Automatic clustering of data from sampling and evaluating of neuro-fuzzy network forestimatinge the distribution of Bemisia. tabaci (Hem.:Aleyrodidae)

In this study, Neuro Fuzzy network was used to estimate the spatial distribution of Bemisia tabaci in a cucumber field in Behbahan. Pest density assessments were performed based on a 10 m × 10 m grid pattern pattern and a total of 100 sampling units in. In this method latitude and longitude information was used the input data and output of method showed the number of pest. To determine the sensitivity of this method to different levels of the pest after collecting samples, automatic clustering method was used to determine the number of clusters Davies and Bouldin index was used to evaluae criterion. In order to finding the answer, Clustering Search Space Genetic Algorithm was used.Davies and Bouldin index (0.46) showed that the data should be divided into three clusters. Results indicated average, variance, statistical distribution and also coefficient of determination in the observed and the estimated Bemisia tabaci density were not significantly different.Our map showed that patchy pest distribution offers large potential for using site-specific pest control on this field.