InceptionTime vs. Wavelet -- A comparison for time series classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909152875380736 |
|---|---|
| author | Klenkert, Daniel Schaeffer, Daniel Stauch, Julian |
| author_facet | Klenkert, Daniel Schaeffer, Daniel Stauch, Julian |
| contents | Neural networks were used to classify infrasound data. Two different approaches were compared. One based on the direct classification of time series data, using a custom implementation of the InceptionTime network. For the other approach, we generated 2D images of the wavelet transformation of the signals, which were subsequently classified using a ResNet implementation. Choosing appropriate hyperparameter settings, both achieve a classification accuracy of above 90 %, with the direct approach reaching 95.2 %. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18687 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InceptionTime vs. Wavelet -- A comparison for time series classification Klenkert, Daniel Schaeffer, Daniel Stauch, Julian Machine Learning I.5.4; J.2 Neural networks were used to classify infrasound data. Two different approaches were compared. One based on the direct classification of time series data, using a custom implementation of the InceptionTime network. For the other approach, we generated 2D images of the wavelet transformation of the signals, which were subsequently classified using a ResNet implementation. Choosing appropriate hyperparameter settings, both achieve a classification accuracy of above 90 %, with the direct approach reaching 95.2 %. |
| title | InceptionTime vs. Wavelet -- A comparison for time series classification |
| topic | Machine Learning I.5.4; J.2 |
| url | https://arxiv.org/abs/2403.18687 |