| Title: | Optimizing real-time MI-BCI performance in post-stroke patients : impact of time window duration on classification accuracy and responsiveness |
|---|
| Authors: | ID Miladinović, Aleksandar (Author)
ID Accardo, Agostino (Author)
ID Jarmolowska, Joanna (Author)
ID Marušič, Uroš (Author)
ID Ajčević, Miloš (Author) |
|---|
| Files: |  URL - Source URL, visit https://doi.org/10.3390/s24186125
URL - Source URL, visit https://www.mdpi.com/1424-8220/24/18/6125
 PDF - Presentation file, download (3,37 MB)
MD5: 99452FE06A9F70A772AE0A7E6A4B9440
|
|---|
| Language: | English |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: |  ZRS Koper - Science and Research Centre Koper
|
|---|
| Abstract: | 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. |
|---|
| Keywords: | BCI, EEG, classification, motor imagery |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 10.09.2024 |
|---|
| Article acceptance date: | 19.09.2024 |
|---|
| Publication date: | 22.09.2024 |
|---|
| Year of publishing: | 2024 |
|---|
| Number of pages: | 13 str. |
|---|
| Numbering: | Vol. 24, no. 18 |
|---|
| PID: | 20.500.12556/DiRROS-20588  |
|---|
| UDC: | 612.8:004.891 |
|---|
| ISSN on article: | 1424-8220 |
|---|
| DOI: | 10.3390/s24186125 |
|---|
| COBISS.SI-ID: | 212716035 |
|---|
| Copyright: | © 2024 by the authors |
|---|
| Note: | Nasl. z nasl. zaslona;
Opis vira z dne 23. 10. 2024;
|
|---|
| Publication date in DiRROS: | 23.10.2024 |
|---|
| Views: | 16 |
|---|
| Downloads: | 15 |
|---|
| Metadata: |    |
|---|
|
:
|
Copy citation |
|---|
| | | | Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
