Identifikasi jenis shorea menggunakan jaringan syaraf tiruan propagasi balik berdasarkan karakteristik morfologi daun

Abstract

Dipterocarpaceae is a major timber tree of tropical rain forest. Shorea is a genus of the Dipterocarpaceae family which consists of around 194 species. Species diversity may lead to difficulty in distinguishing species of Shorea of one another. It takes knowledge from an expert in the field of Shorea to be able to identify the types of Shorea. Errors in identifying the type of Shorea wood can lead to inappropriate selection for the final usability. Identifying the type of Shorea carried out on five species of Shorea owned Bogor Botanical Gardens on the basis of morphological characteristics of leaves. The identification was carried out using Backpropagation Neural Network. To obtain the values of each leaf morphological characteristics of Shorea, each sample measurement data collected manually. The values are then processed using Backpropagation Neural Network to get the pattern from the training and the accuracy of the test phase. This research used a total of 50 data from five species of Shorea. The data are divided into five subsets. The fifth subset is used in the training and testing phases and conducted five times. The use of methods Backpropagation neural networks in identifying species Shorea produces an average accuracy of 90%.