Fuzzification of rubber tree white root disease based on leaf´s discolouration

This paper describes research work in developing an intelligent model for detecting white root disease stages by using fuzzy logic. In this work, classification of three stages of white root disease is based on discolouration of the tree´s leaf. These stages are healthy, medium & worse and each of them were tested with respect to vein, main vein and peteolute. The reflectance of the leaves discolouration sample is measured by using MCS600 Carl Zeiss spectrometer. Analysis and justification are done statistically for features extraction and selection as input for fuzzy system. From the statistical result there is strong evidence that the stages of the white root disease can be discriminated from each other. Input value for the fuzzy system, based on the selection of the result from statistic software. Two inputs have been selected to be the input for the fuzzy system which are main vein and vein. Overall performance of the system is 78.33% accuracy after being tested with 300 samples in order to distinguish healthy, medium and worse respectively.