查看更多>>摘要：The behavior of two types of finite automata in a non-stationary fuzzy environment is considered, which, depending on the states of the automata, encourages or punishes them with some fixed membership functions. It is assumed that the behavior of automata in a fuzzy environment is described by generalized ergodic Markov chains and, using the property of such chains, it is shown that the considered automata, under certain conditions on fuzzy punishment functions, are learners and predominantly perform the action for which the sum of fuzzy functions of belonging to punishment is minimal.
AZEDDINE HACHMIASMAE ZBIRIDOMINIQUE HAESENFATIMA EZZAHRAE EL ALAOUI-FARIS...
12页
查看更多>>摘要：Working in the virtual world is different to real experiment in field. Nowadays, with remote sensing and new analysis programs we can assure a quick response and with less costs. The problem is efficiency of these methods and formulation of an exact response with low errors to manage an environmental risk. The objective of this article is to ask question about performance of some tools in this decision making in Morocco. The study uses (Test 1: TaylorFit Multivariate Polynomial Regressions (MPR); Test 2: SAS Neural Network (NN) to modeling relationship between European Center for Medium-Range Weather Forecasts dataset and NDVI eMODIS-TERRA at arid Eastern Morocco. The results revealed that the both test could accurately predict future scenario of water stress and livstock production decrease. The experience shows that virtual work with Artificial Intelligence is the future of ecological modeling and rapid decision-making in case of natural disasters.
NSTL