PREDIKSI KUALITAS HASIL HUTAN LAHAN BASAH MENGGUNAKAN BACKPROPAGATION

Abstract

Many forests are wetlands plant palm or tribe (family) Arecaceae. One type is the coconut (Cocos nucifera) is often utilized all its parts including stem used for wood materials, the process of selecting coconut wood are used as ingredients of a product made by a grader trained by observing the wood directly without using tools (manual). The method of causing dependence expertise and experience in the selection of a grader coconut wood. With the limitations of a grader, then arises a problem when a large number of coconut wood objects tested manually exceeds the capacity of a grader. Therefore, the grouping of coconut wood needs to be made with intelligent systems that can overcome these problems. Determination of coconut wood can be automatically built using backpropagation method to identify the parameters of the determining characteristics of coconut wood obtained from coconut wood image of two-dimensional (2D). Determination of coconut wood characteristic parameters based on the extraction of texture features based on the image histogram 2D coconut wood. Features texture obtained from the histogram method is among others: the mean intensity, standard deviation, skewness, energy, entropy, and subtlety. This paper describes the determination of the quality of coconut timber using back propagation algorithm based on coconut wood texture 2D image.