Using Public Open Data to Predict Dengue Epidemic: Assessment of Weather Variability, Population Density, and Land use as Predictor Variables for Dengue Outbreak Prediction using Support Vector Machine

Chiung Ching Ho; Choo Yee Ting  and Dhesi Baha Raja  nbsp

doi:10.17485/ijst/2018/v11i4/115405

Article

Using Public Open Data to Predict Dengue Epidemic: Assessment of Weather Variability, Population Density, and Land use as Predictor Variables for Dengue Outbreak Prediction using Support Vector Machine

VIEWS 1504
PDF 878

Abstract
Full-Text HTML
Full-Text PDF
How to Cite

Indian Journal of Science and Technology

DOI: 10.17485/ijst/2018/v11i4/115405

Year: 2018, Volume: 11, Issue: 4, Pages: 1-8

Original Article

Using Public Open Data to Predict Dengue Epidemic: Assessment of Weather Variability, Population Density, and Land use as Predictor Variables for Dengue Outbreak Prediction using Support Vector Machine

Chiung Ching Ho¹ , Choo-Yee Ting¹ and Dhesi Baha Raja²

¹ Data Science SIG, Faculty of Computing and Informatics, Multimedia University, Persiaran Multimedia, 63100 Cyberjaya, Selangor DE, Malaysia; [email protected], [email protected]
² Department of Community Medicine & Public Health, Faculty of Medicine and Health Sciences, Universiti Malaysia Sarawak; [email protected]

^*Author for correspondence
Chiung Ching Ho,
Data Science SIG, Faculty of Computing and Informatics, Multimedia University, Persiaran Multimedia, 63100 Cyberjaya, Selangor DE, Malaysia; [email protected]

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: This study was performed to predict dengue outbreaks using predictor variables derived from weather variability, population density, land use and elevation in Malaysia. Methods: We used publicly available data associated with dengue from the Malaysian open data platform and historical dengue case data from the Ministry of Health Malaysia. We investigated the correlations between predictor variables related to Weather Variability, Population Density, Residential Building Types and Construction Sites; with that of outbreaks of dengue in the chosen site of study, and used the Support Vector Machine classifier to predict outbreak of dengue fever. Results: The model we proposed was evaluated through cross-validation, and returned an accuracy rate of 88.62%, while sensitivity was 93%, and specificity was recorded at 79.32%. Population density had the highest correlation with predicted dengue fever outbreak. Conclusions: In this study, we assessed weather variability, population density, and land use as predictor variables for predicting dengue fever outbreak using a Support Vector Machine classifier.

Keywords: Dengue, Infectious Disease, Meteorology, Projection and Predictions, Support Vector Machine