Data-Augmented Numerical Integration in State Prediction: Rule Selection
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_ | 1866913647445409792 |
|---|---|
| author | Dunik, Jindrich Kral, Ladislav Matousek, Jakub Straka, Ondrej Brandner, Marek |
| author_facet | Dunik, Jindrich Kral, Ladislav Matousek, Jakub Straka, Ondrej Brandner, Marek |
| contents | This paper deals with the state prediction of nonlinear stochastic dynamic systems. The emphasis is laid on a solution to the integral Chapman-Kolmogorov equation by a deterministic-integration-rule-based point-mass method. A novel concept of reliable data-augmented, i.e., mathematics- and data-informed, integration rule is developed to enhance the point-mass state predictor, where the trained neural network (representing data contribution) is used for the selection of the best integration rule from a set of available rules (representing mathematics contribution). The proposed approach combining the best properties of the standard mathematics-informed and novel data-informed rules is thoroughly discussed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06376 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data-Augmented Numerical Integration in State Prediction: Rule Selection Dunik, Jindrich Kral, Ladislav Matousek, Jakub Straka, Ondrej Brandner, Marek Signal Processing This paper deals with the state prediction of nonlinear stochastic dynamic systems. The emphasis is laid on a solution to the integral Chapman-Kolmogorov equation by a deterministic-integration-rule-based point-mass method. A novel concept of reliable data-augmented, i.e., mathematics- and data-informed, integration rule is developed to enhance the point-mass state predictor, where the trained neural network (representing data contribution) is used for the selection of the best integration rule from a set of available rules (representing mathematics contribution). The proposed approach combining the best properties of the standard mathematics-informed and novel data-informed rules is thoroughly discussed. |
| title | Data-Augmented Numerical Integration in State Prediction: Rule Selection |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2412.06376 |