EEG Signal Prediction for Motor Imagery Classification in Brain–Computer Interfaces
Sensors · 03.04.2025 · 25 (7) · 2259
DOI: 10.3390/s25072259 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 03.04.2025. Verfasst von Óscar Wladimir Gómez-Morales und 3 weiteren Autor:innen. Beteiligte Einrichtung: TECED-Research Group, Faculty of Systems and Telecommunications, Universidad Estatal Península de Santa Elena, Avda. La Libertad, La Libertad, Santa …. Hauptthemen laut MEDLINE: Brain-Computer Interfaces, Electroencephalography, Signal Processing, Computer-Assisted, Imagination. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Estatal Península de Santa Elena, Ecuador, Minciencias.
Abstract (Originalsprache)
Brain–computer interfaces (BCIs) based on motor imagery (MI) generally require EEG signals recorded from a large number of electrodes distributed across the cranial surface to achieve accurate MI classification. Not only does this entail long preparation times and high costs, but it also carries the risk of losing valuable information when an electrode is damaged, further limiting its practical applicability. In this study, a signal prediction-based method is proposed to achieve high accuracy in MI classification using EEG signals recorded from only a small number of electrodes. The signal prediction model was constructed using the elastic net regression technique, allowing for the estimation of EEG signals from 22 complete channels based on just 8 centrally located channels. The predicted EEG signals from the complete channels were used for feature extraction and MI classification. The results obtained indicate a notable efficacy of the proposed prediction method, showing an average performance of 78.16% in classification accuracy. The proposed method demonstrated superior performance compared to the traditional approach that used few-channel EEG and also achieved better results than the traditional method based on full-channel EEG. Although accuracy varies among subjects, from 62.30% to an impressive 95.24%, these data indicate the capability of the method to provide accurate estimates from a reduced set of electrodes. This performance highlights its potential to be implemented in practical MI-based BCI applications, thereby mitigating the time and cost constraints associated with systems that require a high density of electrodes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- TECED-Research Group, Faculty of Systems and Telecommunications, Universidad Estatal Península de Santa Elena, Avda. La Libertad, La Libertad, Santa Elena 7047, Ecuador.
- Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, Colombia.
ORCID-Profile: Óscar Wladimir Gómez-Morales, Diego Fabian Collazos-Huertas, Andrés Marino Álvarez-Meza, Cesar German Castellanos-Dominguez
Förderung
- Universidad Estatal Península de Santa Elena, Ecuador
- Minciencias
Zitieren
APA
Gómez-Morales, Ó. W., Collazos-Huertas, D. F., Álvarez-Meza, A. M., & Castellanos-Dominguez, C. G. (2025). EEG Signal Prediction for Motor Imagery Classification in Brain–Computer Interfaces. Sensors, 25(7), 2259. https://doi.org/10.3390/s25072259
Vancouver
Gómez-Morales ÓW, Collazos-Huertas DF, Álvarez-Meza AM, Castellanos-Dominguez CG. EEG Signal Prediction for Motor Imagery Classification in Brain–Computer Interfaces. Sensors. 2025;25(7):2259. doi:10.3390/s25072259
BibTeX
@article{GmezMorales2025,
author = {Gómez-Morales, Óscar Wladimir and Collazos-Huertas, Diego Fabian and Álvarez-Meza, Andrés Marino and Castellanos-Dominguez, Cesar German},
title = {EEG Signal Prediction for Motor Imagery Classification in Brain–Computer Interfaces},
journal = {Sensors},
year = {2025},
volume = {25},
number = {7},
pages = {2259},
doi = {10.3390/s25072259}
}
EUVIMED