Using Local Weather and Geographical Information to Predict Cholera Outbreaks in Hanoi, Vietnam

Nguyen, Hai Chau and Le, Thi Ngoc Anh (2016) Using Local Weather and Geographical Information to Predict Cholera Outbreaks in Hanoi, Vietnam. Advanced Computational Methods for Knowledge Engineering Volume 453 of the series Advances in Intelligent Systems and Computing, 453 . pp. 195-212. ISSN 2194-5357

PDF Download (804kB)

Abstract

In 2007, repeated outbreaks of cholera in Hanoi have raised the need to have up-to-date evidence on the impact of factors on cholera epidemic, which is essential for developing an early warning system. We have successfully built models to predict cholera outbreaks in Hanoi from 2001 to 2012 using Random Forests method. We found that geographical factors - the number of cholera cases of a district of interest and its neighbours - are very important to predict accurately cholera cases besides the weather factors. Among weather factors, temperature and relative humidity are the most important. We also found that prediction accuracy of our models, measured in adjusted coefficient of determination, will decrease by 0.0076 if prediction length increases by one day.

Item Type:	Article
Subjects:	Information Technology (IT)
Divisions:	Faculty of Information Technology (FIT)
Depositing User:	Hải Châu Nguyễn
Date Deposited:	29 Aug 2016 08:58
Last Modified:	29 Aug 2016 08:58
URI:	http://eprints.uet.vnu.edu.vn/eprints/id/eprint/1838

Actions (login required)

View Item