EUVIMEDEUVIMED entdecken
Crossref

Time–frequency-spatial channel attention network for semantic decoding: an exploratory EEG study

Xiang Tang, Huixiang Wu, Shuran Li, Anastasios Bezerianos, Rongliang Hu, Zhaocong Chen, Hongtao Wang

Medical & Biological Engineering & Computing · 2026-04 · 64 (4) · 1573-1588

DOI: 10.1007/s11517-026-03539-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 05.03.2026. Verfasst von Xiang Tang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Information Engineering, Wuyi University, Jiangmen, China. Hauptthemen laut MEDLINE: Electroencephalography, Semantics, Signal Processing, Computer-Assisted. Die Arbeit nennt 58 Literaturangaben. Gefördert von: Key Discipline Research Capability Enhancement Project in Guangdong Province, Guangdong University Innovation Team Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic decoding is a crucial approach for investigating the neural mechanisms underlying language processing and representation. Informed by brain-computer interface (BCI) technology, this study investigated methods for decoding semantic information, with an emphasis on the neural representations of semantics in language perception. Due to the limited availability of electroencephalography (EEG) datasets containing Chinese linguistic stimuli, we have specifically designed a semantic task paradigm as a promising attempt to decode language comprehension and expression in patients with aphasia using scalp EEG. This paradigm fully incorporates the processes underlying both speech perception and speech imagery by adopting tasks such as overt speech perception and silent speech imagery. Firstly, Seventeen participants of aphasia patients and healthy subjects were recruited for EEG data collection. Secondly, we constructed a deep learning model termed Time-Frequency-Spatial Channel Attention Network (TFSANet), which processes both time-domain and frequency-domain features to extract key neural signatures associated with semantics. By optimizing the model and employing multidimensional feature extraction mechanisms, we significantly improved the model's ability to decode semantically relevant EEG features. Finally, the experimental results demonstrate the proposed TFSANet could decode semantic information from EEG for ten categories of four-word phrases under an "auditory-guided" paradigm with an accuracy of 60.73% and 75.09% for aphasia patients and healthy subjects respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographySemanticsSignal Processing, Computer-AssistedHumansFemaleMaleAdultBrain-Computer InterfacesAphasiaMiddle AgedDeep LearningSpeech Perception

Stichwörter der Autor:innen

Brain-computer interfaceDeep learningElectroencephalographySemantic decoding

Autor:innen und Institutionen

  • School of Electronics and Information Engineering, Wuyi University, Jiangmen, China.
  • Department of Rehabilitation Medicine, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China.
  • School of Electronic & Information Engineering, Guangzhou City University of Technology, Guangzhou, China.
  • Hellenic Institute of Transportation, 57001, Thessaloniki, Greece.
  • Jiangmen Central Hospital, Jiangmen, China.
  • Department of Rehabilitation Medicine, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China. chenzhc5@mail.sysu.edu.cn.

Förderung

  • Key Discipline Research Capability Enhancement Project in Guangdong Province
  • Guangdong University Innovation Team Program

Zitieren

APA

Tang, X., Wu, H., Li, S., Bezerianos, A., Hu, R., Chen, Z., & Wang, H. (2026). Time–frequency-spatial channel attention network for semantic decoding: an exploratory EEG study. Medical & Biological Engineering & Computing, 64(4), 1573-1588. https://doi.org/10.1007/s11517-026-03539-7

Vancouver

Tang X, Wu H, Li S, Bezerianos A, Hu R, Chen Z, et al. Time–frequency-spatial channel attention network for semantic decoding: an exploratory EEG study. Medical & Biological Engineering & Computing. 2026;64(4):1573-1588. doi:10.1007/s11517-026-03539-7

BibTeX
@article{Tang2026,
  author = {Tang, Xiang and Wu, Huixiang and Li, Shuran and Bezerianos, Anastasios and Hu, Rongliang and Chen, Zhaocong and Wang, Hongtao},
  title = {Time–frequency-spatial channel attention network for semantic decoding: an exploratory EEG study},
  journal = {Medical & Biological Engineering & Computing},
  year = {2026},
  volume = {64},
  number = {4},
  pages = {1573--1588},
  doi = {10.1007/s11517-026-03539-7}
}
Kostenlos starten →