Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK Cases

The<b> </b>novel coronavirus disease, also known as COVID-19, is a disease outbreak that was first identified in Wuhan, a Central Chinese city. In this report, a short analysis focusing on Australia, Italy, and the United Kingdom is conducted. The analysis includes confirmed and recovere...

Full description

Bibliographic Details
Main Authors: Iman Rahimi, Amir H. Gandomi, Panagiotis G. Asteris, Fang Chen
Format: Article
Language:English
Published: MDPI AG 2021-03-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/12/3/109
id doaj-9666658712ca4178811660f1ade8621d
record_format Article
spelling doaj-9666658712ca4178811660f1ade8621d2021-03-04T00:07:08ZengMDPI AGInformation2078-24892021-03-011210910910.3390/info12030109Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK CasesIman Rahimi0Amir H. Gandomi1Panagiotis G. Asteris2Fang Chen3Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, MalaysiaData Science Institute, University of Technology Sydney, Ultimo 2007, AustraliaComputational Mechanics Laboratory, School of Pedagogical and Technological Education, 15122 Athens, GreeceData Science Institute, University of Technology Sydney, Ultimo 2007, AustraliaThe<b> </b>novel coronavirus disease, also known as COVID-19, is a disease outbreak that was first identified in Wuhan, a Central Chinese city. In this report, a short analysis focusing on Australia, Italy, and the United Kingdom is conducted. The analysis includes confirmed and recovered cases and deaths, the growth rate in Australia compared with that in Italy and the United Kingdom, and the trend of the disease in different Australian regions. Mathematical approaches based on susceptible, infected, and recovered (SIR) cases and susceptible, exposed, infected, quarantined, and recovered (SEIQR) cases models are proposed to predict epidemiology in the above-mentioned countries. Since the performance of the classic forms of SIR and SEIQR depends on parameter settings, some optimization algorithms, namely Broyden–Fletcher–Goldfarb–Shanno (BFGS), conjugate gradients (CG), limited memory bound constrained BFGS ( L-BFGS-B), and Nelder–Mead, are proposed to optimize the parameters and the predictive capabilities of the SIR and SEIQR models. The results of the optimized SIR and SEIQR models were compared with those of two well-known machine learning algorithms, i.e., the Prophet algorithm and logistic function. The results demonstrate the different behaviors of these algorithms in different countries as well as the better performance of the improved SIR and SEIQR models. Moreover, the Prophet algorithm was found to provide better prediction performance than the logistic function, as well as better prediction performance for Italy and UK cases than for Australian cases. Therefore, it seems that the Prophet algorithm is suitable for data with an increasing trend in the context of a pandemic. Optimization of SIR and SEIQR model parameters yielded a significant improvement in the prediction accuracy of the models. Despite the availability of several algorithms for trend predictions in this pandemic, there is no single algorithm that would be optimal for all cases.https://www.mdpi.com/2078-2489/12/3/109COVID-19analysismachine learningSIR and SEIQR modelsoptimization
collection DOAJ
language English
format Article
sources DOAJ
author Iman Rahimi
Amir H. Gandomi
Panagiotis G. Asteris
Fang Chen
spellingShingle Iman Rahimi
Amir H. Gandomi
Panagiotis G. Asteris
Fang Chen
Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK Cases
Information
COVID-19
analysis
machine learning
SIR and SEIQR models
optimization
author_facet Iman Rahimi
Amir H. Gandomi
Panagiotis G. Asteris
Fang Chen
author_sort Iman Rahimi
title Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK Cases
title_short Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK Cases
title_full Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK Cases
title_fullStr Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK Cases
title_full_unstemmed Analysis and Prediction of COVID-19 Using SIR, SEIQR and Machine Learning Models: Australia, Italy and UK Cases
title_sort analysis and prediction of covid-19 using sir, seiqr and machine learning models: australia, italy and uk cases
publisher MDPI AG
series Information
issn 2078-2489
publishDate 2021-03-01
description The<b> </b>novel coronavirus disease, also known as COVID-19, is a disease outbreak that was first identified in Wuhan, a Central Chinese city. In this report, a short analysis focusing on Australia, Italy, and the United Kingdom is conducted. The analysis includes confirmed and recovered cases and deaths, the growth rate in Australia compared with that in Italy and the United Kingdom, and the trend of the disease in different Australian regions. Mathematical approaches based on susceptible, infected, and recovered (SIR) cases and susceptible, exposed, infected, quarantined, and recovered (SEIQR) cases models are proposed to predict epidemiology in the above-mentioned countries. Since the performance of the classic forms of SIR and SEIQR depends on parameter settings, some optimization algorithms, namely Broyden–Fletcher–Goldfarb–Shanno (BFGS), conjugate gradients (CG), limited memory bound constrained BFGS ( L-BFGS-B), and Nelder–Mead, are proposed to optimize the parameters and the predictive capabilities of the SIR and SEIQR models. The results of the optimized SIR and SEIQR models were compared with those of two well-known machine learning algorithms, i.e., the Prophet algorithm and logistic function. The results demonstrate the different behaviors of these algorithms in different countries as well as the better performance of the improved SIR and SEIQR models. Moreover, the Prophet algorithm was found to provide better prediction performance than the logistic function, as well as better prediction performance for Italy and UK cases than for Australian cases. Therefore, it seems that the Prophet algorithm is suitable for data with an increasing trend in the context of a pandemic. Optimization of SIR and SEIQR model parameters yielded a significant improvement in the prediction accuracy of the models. Despite the availability of several algorithms for trend predictions in this pandemic, there is no single algorithm that would be optimal for all cases.
topic COVID-19
analysis
machine learning
SIR and SEIQR models
optimization
url https://www.mdpi.com/2078-2489/12/3/109
work_keys_str_mv AT imanrahimi analysisandpredictionofcovid19usingsirseiqrandmachinelearningmodelsaustraliaitalyandukcases
AT amirhgandomi analysisandpredictionofcovid19usingsirseiqrandmachinelearningmodelsaustraliaitalyandukcases
AT panagiotisgasteris analysisandpredictionofcovid19usingsirseiqrandmachinelearningmodelsaustraliaitalyandukcases
AT fangchen analysisandpredictionofcovid19usingsirseiqrandmachinelearningmodelsaustraliaitalyandukcases
_version_ 1724232366132559872