Estimation of Kinetic Parameters in Stochastic Biomedical Models Using Estimation Theory

IEEE International Symposium on Intelligent Systems and Informatics (SISY), vol. ch 7, pp. 15–20

Abstract

This paper presents an analytic learning approach to estimate the kinetic parameters in stochastic Petri Nets. Stochastic Petri Nets are very useful to describe time dependent processes in medical and biomedical applications. To be able to model processes more accurately and reliably without prior knowledge of the process, it is essential to automatically build these mathematical models based on measured data. Besides the structural parameters, stochastic Petri Nets are defined by a set of kinetic parameters that give the model its dynamics. Efficient and reliable estimation of these kinetic parameters is enormously important for the simulation of the model to output useful results. Therefore a new method is presented that determines these kinetic parameters based on estimation theory. Simulations show that the new analytic algorithm is similar in precision and trueness but multiple orders faster than an iterative evolutionary algorithm.

Authors 4

1. Lukas David Schuck Aachen Research Area ISEK

   RWTH Aachen University

   Affiliation as printed

   Research Area ISEK, RWTH Aachen University, Germany

2. Lejla Begic Fazlic

   Trier University of Applied Sciences

   Affiliation as printed

   Environmental Campus Birkenfeld, Trier University of Applied Sciences, Germany

3. Guido Dartmann

   Trier University of Applied Sciences

   Affiliation as printed

   Environmental Campus Birkenfeld, Trier University of Applied Sciences, Germany

4. Anke Schmeink Aachen Research Area ISEK

   RWTH Aachen University

   Affiliation as printed

   Research Area ISEK, RWTH Aachen University, Germany