491. Optimizing real-time MI-BCI performance in post-stroke patients : impact of time window duration on classification accuracy and responsivenessAleksandar Miladinović, Agostino Accardo, Joanna Jarmolowska, Uroš Marušič, Miloš Ajčević, 2024, original scientific article 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
Published in DiRROS: 23.10.2024; Views: 117; Downloads: 477
 Full text (3,37 MB)
This document has many files! More... |
492. |
493. |
494. First Report of Globisporangium (Pythium) mastophorum causing Damping-off / Root Rot on Parsley in SloveniaJanja Zajc, Eva Kovačec, Urša Prislan, Aleksandra Podboj Ronta, Metka Žerjav, Hans-Josef Schroers, 2024, other scientific articles Keywords: damping-off / Root Rot, parsley, pathogen detection, common bean, phatoggenecity
Published in DiRROS: 23.10.2024; Views: 312; Downloads: 61
Full text (225,51 KB) |
495. |
496. |
497. Poročilo o preskusu št.: LVG 2024-157 : vzorec št. 2024/00650Nikica Ogris, Patricija Podkrajšek, Zina Devetak, Špela Hočevar, Barbara Piškur, 2024, expertise, arbitration decision Keywords: varstvo gozdov, morfološke analize, Pseudocercospora pini-densiflorae, rdeči bor, bolezen iglic
Published in DiRROS: 23.10.2024; Views: 144; Downloads: 0
This document has many files! More... |
498. Poročilo o preskusu št.: LVG 2024-156 : vzorec št. 2024/00627Barbara Piškur, Patricija Podkrajšek, Zina Devetak, Nikica Ogris, 2024, expertise, arbitration decision Keywords: varstvo gozdov, morfološke analize, Pseudocercospora pini-densiflorae, rdeči bor, bolezen iglic
Published in DiRROS: 23.10.2024; Views: 134; Downloads: 0
This document has many files! More... |
499. |
500. Poročilo o preskusu št.: LVG 2024-153 : vzorec št. 2024/00608Barbara Piškur, Zina Devetak, Patricija Podkrajšek, Špela Hočevar, Nikica Ogris, 2024, expertise, arbitration decision Keywords: varstvo gozdov, morfološke analize, Pseudocercospora pini-densiflorae, rdeči bor, bolezen iglic
Published in DiRROS: 23.10.2024; Views: 148; Downloads: 0
This document has many files! More... |
