2004 
output data, in other words the less noise in output data would Deformation Measurements, Hong Kong, June 25 — 28, pp. 
increase the approximation quality as well. 147-156 
Neural networks can be considered as efficient tools for the 
description of deformations, especially in continuous 
monitoring of engineering structures where there is no a priori 
| knowledge on the underlying deformation processes or where 
the relations between the acting forces and the behaviour of the 
| monitored object is very complex to be described by 
| 
| 
| 
| 
| 
/ International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXX V, Part B7. Istanbul 2004 
| 
| 
| 
conventional mathematical tools. 
| References 
ition | Bishop, C. M., 1995. Neural networks for pattern recognition. 
s for | Oxford University Press. 
| 
| Chatfield, C., 1975. The analysis of time series: an 
wide introduction. Chapman and Hall. 
ulting | 
errors Haykin, S., 1994. Neural networks: a comprehensive 
ces of | Joundation, Maxwell Macmillan Int, New York. 
le 2). | 
| Heine, K. 1999, Beschreibung von Deformationsprozessen 
| durch Volterra und Fuzzy Modelle sowie Neuronale Netze. 
| Dissertation. Deutsche Geodaetische Kommission, Reihe C, 
nation | Heft No. 516 
s such | 
or the | Heunecke, O., Pelzer, H., 1998. A new terminology for 
using deformation analysis models based on system theory. In: 
odetic | Kahmen H., Briickl E., Wunderlich T. (Eds.): IAG Symposium 
mined | on Geodesy for Geotechnical and Structural Engineering, 
eurons | Eisenstadt, April 20-22, pp. 285-292 
utputs, 
ypical | Heunecke, O., 1995. Zur Identifikation und Verifikation von 
Deformationsprozessen mittels adaptiver Kalman-Filterung 
rk are | (Hannoversches Filter).  Wissenschaftliche Arbeiten der 
ts, and | fachrichtung Vermessungswesen der Universtaet Hannover, No. 
able of | 208, Hannover. 
etwork 
to any | Miima, J. B., Niemeier, W., 2004. Adapting neural networks for 
of the modelling structural behavior in  geodetic deformation 
ecially monitoring, Z/V, to be published. 
ettings 
re, the Miima, J. B., Niemeier, W., Kraus, B., 2001. A neural network 
lution. approach to modelling geodetic deformations. In: Carosio A., 
among Kutterer H. (Eds): First International Symposium on Robust 
ion of Statistics and Fuzzy Techniques in Geodesy and GIS, ETH 
Zurich, March 12-16, pp. 111-116. 
sed for 
earning Pfeufer, A., 1994. Classification of models for geodetic 
ayer as 
examination of deformations. Final paper of the Ad Hoc 
kept as 
Committee on Classification on Models and Terminology. By 
ig and G. Milev, A. Pfeufer, W. Proszynski, G. Steinberg, W. Teskey, 
W. Welsch, In: Perelmuter Workshop on Dynamic Deformation 
ry good Models, August 29- September,1 Haifa. 
impling 
of input Welsch, W., Heunecke, O., 1999. Terminology and Classi- 
ing and fication of Deformation Models. In: 9" International FIG- 
data is Symposium on Deformation Measurements, Olsztyn, September 
y using 27-30, pp. 416-429 if, 
accurate 
Welsch, W., 1996. Geodetic analysis of dynamic processes: 
Classification and terminology. 8" International Symposium on 
707