EUVIMEDEUVIMED entdecken
Open Access

Adaptive filter of frequency bands based coordinate attention network for EEG-based motor imagery classification

Xiaoli Zhang, Yongxionga Wang, Yiheng Tang, Zhe Wang

Health Information Science and Systems · 23.02.2024 · 12 (1)

DOI: 10.1007/s13755-024-00270-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Health Information Science and Systems, online erschienen am 23.02.2024. Verfasst von Xiaoli Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: The School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, 200093 China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Natural Science Foundation of Shanghai.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

In the brain-computer interface (BCI), motor imagery (MI) could be defined as the Electroencephalogram (EEG) signals through imagined movements, and ultimately enabling individuals to control external devices. However, the low signal-to-noise ratio, multiple channels and non-linearity are the essential challenges of accurate MI classification. To tackle these issues, we investigate the role of adaptive frequency bands selection and spatial-temporal feature learning in decoding motor imagery.

Methods

We propose an Adaptive Filter of Frequency Bands based Coordinate Attention Network (AFFB-CAN) to improve the performance of MI classification. Specifically, we design the AFFB to adaptively obtain the upper and lower limits of frequency bands in order to alleviate information loss caused by manual selection. Next, we propose the CAN-based network to emphasize the key brain regions and temporal segments. And we design a multi-scale module to enhance temporal context learning.

Results

The conducted experiments on the BCI Competition IV-2a and 2b datasets reveal that our approach achieves an outstanding average accuracy, kappa values, and Macro F1-Score with 0.7825, 0.7104, and 0.7486 respectively. Similarly, for the BCI Competition IV-2b dataset, the average accuracy, kappa values, and F1-Score obtained are 0.8879, 0.7427, and 0.8734, respectively.

Conclusion

The proposed AFFB-CAN method improves the performance of MI classification. In addition, our study confirms previous findings that motor imagery is mainly associated with µ and β rhythms. Moreover, we also find that γ rhythms also play an important role in MI classification.

Schlagwörter

Stichwörter der Autor:innen

Adaptive filterCoordinate attentionElectroencephalogramMotor imageryMulti-scale learning

Autor:innen und Institutionen

  • The School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, 200093 China.

Förderung

  • Natural Science Foundation of Shanghai

Zitieren

APA

Zhang, X., Wang, Y., Tang, Y., & Wang, Z. (2024). Adaptive filter of frequency bands based coordinate attention network for EEG-based motor imagery classification. Health Information Science and Systems, 12(1). https://doi.org/10.1007/s13755-024-00270-1

Vancouver

Zhang X, Wang Y, Tang Y, Wang Z. Adaptive filter of frequency bands based coordinate attention network for EEG-based motor imagery classification. Health Information Science and Systems. 2024;12(1). doi:10.1007/s13755-024-00270-1

BibTeX
@article{Zhang2024,
  author = {Zhang, Xiaoli and Wang, Yongxionga and Tang, Yiheng and Wang, Zhe},
  title = {Adaptive filter of frequency bands based coordinate attention network for EEG-based motor imagery classification},
  journal = {Health Information Science and Systems},
  year = {2024},
  volume = {12},
  number = {1},
  doi = {10.1007/s13755-024-00270-1}
}
Kostenlos starten →