Model selection for system identification by means of artificial neural networks
-
Hans Neuner
Abstract.
System identification is one main task in modern deformation analysis. If the physical structure of the monitoring object is unknown or not accessible the system identification is performed in a behavioural framework. Therein the relations between input and output signals are formulated on the basis of regression models. Artificial neural networks (ANN) are a very flexible tool for modelling especially non-linear relationships between the input and the output measures. The universal approximation theorem ensures that every continuous relation can be modelled with this approach. However, some structural aspects of the ANN-based models, like the number of hidden nodes or the number of data needed to obtain a good generalisation, remain unspecified in the theorem. Therefore, one faces a model selection problem. In this article the methodology of modelling the deformations of a lock occurring due to water level and temperature changes is described. We emphasise the aspect of model selection, by presenting and discussing the results of various approaches for the determination of the number of hidden nodes. The first one is cross-validation. The second one is a weight deletion technique based on the exact computation of the Hessian matrix. Finally, the third method has a rigorous theoretical background and is based on the capacity concept of a model structure.
© 2012 by Walter de Gruyter Berlin Boston
Articles in the same Issue
- Masthead
- Editorial: Special Issue on Deformation Monitoring
- Model selection for system identification by means of artificial neural networks
- Adjustment of highly non-linear redundant systems of equations using a numerical, topology-based approach
- Optimized Kalman filter versus rigorous method in deformation analysis
- The application of the model of coordinate S-transformation for stability analysis of datum points in high-precision GPS deformation monitoring networks
- Velocity estimation of GPS base stations considering the coloured noises
- Spectral analysis of structural deformation – A case study
- Ambient vibration monitoring of slender structures by microwave interferometer remote sensing
- A 3-d laser scanning system and scan data processing method for the monitoring of tunnel deformations
- On the detection of systematic errors in terrestrial laser scanning data
- Point-based and plane-based deformation monitoring of indoor environments using terrestrial laser scanners
- Recurring mass movements on the Danube's bank at Dunaszekcső (Hungary) observed by geodetic methods
- Monitoring ground subsidence in Shanghai maglev area using two kinds of SAR data
- Monitoring of surface deformation in Dangxiong using PSInSAR technique
- IAG Commission 4: Mission and contributions to observing and modeling dynamic earth
Articles in the same Issue
- Masthead
- Editorial: Special Issue on Deformation Monitoring
- Model selection for system identification by means of artificial neural networks
- Adjustment of highly non-linear redundant systems of equations using a numerical, topology-based approach
- Optimized Kalman filter versus rigorous method in deformation analysis
- The application of the model of coordinate S-transformation for stability analysis of datum points in high-precision GPS deformation monitoring networks
- Velocity estimation of GPS base stations considering the coloured noises
- Spectral analysis of structural deformation – A case study
- Ambient vibration monitoring of slender structures by microwave interferometer remote sensing
- A 3-d laser scanning system and scan data processing method for the monitoring of tunnel deformations
- On the detection of systematic errors in terrestrial laser scanning data
- Point-based and plane-based deformation monitoring of indoor environments using terrestrial laser scanners
- Recurring mass movements on the Danube's bank at Dunaszekcső (Hungary) observed by geodetic methods
- Monitoring ground subsidence in Shanghai maglev area using two kinds of SAR data
- Monitoring of surface deformation in Dangxiong using PSInSAR technique
- IAG Commission 4: Mission and contributions to observing and modeling dynamic earth
