See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/323414227

An ensemble prediction approach to weekly Dengue cases forecasting based on

climatic and terrain conditions

Article  in  Journal of Health and Social Sciences · November 2017

DOI: 10.19204/2017/nnsm3

CITATIONS READS

10 251

3 authors, including:

Matthew Chin Heng Chua Sougata Deb

National University of Singapore National University of Singapore
68 PUBLICATIONS   612 CITATIONS    6 PUBLICATIONS   38 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Deep Learning Models for Drug Discovery View project

Disease and Epidemic Modelling View project

All content following this page was uploaded by Sougata Deb on 06 August 2018.

The user has requested enhancement of the downloaded file.

 An ensemble prediction approach to weekly Dengue cases
forecasting based on climatic and terrain conditions

Sougata Deb, Cleta Milagros Libre Acebedo, Gomathypriya Dhanapal, Chua Matthew Chin Heng

Full version of the peer-reviewed published article is available at:

http://journalhss.com/wp-content/uploads/jhss23_257-272.pdf

Abstract

Introduction: Dengue fever has been one of the most concerning endemic diseases of
recent times. Every year, 50-100 million people get infected by the dengue virus across the
world. Historically, it has been most prevalent in Southeast Asia and the Pacific islands. In
recent years, frequent dengue epidemics have started occurring in Latin America as well.
Changes in global climatic conditions and unplanned urbanization are posited as some of
the key drivers behind these surges.
Method of Study: The relationship between different climatic conditions and the number
of dengue cases recorded weekly in two Latin American cities, viz. San Juan (Puerto Rico)
and Iquitos (Peru) was analyzed. Due to the differences in geographical location and
prevailing climatic conditions, San Juan recorded higher dengue incidences than Iquitos.
Using lagged cross-correlations, this study confirmed the impact of temperature and
vegetation on the number of dengue cases for both cities, though in varied degrees and time
lags. An ensemble of multiple predictive models using an array of data mining techniques at
different stages of model development was built and validated.
Results: The proposed ensemble prediction achieved a mean absolute error of 21.55, 4.26
points lower than the 25.81 obtained by a standard negative binomial model. Most of the
predictors were intuitive and were empirically established as important factors in other
researches. Some of the predictors were new and informative, which have not been
explored in any other relevant studies yet.
Conclusions: Two original contributions were made in this research. Firstly, a focused and
extensive feature engineering aligned with the mosquito lifecycle. Secondly, a novel
covariate pattern-matching based prediction approach using past time series trend of the
predictor variables. Increased accuracy of the proposed model over the benchmark model
proved the appropriateness of the analytical approach for similar epidemic prediction
research.

View publication stats