Low complexity surrogate models
![Low complexity surrogate models](/var/ezflow_site/storage/images/istrazivanja/zavodi-i-centri/zel-zavod-za-elektroniku/lis-laboratorij-za-informacijske-sustave/maric-i-ivek-rad-2011/63383-2-cro-HR/Maric-i-Ivek-rad-2011.jpg)
Marić, I., Ivek, I. Self-Organizing Polynomial Networks for Time-Constrained Applications. // IEEE transactions on industrial electronics, DOI: 10.1109/TIE.2010.2051934, vol. 58, no. 5, May 2011, pp. 2019-2029.
We are dealing with the procedures for meta-modeling of complex systems and algorithmsaiming to build high-accuracy and low-complexity surrogate models applicable to real-timesystems. We are developing new algorithms and metrics for the optimization of models.The efficiency of the surogate models has been verified in real-time calculationof fluid properties and the compensation of fluid flowrate error. The derived procedures can besuccessfuly applied to complex systems modeling in various research areas.