EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing EEG-Based MI-BCIs with Class-Specific and Subject-Specific Features Detected by Neural Manifold Analysis

Mirco Frosolone iD, Roberto Prevete iD, Lorenzo Ognibeni iD, Salvatore Giugliano iD, Andrea Apicella iD, Giovanni Pezzulo iD, Francesco Donnarumma iD

Sensors · 2024

DOI: 10.3390/s24186110 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Mirco Frosolone und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Cognitive Sciences and Technologies, National Research Council, Via Gian Domenico Romagnosi, 00196 Rome, Italy. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Algorithms. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council, European Union—NextGenerationEU, Bayesian inference—Grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents an innovative approach leveraging Neuronal Manifold Analysis of EEG data to identify specific time intervals for feature extraction, effectively capturing both class-specific and subject-specific characteristics. Different pipelines were constructed and employed to extract distinctive features within these intervals, specifically for motor imagery (MI) tasks. The methodology was validated using the Graz Competition IV datasets 2A (four-class) and 2B (two-class) motor imagery classification, demonstrating an improvement in classification accuracy that surpasses state-of-the-art algorithms designed for MI tasks. A multi-dimensional feature space, constructed using NMA, was built to detect intervals that capture these critical characteristics, which led to significantly enhanced classification accuracy, especially for individuals with initially poor classification performance. These findings highlight the robustness of this method and its potential to improve classification performance in EEG-based MI-BCI systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyBrain-Computer InterfacesAlgorithmsHumansSignal Processing, Computer-AssistedImagination

Stichwörter der Autor:innen

EEG-based BCImotor imagery BCIneural manifold analysistransfer learning

Autor:innen und Institutionen

  • Institute of Cognitive Sciences and Technologies, National Research Council, Via Gian Domenico Romagnosi, 00196 Rome, Italy.
  • Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, Italy.
  • Department of Computer, Control and Management Engineering 'Antonio Ruberti' (DIAG), Sapienza University of Rome, 00185 Rome, Italy.

ORCID-Profile: Mirco Frosolone, Roberto Prevete, Lorenzo Ognibeni, Salvatore Giugliano, Andrea Apicella, Giovanni Pezzulo, Francesco Donnarumma

Förderung

  • European Research Council
  • European Union—NextGenerationEU
  • Bayesian inference—Grant

Zitieren

APA

Frosolone, M., Prevete, R., Ognibeni, L., Giugliano, S., Apicella, A., Pezzulo, G., & Donnarumma, F. (2024). Enhancing EEG-Based MI-BCIs with Class-Specific and Subject-Specific Features Detected by Neural Manifold Analysis. Sensors. https://doi.org/10.3390/s24186110

Vancouver

Frosolone M, Prevete R, Ognibeni L, Giugliano S, Apicella A, Pezzulo G, et al. Enhancing EEG-Based MI-BCIs with Class-Specific and Subject-Specific Features Detected by Neural Manifold Analysis. Sensors. 2024. doi:10.3390/s24186110

BibTeX
@article{Frosolone2024,
  author = {Frosolone, Mirco and Prevete, Roberto and Ognibeni, Lorenzo and Giugliano, Salvatore and Apicella, Andrea and Pezzulo, Giovanni and Donnarumma, Francesco},
  title = {Enhancing EEG-Based MI-BCIs with Class-Specific and Subject-Specific Features Detected by Neural Manifold Analysis},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24186110}
}
Kostenlos starten →