Transactions on Mass-Data Analysis of Images and Signals (ISSN:1868-6451)
Volume 1 - Number 2 - September 2009 - Pages 224-235
Modeling the Immune Mechanism Diagnose
C. Ciufudean1, O. Ciufudean2 and C. Filote1
1Computers and Control Systems Department of the Stefan cel Mare University, University str. 9, 720225, Suceava, Romania 2 Areni Medical Center, Stefan cel Mare str.78, 720229, Suceava, Romania
In this paper we introduce a discrete event system model of immune systems of mammalians using Markov decision processes based on Petri nets models. Based on immunological principles we propose a new approach for the study of the mechanisms that govern the functionality of the immune system. A two-module algorithm that launches a specific action against an anomalous situation is developed and the Petri nets tools are assumed in this approach. Also, Markov decision processes with a truncated state space to the problem with infinite state space are considered. We also propose a new algorithm to build a large model (e.g. a macro-model) of immune mechanisms of mammalians. We conclude that an optimal stationary policy exists and we apply it to a dynamic scheduling problem of the immunological response to external stimuli.