Robust Motor Imagery Tasks Classification Approach Using Bayesian Neural Network
Sensors · 2023
DOI: 10.3390/s23020703 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Daily Milanés-Hermosilla und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automatic Engineering, University of Oriente, Santiago de Cuba 90500, Cuba. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Project "Development of upper limb exo-503 skeletons for rehabilitation task", National Science Project “Development of upper limb exoskeletons for rehabilitation task”.
Abstract (Originalsprache)
The development of Brain–Computer Interfaces based on Motor Imagery (MI) tasks is a relevant research topic worldwide. The design of accurate and reliable BCI systems remains a challenge, mainly in terms of increasing performance and usability. Classifiers based on Bayesian Neural Networks are proposed in this work by using the variational inference, aiming to analyze the uncertainty during the MI prediction. An adaptive threshold scheme is proposed here for MI classification with a reject option, and its performance on both datasets 2a and 2b from BCI Competition IV is compared with other approaches based on thresholds. The results using subject-specific and non-subject-specific training strategies are encouraging. From the uncertainty analysis, considerations for reducing computational cost are proposed for future work.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Automatic Engineering, University of Oriente, Santiago de Cuba 90500, Cuba.
- Electronics, Communications and Computing Services Company for the Nickel Industry, Holguín 80100, Cuba.
- Independent Researcher, 33720 Tampere, Finland.
- Department of Mechanical Engineering, University of Oriente, Santiago de Cuba 90500, Cuba.
- Department of Electrical and Electronic Engineering, Federal University of Santa Catarina, Florianopolis 88040-900, SC, Brazil.
- Postgraduate Program in Neuroengineering, Edmond and Lily Safra International Institute of Neurosciences, Santos Dumont Institute, Macaiba 59280-000, RN, Brazil.
ORCID-Profile: Daily Milanés-Hermosilla, Rafael Trujillo-Codorniú, Roberto Sagaró-Zamora, John Jairo Villarejo-Mayor, Denis Delisle-Rodriguez
Förderung
- National Science Project "Development of upper limb exo-503 skeletons for rehabilitation task"
- National Science Project “Development of upper limb exoskeletons for rehabilitation task”
Zitieren
APA
Milanés-Hermosilla, D., Trujillo-Codorniú, R., Lamar-Carbonell, S., Sagaró-Zamora, R., Tamayo-Pacheco, J. J., Villarejo-Mayor, J. J., & Delisle-Rodriguez, D. (2023). Robust Motor Imagery Tasks Classification Approach Using Bayesian Neural Network. Sensors. https://doi.org/10.3390/s23020703
Vancouver
Milanés-Hermosilla D, Trujillo-Codorniú R, Lamar-Carbonell S, Sagaró-Zamora R, Tamayo-Pacheco JJ, Villarejo-Mayor JJ, et al. Robust Motor Imagery Tasks Classification Approach Using Bayesian Neural Network. Sensors. 2023. doi:10.3390/s23020703
BibTeX
@article{MilansHermosilla2023,
author = {Milanés-Hermosilla, Daily and Trujillo-Codorniú, Rafael and Lamar-Carbonell, Saddid and Sagaró-Zamora, Roberto and Tamayo-Pacheco, Jorge Jadid and Villarejo-Mayor, John Jairo and Delisle-Rodriguez, Denis},
title = {Robust Motor Imagery Tasks Classification Approach Using Bayesian Neural Network},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23020703}
}
EUVIMED