Record Details

PARTICLE SWARM OPTIMIZATION SEBAGAI PENENTU NILAI BOBOT PADA ARTIFICIAL NEURAL NETWORK BERBASIS BACKPROPAGATION UNTUK PREDIKSI TINGKAT PENJUALAN MINYAK PELUMAS PERTAMINA

Jurnal Ilmiah Informatika

View Archive Info
 
 
Field Value
 
Title PARTICLE SWARM OPTIMIZATION SEBAGAI PENENTU NILAI BOBOT PADA ARTIFICIAL NEURAL NETWORK BERBASIS BACKPROPAGATION UNTUK PREDIKSI TINGKAT PENJUALAN MINYAK PELUMAS PERTAMINA
 
Creator Ridla, Muhammad Ali
 
Subject forecasting sales
neural network
attribute weight
pso
forecasting sales
neural network
attribute weight
pso
 
Description The lubricating oil industry is one part of the oil and gas sector which is still one of the main pillars of economic growth in Indonesia. Sales predictions are needed by companies and policy makers as planning materials and economic development strategies to increase income in the future. Predictions that have a better level of accuracy can provide appropriate decisions. Various methods have been used, the Artificial Neural Network algorithm is one of the most widely used, especially in the Backpropagation (BPNN) structure which can predict non linear time series data. Backpropagation has been proven to have a better level of accuracy compared to econometric methods such as ARIMA. The integration of Backpropagation algorithm with other algorithms needs to be done to overcome the shortcomings and improve the ability of the National Land Agency itself. Particle Swarm Optimization (PSO) which is used as an optimization determinant of attribute weight values in the network structure of BPNN shows good results. After testing, BPNN without PSO has a Squared Error (SE) level of 0.012 and a Root Mean Aquared Error (RMSE) of 0.111. While BPNN with PSO has SE levels of 0.004 and RMSE of 0.059. This shows that there is a significant decrease in the error rate after the PSO algorithm is added to the BPNN structure which is 46.85%.
 
Publisher Department of Science and Technology Ibrahimy University
 
Date 2018-06-21
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article
 
Format application/pdf
 
Identifier https://journal.ibrahimy.ac.id/index.php/JIMI/article/view/473
10.35316/jimi.v3i1.473
 
Source Jurnal Ilmiah Informatika; Vol. 3 No. 1 (2018): Jurnal Imliah Informatika; 183-192
2549-6301
2549-7480
10.35316/jimi.v3i1
 
Language ind
 
Relation https://journal.ibrahimy.ac.id/index.php/JIMI/article/view/473/458
 
Rights Copyright (c) 2018 Jurnal Ilmiah Informatika
https://creativecommons.org/licenses/by-nc/4.0