Optimation fuzzy Inference System using Genetic Algorithm for Book Publication Amount Prediction (Case Study in LIPI Press).

Abstract

The research covers the problems in the planning of the LIPI Press publishes scholarly works LIPI, one of them is to predict the number of publications for the following year. The purpose of this study is to optimize the parameters of fuzzy inference system using a genetic algorithm, to predict the number of publications issued LIPI Press for the following year wether it is optimal with the predictors used is the number of units of work, the amount of effort and a long process. The data used is the production data from LIPI Press in five years. The method used is genetic algorithm method. K fold validation is used to split the data training and data testing. The results of this study is the achievement of the publication of an optimal prediction using genetic algorithm parameters which were composed of both population size (30), the probability of crossover (0.75), the probability of mutation (0.01) and the number of generations (150). By the achievement of optimal prediction results are then published a book planning would be better.