EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimizing Real-Time MI-BCI Performance in Post-Stroke Patients: Impact of Time Window Duration on Classification Accuracy and Responsiveness

Aleksandar Miladinović iD, Agostino Accardo, Joanna Jarmolowska, Uros Marusic iD, Miloš Ajčević iD

Sensors · 2024

DOI: 10.3390/s24186125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Aleksandar Miladinović und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Maternal and Child Health-IRCCS "Burlo Garofolo", 34137 Trieste, Italy. Hauptthemen laut MEDLINE: Brain-Computer Interfaces, Electroencephalography, Support Vector Machine, Stroke. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Interreg, Interreg V-A Italia-Slovenia 2014–2020 Programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain–computer interfaces (BCIs) are promising tools for motor neurorehabilitation. Achieving a balance between classification accuracy and system responsiveness is crucial for real-time applications. This study aimed to assess how the duration of time windows affects performance, specifically classification accuracy and the false positive rate, to optimize the temporal parameters of MI-BCI systems. We investigated the impact of time window duration on classification accuracy and false positive rate, employing Linear Discriminant Analysis (LDA), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) on data acquired from six post-stroke patients and on the external BCI IVa dataset. EEG signals were recorded and processed using the Common Spatial Patterns (CSP) algorithm for feature extraction. Our results indicate that longer time windows generally enhance classification accuracy and reduce false positives across all classifiers, with LDA performing the best. However, to maintain the real-time responsiveness, crucial for practical applications, a balance must be struck. The results suggest an optimal time window of 1–2 s, offering a trade-off between classification performance and excessive delay to guarantee the system responsiveness. These findings underscore the importance of temporal optimization in MI-BCI systems to improve usability in real rehabilitation scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain-Computer InterfacesElectroencephalographySupport Vector MachineStrokeHumansMaleFemaleAlgorithmsMiddle AgedStroke RehabilitationAgedDiscriminant AnalysisTime Factors

Stichwörter der Autor:innen

BCIEEG classificationmotor imagery

Autor:innen und Institutionen

  • Institute for Maternal and Child Health-IRCCS "Burlo Garofolo", 34137 Trieste, Italy.
  • Department of Engineering and Architecture, University of Trieste, 34127 Trieste, Italy.
  • Science and Research Centre Koper, Institute for Kinesiology Research, 6000 Koper, Slovenia.
  • Department of Health Sciences, Alma Mater Europaea University, 2000 Maribor, Slovenia.

ORCID-Profile: Aleksandar Miladinović, Uros Marusic, Miloš Ajčević

Förderung

  • Interreg
  • Interreg V-A Italia-Slovenia 2014–2020 Programme

Zitieren

APA

Miladinović, A., Accardo, A., Jarmolowska, J., Marusic, U., & Ajčević, M. (2024). Optimizing Real-Time MI-BCI Performance in Post-Stroke Patients: Impact of Time Window Duration on Classification Accuracy and Responsiveness. Sensors. https://doi.org/10.3390/s24186125

Vancouver

Miladinović A, Accardo A, Jarmolowska J, Marusic U, Ajčević M. Optimizing Real-Time MI-BCI Performance in Post-Stroke Patients: Impact of Time Window Duration on Classification Accuracy and Responsiveness. Sensors. 2024. doi:10.3390/s24186125

BibTeX
@article{Miladinovi2024,
  author = {Miladinović, Aleksandar and Accardo, Agostino and Jarmolowska, Joanna and Marusic, Uros and Ajčević, Miloš},
  title = {Optimizing Real-Time MI-BCI Performance in Post-Stroke Patients: Impact of Time Window Duration on Classification Accuracy and Responsiveness},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24186125}
}
Kostenlos starten →