Prediction of COVID-19 corona virus pandemic based on time series data using support vector machine. (16th November 2020)

• Record Type: Journal Article
• Authors: Singh, Vijander; Poonia, Ramesh Chandra; Kumar, Sandeep; Dass, Pranav; Agarwal, Pankaj; Bhatnagar, Vaibhav; Raja, Linesh
• Is Part Of: Journal of discrete mathematical sciences & cryptography. Volume 23:Number 8(2020)
• Page Start: 1583
• Page End: 1597
• Publication Date: 2020-11-16
• Subjects: 97R40; Pandemic -- Support vector machine -- COVID-19 -- Machine learning; Computer science -- Mathematics -- Periodicals; Cryptography -- Periodicals; Computer science -- Mathematics; Cryptography; Periodicals; 004.0151
• DOI: 10.1080/09720529.2020.1784535
• Languages: English
• ISSNs: 0972-0529

Abstract

Abstract: Predicting the probability of CORONA virus outbreak has been studied in recent days, but the published literature seldom contains multiple model comparisons or predictive analysis of uncertainty. Time series parameters are the core factors influencing infectious diseases such as severe acute respiratory syndrome (SARS) and influenza. As a global pandemic is imminent, the prediction of real-time transmission of COVID-19 is crucial. The objective of this paper is to produce a real-time forecasts using the SVM model. The purpose of this study is to investigate the Corona Virus Disease 2019 (COVID-19) prediction of confirmed, deceased and recovered cases. This prediction will help to plan resources, determine government policy, and provide survivors with immunity passports, and use the same plasma for care. In this analysis, data including attributes such as location wise confirmed, deceased, recovered COVID-19, longitude and latitude were collected from January 22, 2020 to April 25, 2020 worldwide. Support Vector Machine was used to explore the impact on identification, deceased, and recovery.