Dengue confirmed-cases prediction: A neural network model

Aburas H., Cetiner B., SARI M.

EXPERT SYSTEMS WITH APPLICATIONS, vol.37, no.6, pp.4256-4260, 2010 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 37 Issue: 6
  • Publication Date: 2010
  • Doi Number: 10.1016/j.eswa.2009.11.077
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.4256-4260
  • Yıldız Technical University Affiliated: No


This research aims to predict the dengue confirmed-cases using Artificial Neural Networks (ANNs). Real data provided by Singaporean National Environment Agency (NEA) was used to model the behavior of dengue cases based on the physical parameters of mean temperature, mean relative humidity and total rainfall. The set of data recorded consists of 14,209 dengue reported confirmed-cases have been analyzed by using the ANNs. It has been produced very encouraging results in this study. The results showed that the four important features namely mean temperature, mean relative humidity, total rainfall and the total number of dengue confirmed-cases were very effective in predicting the number of dengue confirmed-cases. The ANNs have been found to be very effective processing systems for modelling and simulation in the dengue confirmed-cases data assessments. The proposed prediction model can be used world-wide and in any period of time since the approach does not use time information in building it. (C) 2009 Elsevier Ltd. All rights reserved.