A Novel Stacking-Based Deterministic Ensemble Model for Infectious Disease Prediction

Asmita Mahajan, Nonita Sharma, Silvia Aparicio-Obregon, Hashem Alyami, Abdullah Alharbi, Divya Anand, Manish Sharma and Nitin Goyal
Additional contact information
Asmita Mahajan: Indian Institute of Technology Roorkee, Roorkee 247667, India
Nonita Sharma: Department of Information Technology, IGDTUW Delhi, New Delhi 110006, India
Silvia Aparicio-Obregon: Faculty of Social Sciences and Humanities, Universidad Europea del Atlántico, C/Isabel Torres 21, 39011 Santander, Spain
Hashem Alyami: Department of Computer Science, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia
Abdullah Alharbi: Department of Information Technology, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia
Divya Anand: School of Computer Science and Engineering, Lovely Professional University, Phagwara 144411, India
Manish Sharma: Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140401, India
Nitin Goyal: Computer Science Engineering Department, Shri Vishwakarma Skill University, Palwal 121102, India

Mathematics, 2022, vol. 10, issue 10, 1-15

Abstract: Infectious Disease Prediction aims to anticipate the aspects of both seasonal epidemics and future pandemics. However, a single model will most likely not capture all the dataset’s patterns and qualities. Ensemble learning combines multiple models to obtain a single prediction that uses the qualities of each model. This study aims to develop a stacked ensemble model to accurately predict the future occurrences of infectious diseases viewed at some point in time as epidemics, namely, dengue, influenza, and tuberculosis. The main objective is to enhance the prediction performance of the proposed model by reducing prediction errors. Autoregressive integrated moving average, exponential smoothing, and neural network autoregression are applied to the disease dataset individually. The gradient boosting model combines the regress values of the above three statistical models to obtain an ensemble model. The results conclude that the forecasting precision of the proposed stacked ensemble model is better than that of the standard gradient boosting model. The ensemble model reduces the prediction errors, root-mean-square error, for the dengue, influenza, and tuberculosis dataset by approximately 30%, 24%, and 25%, respectively.

Keywords: autoregressive integrated moving average; epidemiology; exponential smoothing; ensemble; gradient boosting; infectious disease; neural network autoregression; pandemic; stacking (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/10/1714/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/10/1714/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:10:p:1714-:d:817573

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().