EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid CNN-GRU Models for Improved EEG Motor Imagery Classification

Mouna Bouchane iD, Wei Guo iD, Shuojin Yang iD

Sensors · 25.02.2025 · 25 (5) · 1399

DOI: 10.3390/s25051399 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.02.2025. Verfasst von Mouna Bouchane und 2 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Augmented Reality, School of Mathematical Sciences, Hebei Normal University, Shijiazhuang 050024, China. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Neural Networks, Computer, Imagination. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hebei Central Leading Local Science and Technology Development Foundation, Hebei Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain–computer interfaces (BCIs) based on electroencephalography (EEG) enable neural activity interpretation for device control, with motor imagery (MI) serving as a key paradigm for decoding imagined movements. Efficient feature extraction from raw EEG signals is essential to improve classification accuracy while minimizing reliance on extensive preprocessing. In this study, we introduce new hybrid architectures to enhance MI classification using data augmentation and a limited number of EEG channels. The first model combines a shallow convolutional neural network and a gated recurrent unit (CNN-GRU), while the second incorporates a convolutional neural network with a bidirectional gated recurrent unit (CNN-Bi-GRU). Evaluated using the publicly available PhysioNet dataset, the CNN-GRU classifier achieved peak mean accuracy rates of 99.71%, 99.73%, 99.61%, and 99.86% for tasks involving left fist (LF), right fist (RF), both fists (LRF), and both feet (BF), respectively. The experimental results provide compelling evidence that our proposed models outperform current state-of-the-art methods, underscoring their efficiency on small-scale EEG datasets. The CNN-GRU and CNN-Bi-GRU architectures exhibit superior predictive reliability, offering a faster, cost-effective solution for user-adaptable MI-BCI applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyBrain-Computer InterfacesNeural Networks, ComputerImaginationHumansSignal Processing, Computer-AssistedMovementAlgorithms

Stichwörter der Autor:innen

bidirectional GRUconvolutional neural network (CNN)electroencephalography (EEG)gated recurrent unit (GRU)hybrid modelsmotor imagery (MI)

Autor:innen und Institutionen

  • Key Laboratory of Augmented Reality, School of Mathematical Sciences, Hebei Normal University, Shijiazhuang 050024, China.
  • Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.

ORCID-Profile: Mouna Bouchane, Wei Guo, Shuojin Yang

Förderung

  • Hebei Central Leading Local Science and Technology Development Foundation
  • Hebei Natural Science Foundation

Zitieren

APA

Bouchane, M., Guo, W., & Yang, S. (2025). Hybrid CNN-GRU Models for Improved EEG Motor Imagery Classification. Sensors, 25(5), 1399. https://doi.org/10.3390/s25051399

Vancouver

Bouchane M, Guo W, Yang S. Hybrid CNN-GRU Models for Improved EEG Motor Imagery Classification. Sensors. 2025;25(5):1399. doi:10.3390/s25051399

BibTeX
@article{Bouchane2025,
  author = {Bouchane, Mouna and Guo, Wei and Yang, Shuojin},
  title = {Hybrid CNN-GRU Models for Improved EEG Motor Imagery Classification},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {5},
  pages = {1399},
  doi = {10.3390/s25051399}
}
Kostenlos starten →