Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset

The COVID-19 pandemic has emphasized the importance of timely and accurate prediction of disease outbreaks. Mathematical disease models can help simulate the trajectory of diseases and guide policymakers in identifying priorities and gaps in current policies. This study evaluates the performance, on...

Full description

Saved in:
Bibliographic Details
Main Authors: Pulmano, Christian, Fernandez, Proceso L, Jr
Format: text
Published: Archīum Ateneo 2023
Subjects:
Online Access:https://archium.ateneo.edu/discs-faculty-pubs/417
https://doi.org/10.5220/0011626400003414
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Ateneo De Manila University
id ph-ateneo-arc.discs-faculty-pubs-1418
record_format eprints
spelling ph-ateneo-arc.discs-faculty-pubs-14182024-06-14T06:35:47Z Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset Pulmano, Christian Fernandez, Proceso L, Jr The COVID-19 pandemic has emphasized the importance of timely and accurate prediction of disease outbreaks. Mathematical disease models can help simulate the trajectory of diseases and guide policymakers in identifying priorities and gaps in current policies. This study evaluates the performance, on various metrics, of three different parameter estimation algorithms in compartmental models, i.e., Nelder-Mead, Simulated Annealing, and L-BFGS-B, together with the ARIMA time series modeling, in modeling COVID-19 cases. Using the daily number of confirmed cases of COVID-19 in the Philippines as the dataset, the models were trained on 90 different periods, with each period having 30 days of case data. After training, the models were used to predict the cases up to 30 days later. The Negative Log Likelihood (NLL), time spent, iterations per second, and memory allocation were all measured. The results show that ARIMA performed better in terms of accuracy, time, and space efficiency than each of the other algorithms. This suggests that ARIMA should be preferred for predicting the number of cases. However, policymaking sometimes requires scenario-based modeling, which ARIMA is unable to provide. For such requirements, any of the three compartmental models may be preferred, as each performed generally very well, too. 2023-01-01T08:00:00Z text application/pdf https://archium.ateneo.edu/discs-faculty-pubs/417 https://doi.org/10.5220/0011626400003414 Department of Information Systems & Computer Science Faculty Publications Archīum Ateneo Mathematical Modeling Parameter Estimation ARIMA COVID-19 Artificial Intelligence and Robotics COVID-19 Data Science Other Computer Sciences
institution Ateneo De Manila University
building Ateneo De Manila University Library
continent Asia
country Philippines
Philippines
content_provider Ateneo De Manila University Library
collection archium.Ateneo Institutional Repository
topic Mathematical Modeling
Parameter Estimation
ARIMA
COVID-19
Artificial Intelligence and Robotics
COVID-19
Data Science
Other Computer Sciences
spellingShingle Mathematical Modeling
Parameter Estimation
ARIMA
COVID-19
Artificial Intelligence and Robotics
COVID-19
Data Science
Other Computer Sciences
Pulmano, Christian
Fernandez, Proceso L, Jr
Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset
description The COVID-19 pandemic has emphasized the importance of timely and accurate prediction of disease outbreaks. Mathematical disease models can help simulate the trajectory of diseases and guide policymakers in identifying priorities and gaps in current policies. This study evaluates the performance, on various metrics, of three different parameter estimation algorithms in compartmental models, i.e., Nelder-Mead, Simulated Annealing, and L-BFGS-B, together with the ARIMA time series modeling, in modeling COVID-19 cases. Using the daily number of confirmed cases of COVID-19 in the Philippines as the dataset, the models were trained on 90 different periods, with each period having 30 days of case data. After training, the models were used to predict the cases up to 30 days later. The Negative Log Likelihood (NLL), time spent, iterations per second, and memory allocation were all measured. The results show that ARIMA performed better in terms of accuracy, time, and space efficiency than each of the other algorithms. This suggests that ARIMA should be preferred for predicting the number of cases. However, policymaking sometimes requires scenario-based modeling, which ARIMA is unable to provide. For such requirements, any of the three compartmental models may be preferred, as each performed generally very well, too.
format text
author Pulmano, Christian
Fernandez, Proceso L, Jr
author_facet Pulmano, Christian
Fernandez, Proceso L, Jr
author_sort Pulmano, Christian
title Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset
title_short Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset
title_full Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset
title_fullStr Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset
title_full_unstemmed Benchmarking Disease Modeling Techniques on the Philippines’ COVID-19 Dataset
title_sort benchmarking disease modeling techniques on the philippines’ covid-19 dataset
publisher Archīum Ateneo
publishDate 2023
url https://archium.ateneo.edu/discs-faculty-pubs/417
https://doi.org/10.5220/0011626400003414
_version_ 1802997540736466944