Sistem Klasifikasi Khasiat Formula Jamu Dengan Metode Voting Feature Interval 5

Abstract

Jamu is Indonesian traditional medicine consisting of foliage, fruits, roots and other ingredients natural materials. Herbal medicine has variations of formula comprising a combination of hundreds of medicinal plants herbal formula so that the classification process is an interesting issue to be investigated. The purpose of this research is to create a classification system based on the composition of medicinal properties of plants using Voting Feature Intervals 5 (VFI5) method. This study also tried to generate the weights of each plant as the important information in the formula of Jamu. The weights are yielded based on the intensity of the occurencies of plant in Jamu ingredients. The results of this study will be compared to the previous studies using Partial Least Square – Discriminant Analysis ( PLSDA ) and Support Vector Machine (SVM). The accuracy of the proposed method is 94% comparable to those of the previous studies using PLS-DA and SVM. However, the proposed method perform faster than those of using PLS-DA and SVM in term of computation time. In addition, this research can be used to find existing plants that cause incorect results in the classification process.