MACNet: A Multidimensional Attention-Based Convolutional Neural Network for Lower-Limb Motor Imagery Classification
Sensors · 2024
DOI: 10.3390/s24237611 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Ling-Long Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots, College of Mechatronics and Control Engineering, Shenzhen University, She…. Hauptthemen laut MEDLINE: Neural Networks, Computer, Electroencephalography, Brain-Computer Interfaces. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the State Key Program of National Natural Science Foundation of China, National Natural Science Foundation of China, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Decoding lower-limb motor imagery (MI) is highly important in brain–computer interfaces (BCIs) and rehabilitation engineering. However, it is challenging to classify lower-limb MI from electroencephalogram (EEG) signals, because lower-limb motions (LLMs) including MI are excessively close to physiological representations in the human brain and generate low-quality EEG signals. To address this challenge, this paper proposes a multidimensional attention-based convolutional neural network (CNN), termed MACNet, which is specifically designed for lower-limb MI classification. MACNet integrates a temporal refining module and an attention-enhanced convolutional module by leveraging the local and global feature representation abilities of CNNs and attention mechanisms. The temporal refining module adaptively investigates critical information from each electrode channel to refine EEG signals along the temporal dimension. The attention-enhanced convolutional module extracts temporal and spatial features while refining the feature maps across the channel and spatial dimensions. Owing to the scarcity of public datasets available for lower-limb MI, a specified lower-limb MI dataset involving four routine LLMs is built, consisting of 10 subjects over 20 sessions. Comparison experiments and ablation studies are conducted on this dataset and a public BCI Competition IV 2a EEG dataset. The experimental results show that MACNet achieves state-of-the-art performance and outperforms alternative models for the subject-specific mode. Visualization analysis reveals the excellent feature learning capabilities of MACNet and the potential relationship between lower-limb MI and brain activity. The effectiveness and generalizability of MACNet are verified.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots, College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, China.
- Shenzhen Institute of Information Technology, Shenzhen 518172, China.
- School of Psychology, Shenzhen University, Shenzhen 518060, China.
ORCID-Profile: Ling-Long Li, Guang-Zhong Cao, Yue-Peng Zhang
Förderung
- the State Key Program of National Natural Science Foundation of China
- National Natural Science Foundation of China
- Shenzhen Science and Technology Program
- State Key Program of National Natural Science Foundation of China
Zitieren
APA
Li, L. L., Cao, G. Z., Zhang, Y. P., Li, W. C., & Cui, F. (2024). MACNet: A Multidimensional Attention-Based Convolutional Neural Network for Lower-Limb Motor Imagery Classification. Sensors. https://doi.org/10.3390/s24237611
Vancouver
Li LL, Cao GZ, Zhang YP, Li WC, Cui F. MACNet: A Multidimensional Attention-Based Convolutional Neural Network for Lower-Limb Motor Imagery Classification. Sensors. 2024. doi:10.3390/s24237611
BibTeX
@article{Li2024,
author = {Li, Ling-Long and Cao, Guang-Zhong and Zhang, Yue-Peng and Li, Wan-Chen and Cui, Fang},
title = {MACNet: A Multidimensional Attention-Based Convolutional Neural Network for Lower-Limb Motor Imagery Classification},
journal = {Sensors},
year = {2024},
doi = {10.3390/s24237611}
}
EUVIMED