A comparative study on parameter estimation of COVID epidemiological models using differential evolution algorithm

DOI10.1007/978-981-16-8082-3_9MaRDI QIDQ2086563zbMATH OpenOpenAlexFDO

Authors Sai Sudha Panigrahi, Arul Jayanth Muthukumar, G. Jeyakumar, C. Shunmuga Velayutham, S. Thangavelu

Publication date 25 October 2022

Full work available at URL https://doi.org/10.1007/978-981-16-8082-3_9

zbMATH Keywords

COVID-19differential evolutionIndiamachine learningparameter estimationRMSESIR model

Mathematics Subject Classification ID

Epidemiology (92D30)

Review text

This paper presents a comparative study on parameter estimation of Covid epidemiological models using differential evolution algorithm. The paper aims to investigate and estimate the parameters of the SIR model using differential evolution and compare its performance with some machine learning models. An exploratory data analysis is adopted to find the top-five heavily affected states with the highest number of cases. They are chosen for training purposes. The models include differential evolution approach to estimate parameters of SIR model, SIR model, linear regression, polynomial regression, and prophet model. Based on the fourth-order Runge-Kutta method, the SIR model is fitted with differential evolution. For the entire collection see [Zbl 1480.90003].

Recommendations

• Identification and prediction of time-varying parameters of COVID-19 model: a data-driven deep learning approach
• Identification of an epidemiological model to simulate the COVID-19 epidemic using robust multiobjective optimization and stochastic fractal search
• On stable parameter estimation and short-term forecasting with quantified uncertainty with application to COVID-19 transmission
• Inferring key epidemiological parameters and transmission dynamics of COVID-19 based on a modified SEIR model
• Comparing epidemiological models with the help of visualization dashboards

Cites work

• Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces

Cited in

(9)

• Comparing epidemiological models with the help of visualization dashboards
• Identification of an epidemiological model to simulate the COVID-19 epidemic using robust multiobjective optimization and stochastic fractal search
• Using a genetic algorithm to fit parameters of a COVID-19 SEIR model for US states
• Identification and prediction of time-varying parameters of COVID-19 model: a data-driven deep learning approach
• Application of dynamic mode decomposition and compatible window-wise dynamic mode decomposition in deciphering COVID-19 dynamics of India
• Comparative study of physics-based model and machine learning model for epidemic forecasting and countermeasure
• Markov modeling on dynamic state space for genetic disorders and infectious diseases with mutations: probabilistic framework, parameter estimation, and applications
• Estimation of time-dependent transmission rate for COVID-19 SVIRD model using predictor-corrector algorithm
• Multi-wave modelling and short-term prediction of ICU bed occupancy by patients with COVID-19 in regions of Italy

Describes a project that uses

Uses Software

• prophet
• GitHub

This page was built for publication: A comparative study on parameter estimation of COVID epidemiological models using differential evolution algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2086563)