Liu, Dongxu Jiang

Sensors · 17.06.2026 · 26 (12) · 3861

DOI: 10.3390/s26123861 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.06.2026. Verfasst von Haijun Lin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application, Harbin University of Science and Technology, Harbin 150080, Ch…. Hauptthemen laut MEDLINE: Electroencephalography, Depression, Major Depressive Disorder. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Heilongjiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early depression screening is important for timely intervention, and electroencephalography (EEG) offers an objective and potentially portable sensing modality for computer-aided assessment. However, recognition from fixed three-channel frontal EEG remains difficult because of limited spatial information and incomplete modeling of temporal–frequency characteristics and temporal dependencies. This study proposes DEP-TFDualNet for acquisition-constrained frontal resting-state EEG. The framework integrates multi-scale convolution, dual-domain channel attention, temporal modeling derived from the independent recurrent neural network (IndRNN) architecture, and decision-stage fusion of deep representations with low-order statistical descriptors through a Kolmogorov–Arnold Network (KAN)-based nonlinear projection layer. Experiments were conducted on the publicly available three-channel frontal EEG subset of the MODMA dataset. After additional quality control, 48 subjects were retained (22 patients with major depressive disorder, 26 healthy controls). Under subject-wise stratified five-fold cross-validation, DEP-TFDualNet achieved 85.42% accuracy, 85.26% macro-F1, 81.82% sensitivity, 88.46% specificity, an AUC of 0.82, and a Brier score of 0.121. It achieved the best threshold-based subject-level performance and the lowest Brier score among the evaluated models. These results provide preliminary evidence that simplified frontal EEG sensing may support depression recognition in acquisition-constrained settings, although larger and external validation is still required.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyDepressionMajor Depressive DisorderHumansFemaleAdultMaleSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

deep learningdepression recognitionelectroencephalographyfrontal EEGresting-state EEGtemporal–frequency fusion

Autor:innen und Institutionen

  • Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application, Harbin University of Science and Technology, Harbin 150080, China.

Förderung

  • Natural Science Foundation of Heilongjiang Province

Zitieren

APA

Lin, H., Liu, J., & Jiang, D. (2026). DEP-TFDualNet: A Dual-Domain Attention Framework with Temporal–Frequency Fusion for Depression Recognition Using Three-Channel Frontal EEG. Sensors, 26(12), 3861. https://doi.org/10.3390/s26123861

Vancouver

Lin H, Liu J, Jiang D. DEP-TFDualNet: A Dual-Domain Attention Framework with Temporal–Frequency Fusion for Depression Recognition Using Three-Channel Frontal EEG. Sensors. 2026;26(12):3861. doi:10.3390/s26123861

BibTeX
@article{Lin2026,
  author = {Lin, Haijun and Liu, Jiayi and Jiang, Dongxu},
  title = {DEP-TFDualNet: A Dual-Domain Attention Framework with Temporal–Frequency Fusion for Depression Recognition Using Three-Channel Frontal EEG},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3861},
  doi = {10.3390/s26123861}
}
Kostenlos starten →