Fuzzy knowledge- and data-based models of damage to reeds by grazing of Greylag Geese

摘要: Abstract This paper describes a fuzzy and neuro-fuzzy approach to modelling feeding intensity of Greylag Geese on reed. As consequence the presence some non-measurable or random factors heterogeneity reed goose behaviour, relationships between model variables are often not well known data collected have high degree uncertainty. A was selected which can be applied with vague knowledge Fuzzy logic used handle inexact reasoning in knowledge-based models rules sets uncertainty data. The neural network technique develop data-based models. For training, several dataset combinations three lakes North Germany were used. generalisation capability these checked for other lakes. performance compared results developed next step. base this contains Mamdani-type formulated by domain expert. All implemented using Logic Toolbox MATLAB ® .