Analysis of agricultural data with multivariate nonlinear fuzzy regression method

The problems encountered in the real world and within are filled with complexity and uncertainty. Fuzzy logic and its related methods provide researchers with appropriate views on nature and are among the dynamic methods developed to quantify uncertainty. It is determined that there are some nonspecific phenomena in the structure of the system related to the nonlinear regression problem examined within the scope of the thesis study. It is aimed to create a model that can make more accurate estimations according to the classical methods by giving a new perspective to the literature with the fuzzy regression method, which has been started to be used in agricultural field. The univariate and multivariate nonlinear fuzzy regression analyses of fuzzy data related to egg performance and egg weight variables are structured to be integrated with artificial neural networks and least squares support vector machines. The results of nonlinear fuzzy regression estimates are compared with the results of both univariate and multivariate nonlinear classical regression analysis. It has been determined that an intelligent system with fuzzified characters at this point performs better than conventional methods. The results of the analysis show that multivariate nonlinear fuzzy regression analysis can be used as an alternative to classical nonlinear regression analysis.