Editor/Reviewer login
Frequency : 12 issues per year
Subject : Computer Applications and Technology
ISSN : 2319–8656 (Online)
Home Archives Volume 9 Issue 12 ijcatr09121002

IJCATR Volume 9 Issue 12

Prediction of Fleet Demand Needs Using Backpropagation Artificial Neural Networks and Fuzzy Time Series in Sea Release Transport System

Nur Hijriah Zubaedah Narang , Rahmadwati , Erni Yudaningtyas
10.7753/IJCATR0912.1002
keywords : Backpropagation ANN, Fuzzy Times Series, Mean Square Error, Demand, Forecasting

PDF
The number of service users or consumers in choosing the marine ship mode as a means of transportation between Kupang City and Rote Ndao Regency can help service users related to inter-island trading activities, serving shipments of commodities and manufactured goods and sectors. The ability to predict quickly, precisely and accurately the demand for fleet demand is very important for service providers or ship service users. As a case in point, errors in predicting demand needs can result in planning allocations for both additional fleets and planning needs for scheduling operations for marine transport traffic. This study discusses the prediction of fleet demand in the ferry system by taking time series research data. The methods used include Backpropagation ANN and Fuzzy Times Series. The results obtained show that the performance of the backpropagation method which is formed from training data and validated on the testing data provides a fairly good level of prediction accuracy with a mean square error (MSE) value of 0.016, while with the FTS method the MSE value is 0.55.
@artical{n9122020ijcatr09121002,
Title = "Prediction of Fleet Demand Needs Using Backpropagation Artificial Neural Networks and Fuzzy Time Series in Sea Release Transport System",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "9",
Issue ="12",
Pages ="323 - 326",
Year = "2020",
Authors ="Nur Hijriah Zubaedah Narang , Rahmadwati , Erni Yudaningtyas "}
  • Times series data as a basis for predicting fleet demand
  • The prediction of fleet demand needs with time series research data use the Backpropagation compare with the Fuzzy Time Series
  • The dataset is divided intnamely 80% training data (training data) and 20% test data (testing data)
  • The results of this testing process are then evaluated using MSE with the parameter of the level of accuracy of the prediction results of the two methods.
Copyright © 2012-2024 International Journal of Computer Applications Technology and Research All Rights Reserved.