Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2311.15654 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910602231808000 |
|---|---|
| author | Azib, Menouar Renard, Benjamin Garnier, Philippe Génot, Vincent André, Nicolas |
| author_facet | Azib, Menouar Renard, Benjamin Garnier, Philippe Génot, Vincent André, Nicolas |
| contents | Event detection in time series is a challenging task due to the prevalence of imbalanced datasets, rare events, and time interval-defined events. Traditional supervised deep learning methods primarily employ binary classification, where each time step is assigned a binary label indicating the presence or absence of an event. However, these methods struggle to handle these specific scenarios effectively. To address these limitations, we propose a novel supervised regression-based deep learning approach that offers several advantages over classification-based methods. Our approach, with a limited number of parameters, can effectively handle various types of events within a unified framework, including rare events and imbalanced datasets. We provide theoretical justifications for its universality and precision and demonstrate its superior performance across diverse domains, particularly for rare events and imbalanced datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_15654 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Event Detection in Time Series: Universal Deep Learning Approach Azib, Menouar Renard, Benjamin Garnier, Philippe Génot, Vincent André, Nicolas Machine Learning Event detection in time series is a challenging task due to the prevalence of imbalanced datasets, rare events, and time interval-defined events. Traditional supervised deep learning methods primarily employ binary classification, where each time step is assigned a binary label indicating the presence or absence of an event. However, these methods struggle to handle these specific scenarios effectively. To address these limitations, we propose a novel supervised regression-based deep learning approach that offers several advantages over classification-based methods. Our approach, with a limited number of parameters, can effectively handle various types of events within a unified framework, including rare events and imbalanced datasets. We provide theoretical justifications for its universality and precision and demonstrate its superior performance across diverse domains, particularly for rare events and imbalanced datasets. |
| title | Event Detection in Time Series: Universal Deep Learning Approach |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2311.15654 |