Your browser doesn't support javascript.
A Comparative Study on Parameter Estimation of COVID Epidemiological Models Using Differential Evolution Algorithm
Studies in Computational Intelligence ; 1009:241-263, 2022.
Article in English | Scopus | ID: covidwho-1669757
ABSTRACT
Epidemiological models are a system of partial differential equations that model the spread of any epidemics in a closed population. These models are crucial tools for public health policy makers and medical practitioners. Reliable model descriptions often demand optimal parameter estimations. The model parameters are often estimated using numerical methods and traditional optimization algorithms. The inherent stochasticity in real-world outbreaks demand powerful optimizers for parameter estimation. Such ill-defined problems have been potential candidates for meta-heuristic optimization algorithms. The objectives of the proposed study include formulating parameter estimation as an optimization problem and finding optimal/near-optimal parameters for existing COVID models and to analyze the COVID epidemiological models (with optimal model parameters) based on their prediction efficacy. Using the parameters, forecasts for upcoming days can be produced. This paper compares epidemiological models with different machine learning models based on evaluation techniques. The top-five heavily affected states of India having the highest number of cases are considered for the study. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Keywords

Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Experimental Studies / Observational study / Prognostic study Language: English Journal: Studies in Computational Intelligence Year: 2022 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Experimental Studies / Observational study / Prognostic study Language: English Journal: Studies in Computational Intelligence Year: 2022 Document Type: Article