Uncertainty Quantification for cross-subject Motor Imagery classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910367296258048 |
|---|---|
| author | Manivannan, Prithviraj de Jong, Ivo Pascal Valdenegro-Toro, Matias Sburlea, Andreea Ioana |
| author_facet | Manivannan, Prithviraj de Jong, Ivo Pascal Valdenegro-Toro, Matias Sburlea, Andreea Ioana |
| contents | Uncertainty Quantification aims to determine when the prediction from a Machine Learning model is likely to be wrong. Computer Vision research has explored methods for determining epistemic uncertainty (also known as model uncertainty), which should correspond with generalisation error. These methods theoretically allow to predict misclassifications due to inter-subject variability. We applied a variety of Uncertainty Quantification methods to predict misclassifications for a Motor Imagery Brain Computer Interface. Deep Ensembles performed best, both in terms of classification performance and cross-subject Uncertainty Quantification performance. However, we found that standard CNNs with Softmax output performed better than some of the more advanced methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09228 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Uncertainty Quantification for cross-subject Motor Imagery classification Manivannan, Prithviraj de Jong, Ivo Pascal Valdenegro-Toro, Matias Sburlea, Andreea Ioana Machine Learning Computer Vision and Pattern Recognition Uncertainty Quantification aims to determine when the prediction from a Machine Learning model is likely to be wrong. Computer Vision research has explored methods for determining epistemic uncertainty (also known as model uncertainty), which should correspond with generalisation error. These methods theoretically allow to predict misclassifications due to inter-subject variability. We applied a variety of Uncertainty Quantification methods to predict misclassifications for a Motor Imagery Brain Computer Interface. Deep Ensembles performed best, both in terms of classification performance and cross-subject Uncertainty Quantification performance. However, we found that standard CNNs with Softmax output performed better than some of the more advanced methods. |
| title | Uncertainty Quantification for cross-subject Motor Imagery classification |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.09228 |