Optimasi Bobot Jaringan Syaraf Tiruan Mengunakan Particle Swarm Optimization

Abstract

AbstrakMasalah peramalan adalah masalah yang sering ditemukan dalam proses pengambilan keputusan. Tool yang cukup populer untuk menangani masalah peramalan adalah jaringan syaraf tiruan. Jaringan syaraf tiruan banyak digunakan karena kemampuannya untuk meramalkan data nonlinear time series. Algoritma pembelajaran yang sering digunakan untuk memperbaiki bobot pada jaringan syaraf tiruan adalah backpropagation. Namun proses pembelajaran backpropagation terkadang menemui kendala seperti over fiting sehingga tidak dapat menggeneralisasi masalah. Untuk mengatasi masalah tersebut diusulkan penggunaan particle swarm optimization untuk melatih bobot pada jaringan. Performa dari masing-masing model akan diukur dengan mean square error, mean absolute percentage error, normalized mean square error, prediction of change in direction, average relative variance. Untuk keperluan analisis model digunakan data time series inflasi di indonesia. Metode yang diusulkan menunjukan sistem jaringan hybrid mampu menangani masalah peramalan data time series dengan performa mendekati jaringan syaraf tiruan backpropagation.. Kata kunci—jaringan syaraf tiruan, particle swarm optimization, prediction of change in direction, average relative variance. AbstractForecasting problem is common problem that easily found in decision making process. The popular tool to handle that problem is artificial neural network. Artificial neural network have been widely use because its ability to forecast nonlinear time series data. The learning method that have been widely use to train artificial neural network weight is backpropagation. Otherwise backpropagation learning process sometimes find problem such as over fiting so it can’t generalized the problem. Particle swarm optimization method had been proposed to train artificial neural network weigth. Mean square error, mean absolute percentage error, normalized mean square error, prediction of change in direction, average relative variance had been use to measures the model performance. Indonesia inflation time series data had been use to analyzed the model. The proposed method show that hybrid system could handle the time series forecasting problem as good as backpropagation artificial neural network Keywords—artificial neural network, particle swarm optimization, prediction of change in direction, average relative variance.