C2.2.
An Introduction to Optimal Experimental Design
Roland Herzog, Technische Universität Chemnitz
Email: roland.herzog@mathematik.tu-chemnitz.de
The determination of unknown parameters in mathematical models is an important problem in applied mathematics. The basic idea is to adjust the model parameters in order to obtain the best agreement between the model’s predictions and experimentally observed data. Numerical methods for this problem, which is also known as parameter identification or estimation, and model calibration, are well developed today. In practical applications however, the identified parameters are perturbed by measurement errors. The accuracy can be verified by statistical methods, e.g., confidence regions. This also allows one to differentiate between suitable and less suitable experiments. In optimum experimental design (OED), the goal is to adjust the experimental conditions in order to maximize the estimation
accuracy. This talk will offer an introduction into OED along with illustrative numerical experiments.
Event Timeslots (1)
Viernes 27
-
Conferencia 2.2. - Optimización
Ponencia: An Introduction to Optimal Experimental Design
