Predictive deep learning models for analyzing discrete fractional dynamics from noisy and incomplete data

[EN] We study the accuracy of machine learning methods for inferring the parameters of noisy fractional Wu¿Baleanu trajectories with some missing initial terms. Our model is based on a combination of convolutional and recurrent neural networks (LSTM), which permits the extraction of characteristics...

Descripción completa

Detalles Bibliográficos
Autores: Garibo-i-Orts, Óscar, Lizama, Carlos, Akgül, Alí, Conejero, J. Alberto|||0000-0003-3681-7533
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/214758
Acceso en línea:https://riunet.upv.es/handle/10251/214758
Access Level:acceso abierto
Palabra clave:Dynamical systems
Discrete fractional calculus
Wu Baleanu model
Logistic map
Convolutional neural networks
LSTM networks
MATEMATICA APLICADA
04.- Garantizar una educación de calidad inclusiva y equitativa, y promover las oportunidades de aprendizaje permanente para todos
Descripción
Sumario:[EN] We study the accuracy of machine learning methods for inferring the parameters of noisy fractional Wu¿Baleanu trajectories with some missing initial terms. Our model is based on a combination of convolutional and recurrent neural networks (LSTM), which permits the extraction of characteristics from trajectories while preserving time dependency. We show that these approach exhibit good accuracy results despite the poor quality of the data.