Dengue Spread Modeling in the Absence of Sufficient Epidemiological Parameters: Comparison of SARIMA and SVM Time Series Models

11 Pages Posted: 14 Dec 2017

See all articles by Jerelyn Co

Jerelyn Co

Ateneo de Manila University - Computer Science, Students

Jason Allan Tan

Ateneo de Manila University, Students

Regina Justina Estuar

Ateneo de Manila University

Kennedy Espina

Ateneo de Manila University, Students

Date Written: October 16, 2017

Abstract

Dengue remains to be a major public health concern in the Philippines, claiming hundreds of lives every year ( Jaymalin 2017). Given limited data for deriving necessary epidemiological parameters in developing deterministic disease models, forecasting as a means in controlling and anticipating outbreaks remains a challenge. In this study, two-time series models, namely Seasonal Autoregressive Integrated Moving Average (SARIMA) and Support Vector Machine (SVM), were developed without the requirement for prior epidemiological parameters. Performances of the models in predicting dengue incidences in the Western Visayas Region of the Philippines were compared by measuring the Root Mean Square Error (RMSE) and Mean Average Error (MAE). Results showed that the models were both effective in forecasting Dengue incidences for epidemiological surveillance as validated by historical data. SARIMA model yielded average RMSE and MAE scores of 16.8187 and 11.4640, respectively. Meanwhile, SVM model achieved scores of 11.8723 and 7.7369, respectively. With the data and setup used, this study showed that SVM outperformed SARIMA in forecasting Dengue incidences. Furthermore, preliminary investigation of one-month lagged climate variables using Random Forest Regressor’s feature ranking yielded rain intensity and value as top possible dengue incidence climate predictors.

Keywords: SARIMA, SVM, Dengue Fever, Time Series Modeling, Feature importance

Suggested Citation

Co, Jerelyn and Tan, Jason Allan and Estuar, Regina Justina and Espina, Kennedy, Dengue Spread Modeling in the Absence of Sufficient Epidemiological Parameters: Comparison of SARIMA and SVM Time Series Models (October 16, 2017). Proceedings of the RAIS Conference: The Future of Ethics, Education and Research. Available at SSRN: https://ssrn.com/abstract=3086161 or http://dx.doi.org/10.2139/ssrn.3086161

Jerelyn Co (Contact Author)

Ateneo de Manila University - Computer Science, Students ( email )

Quezon City
Philippines

Jason Allan Tan

Ateneo de Manila University, Students ( email )

Quezon City
Philippines

Regina Justina Estuar

Ateneo de Manila University ( email )

Katipunan Ave
Quezon City, Manila 1108
Philippines

Kennedy Espina

Ateneo de Manila University, Students ( email )

Quezon City
Philippines

Register to save articles to
your library

Register

Paper statistics

Downloads
44
Abstract Views
268
PlumX Metrics