Grey Wolf Optimization-Based Big Data Analytics for Dengue Outbreak Prediction
In recent decades, dengue fever (DF) and dengue hemorrhagic fever (DHF) outbreaks have occurred frequently in many tropical and subtropical regions of Asia. Big data-driven analytics are recently facilitated on the large dataset to monitor climate-driven changes and also for the dengue outbreak prediction. Many past studies have established an association between the meteorological variables and the dengue incidence. Hence, this paper examines the effects of meteorological factors on dengue incidence in one of the climatic categories of the tropical region in Asia. The nine meteorological parameters and number of dengue cases per week were considered in this study. Subsequently, the most influencing variables of dengue incidence were selected using a new heuristic optimization algorithm such as grey wolf optimization (GWO) based on Adaptive Neuro-Fuzzy Inference System (ANFIS) followed by negative binomial regression model which was employed to evaluate various lag times between dengue incidences and meteorological variables. Therefore, the derived meteorological variables with a time lag period are utilized for the big data analytics of dengue outbreak prediction.
KeywordsDengue Feature selection Optimization algorithm Grey wolf optimization Negative binomial regression
- 4.WHO: Dengue guidelines for diagnosis, treatment, prevention and control: World Health Organization. 1–147 p (2009)Google Scholar
- 11.Fairos, W.Y.W., Azaki, W.H.W., Alias, M., Wah, Y.B.: Modelling dengue fever (DF) and dengue hemorrhagic fever (DHF) outbreak using Poisson and negative binomial model. World Acad. Sci. Eng. Technol. Int. J. Math. Comput. Nat. Phys. Eng. 4(2) (2010)Google Scholar
- 14.Honda, Y., Ono, M.: Issues in health risk assessment of current and future heat extremes. Glob. Health Action 2 (2009)Google Scholar
- 15.Epidemiology Unit, Ministry of Health, Sri Lanka. http://www.epid.gov.lk/web/index.php
- 17.Kira, K., Rendell, L.: The feature selection problem: traditional methods and a new algorithm. In: Proceedings of AAAI’92, San Jose, CA, AAAI (press) (1992)Google Scholar