Extended and unscented Kalman filtering based feedforward neural networks for time series prediction

DOI10.1016/J.APM.2011.07.052zbMATH Open1243.93115OpenAlexW2050878373MaRDI QIDQ437862FDOQ437862

Authors: Xuedong Wu, Yaonan Wang 

Publication date: 20 July 2012

Published in: Applied Mathematical Modelling (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.apm.2011.07.052

Recommendations

• An application of neural networks trained with Kalman filter variants (EKF and UKF) to heteroscedastic time series forecasting
• Training Dynamic Neural Networks Using the Extended Kalman Filter for Multi-Step-Ahead Predictions
• Nonlinear autoregressive neural network and extended Kalman filters for prediction of financial time series
• A fuzzy neural network based extended Kalman filter
• A modified extended Kalman filter method for multi-layered neural network training

zbMATH Keywords

feedforward neural networknonlinear filtering approachestime series prediction

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inference from stochastic processes and prediction (62M20) Filtering in stochastic control theory (93E11) Neural nets and related approaches to inference from stochastic processes (62M45)

Cites Work

• Oscillation and chaos in physiological control systems
• Title not available (Why is that?)
• Kalman filtering with real-time applications
• Training radial basis neural networks with the extended Kalman filter
• A probabilistic method for assisting knowledge extraction from artificial neural networks used for hydrological prediction

Cited In (7)

• A marginalized unscented Kalman filter for efficient parameter estimation with applications to finite element models
• Filtering based multi-innovation extended stochastic gradient algorithm for Hammerstein nonlinear system modeling
• Multi-step prediction of time series with random missing data
• Nonlinear autoregressive neural network and extended Kalman filters for prediction of financial time series
• Multiple sparse-grid Gauss-Hermite filtering
• An application of neural networks trained with Kalman filter variants (EKF and UKF) to heteroscedastic time series forecasting
• Training Dynamic Neural Networks Using the Extended Kalman Filter for Multi-Step-Ahead Predictions

This page was built for publication: Extended and unscented Kalman filtering based feedforward neural networks for time series prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q437862)