Ahsar Symomath_2015 Parameter Estimation in a Fuzzy Dynamical System: A Preliminary Study
Muhammad Ahsar K. (1,2), Agus Yodi Gunawan (2), Kuntjoro Adji Sidarto (2), Mochamad Apri (2)
(1) Faculty of Mathematics and Natural Sciences, Lambung Mangkurat University, Banjarbaru, Indonesia
(2) Department of Mathematics, Institut Teknologi Bandung, Bandung 40132, Indonesia
m_ahsar@unlam.ac.id
Abstract
Measurement from experiments often consists of uncertainty. This is possibly due to the limitations of available data taken from experiment. For example, in a biochemical system a number of experiments must be carried out to obtain data accurately. However, in reality, such efforts are limited by, for example, availability of technology, time, and cost. When we model this phenomenon, this uncertainty may lead to unreliable estimation of model parameters. To accommodate the uncertainty, each dependent variable will be assumed to have uncertainty in the terms of fuzzy variables. Application of fuzzy arithmetic to the model leads to a-cut deterministic models with extra numbers of equations. We then solve the deterministic equations and estimate the parameters of the system. As an illustration, we apply our method to a simple population growth model.
Keywords: fuzzy arithmetic, fuzzy variables, a-cut deterministic models
References
[1] Apri M., Tackling Complex Models in Systems Biology, Thesis, Wegeningen University, Wegeningen, 2013.
[2] Hanss M., Applied Fuzzy Arithmetic: An Introduction with Engineering Applications, Springer, Stuttgart, 2004
[3] Massad E. dkk., Fuzzy Logic in Action: Applications in Epidemiology and Beyond, Springer-Verlag Berlin Heidelberg, Berlin, 2008
[4] Zadeh L. A., Fuzzy Sets, Information and Control, 8 (1965), 338 – 353.
Note: Telah diseminarkan pada The 3rd Symposium of BioMathematics (Symomath 2015)
