EUVIMEDEUVIMED entdecken
Open Access

A Method to Extract Task-Related EEG Feature Based on Lightweight Convolutional Neural Network

Qi Huang, Jing Ding, Xin Wang

Neuroscience Bulletin · 2024

DOI: 10.1007/s12264-024-01247-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neuroscience Bulletin, 2024. Verfasst von Qi Huang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China. Hauptthemen laut MEDLINE: Electroencephalography, Neural Networks, Computer, Brain-Computer Interfaces. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unlocking task-related EEG spectra is crucial for neuroscience. Traditional convolutional neural networks (CNNs) effectively extract these features but face limitations like overfitting due to small datasets. To address this issue, we propose a lightweight CNN and assess its interpretability through the fully connected layer (FCL). Initially tested with two tasks (Task 1: open vs closed eyes, Task 2: interictal vs ictal stage), the CNN demonstrated enhanced spectral features in the alpha band for Task 1 and the theta band for Task 2, aligning with established neurophysiological characteristics. Subsequent experiments on two brain-computer interface tasks revealed a correlation between delta activity (around 1.55 Hz) and hand movement, with consistent results across pericentral electroencephalogram (EEG) channels. Compared to recent research, our method stands out by delivering task-related spectral features through FCL, resulting in significantly fewer trainable parameters while maintaining comparable interpretability. This indicates its potential suitability for a wider array of EEG decoding scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyNeural Networks, ComputerBrain-Computer InterfacesHumansAdultMaleFemaleYoung AdultBrainSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

Convolutional neural networkElectroencephalogramFully connected layerIntelligibility

Autor:innen und Institutionen

  • Department of Neurology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China.
  • Department of Neurology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China. ding.jing@zs-hospital.sh.cn.
  • Department of Neurology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China. wang.xin@zs-hospital.sh.cn.
  • Department of the State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science, Institutes of Brain Science, Fudan University, Shanghai, 200032, China. wang.xin@zs-hospital.sh.cn.

Zitieren

APA

Huang, Q., Ding, J., & Wang, X. (2024). A Method to Extract Task-Related EEG Feature Based on Lightweight Convolutional Neural Network. Neuroscience Bulletin. https://doi.org/10.1007/s12264-024-01247-6

Vancouver

Huang Q, Ding J, Wang X. A Method to Extract Task-Related EEG Feature Based on Lightweight Convolutional Neural Network. Neuroscience Bulletin. 2024. doi:10.1007/s12264-024-01247-6

BibTeX
@article{Huang2024,
  author = {Huang, Qi and Ding, Jing and Wang, Xin},
  title = {A Method to Extract Task-Related EEG Feature Based on Lightweight Convolutional Neural Network},
  journal = {Neuroscience Bulletin},
  year = {2024},
  doi = {10.1007/s12264-024-01247-6}
}
Kostenlos starten →