EEG Motor Imagery Classification using Frequency-Domain and Spatial Filtering Methods: A Comparative Study
Fuente:
Zenodo
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Langue: | anglais |
| Publié: |
Zenodo
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901839261204480 |
|---|---|
| author | Satyamoorthy, Amrutha |
| author_facet | Satyamoorthy, Amrutha |
| contents | <p>This technical report presents a comparative evaluation of bandpower and CSP-based feature extraction for EEG motor imagery classification. Using PhysioNet EEGBCI data from three subjects, Logistic Regression with bandpower features achieved 67.4% accuracy (F1: 0.683), outperforming CSP features (61.5%, F1: 0.660) in a 5-fold cross-validation setup. Full code and methodology<br>are documented for reproducibility.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19118710 |
| institution | Zenodo |
| language | eng |
| publishDate | 2023 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | EEG Motor Imagery Classification using Frequency-Domain and Spatial Filtering Methods: A Comparative Study Satyamoorthy, Amrutha EEG BCI Bandpower CSP Motor Imagery Machine Learning Logistic Regression PhysioNet <p>This technical report presents a comparative evaluation of bandpower and CSP-based feature extraction for EEG motor imagery classification. Using PhysioNet EEGBCI data from three subjects, Logistic Regression with bandpower features achieved 67.4% accuracy (F1: 0.683), outperforming CSP features (61.5%, F1: 0.660) in a 5-fold cross-validation setup. Full code and methodology<br>are documented for reproducibility.</p> |
| title | EEG Motor Imagery Classification using Frequency-Domain and Spatial Filtering Methods: A Comparative Study |
| topic | EEG BCI Bandpower CSP Motor Imagery Machine Learning Logistic Regression PhysioNet |
| url | https://doi.org/10.5281/zenodo.19118710 |