Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System
Recently, artificial neural networks, especially feedforward neural networks, have been widely used for the identification and control of nonlinear dynamical systems. However, the determination of a suitable set of structural and learning parameter value of the feedforward neural networks still rema...
| Main Author: | |
|---|---|
| Format: | Journal Article |
| Published: |
Springer Link
2012
|
| Online Access: | http://hdl.handle.net/20.500.11937/45184 |
| _version_ | 1848757212689727488 |
|---|---|
| author | Saptoro, Agus |
| author_facet | Saptoro, Agus |
| author_sort | Saptoro, Agus |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Recently, artificial neural networks, especially feedforward neural networks, have been widely used for the identification and control of nonlinear dynamical systems. However, the determination of a suitable set of structural and learning parameter value of the feedforward neural networks still remains a difficult task. This paper is concerned with the use of extended Kalman filter and unscented Kalman filter based feed forward neural networks training algorithms. The comparisons of the performances of both algorithms are discussed and illustrated using a simulated example. The simulation results show that in terms of mean squared errors, unscented Kalman filter algorithm is superior to the extended Kalman filter and backpropagation algorithms since there are improvements between 2.45–21.48% (for training) and 8.35–29.15% (for testing). This indicates that unscented Kalman filter based feedforward neural networks learning could be a good alternative in artificial neural network models based applications for nonlinear dynamical systems. |
| first_indexed | 2025-11-14T09:24:30Z |
| format | Journal Article |
| id | curtin-20.500.11937-45184 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T09:24:30Z |
| publishDate | 2012 |
| publisher | Springer Link |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-451842017-09-13T15:57:24Z Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System Saptoro, Agus Recently, artificial neural networks, especially feedforward neural networks, have been widely used for the identification and control of nonlinear dynamical systems. However, the determination of a suitable set of structural and learning parameter value of the feedforward neural networks still remains a difficult task. This paper is concerned with the use of extended Kalman filter and unscented Kalman filter based feed forward neural networks training algorithms. The comparisons of the performances of both algorithms are discussed and illustrated using a simulated example. The simulation results show that in terms of mean squared errors, unscented Kalman filter algorithm is superior to the extended Kalman filter and backpropagation algorithms since there are improvements between 2.45–21.48% (for training) and 8.35–29.15% (for testing). This indicates that unscented Kalman filter based feedforward neural networks learning could be a good alternative in artificial neural network models based applications for nonlinear dynamical systems. 2012 Journal Article http://hdl.handle.net/20.500.11937/45184 10.1134/S0040579512030074 Springer Link restricted |
| spellingShingle | Saptoro, Agus Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System |
| title | Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System |
| title_full | Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System |
| title_fullStr | Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System |
| title_full_unstemmed | Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System |
| title_short | Extended and Unscented Kalman Filters for Artificial Neural Network Modelling of a Nonlinear Dynamical System |
| title_sort | extended and unscented kalman filters for artificial neural network modelling of a nonlinear dynamical system |
| url | http://hdl.handle.net/20.500.11937/45184 |