Your browser doesn't support javascript.
Fuzzy Time Series Forecasting of COVID-2019 Outbreak: A Case Study of U.S. Population
Lecture Notes on Data Engineering and Communications Technologies ; 62:57-69, 2021.
Article in English | Scopus | ID: covidwho-1188072
ABSTRACT
The novel coronavirus (nCoV-2019) was first apparent in Wuhan city in China, which impacted the world and its peoples. This epidemic severely influenced the global equilibrium of humankind, including the USA, where the number of affected cases reached more than 4,323,160 by the end of July 2020. Therefore, the COVID-2019 outbreak scenario warrants a sound forecasting model to accurately predict the catastrophe in human lives that resulted from this pandemic. In this study, the Fuzzy Time Series (FTS) forecasting model for COVID-19 employed to analyze and predict the number of cumulative infected cases of the USA by employing the Abbasov and Mamedova model. Our experiment used 145 days of infected cases of the USA rendered from the World Health Organization (WHO). The optimized model achieved through tuning three hyper parameters of the Abbasov and Mamedova model. To estimate the model performance, we evaluated the forecast accuracy through the lenses of Mean Absolute Percentage Error (MAPE) and Theil U statistics, followed by a comparison between the forecasted with actual observations. We observed that the recommended FTS model’s forecasting is reliable and acceptable up to 35 days ahead of forecasting. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Case report / Experimental Studies Language: English Journal: Lecture Notes on Data Engineering and Communications Technologies Year: 2021 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Case report / Experimental Studies Language: English Journal: Lecture Notes on Data Engineering and Communications Technologies Year: 2021 Document Type: Article