Elsevier

Chaos, Solitons & Fractals

Volume 138, September 2020, 109947
Chaos, Solitons & Fractals

Role of intelligent computing in COVID-19 prognosis: A state-of-the-art review

https://doi.org/10.1016/j.chaos.2020.109947Get rights and content

Highlights

  • State-of-the-Art review on various Intelligent Computing based research for COVID-19

  • Analysing the limitations of prediction based models for COVID-19

  • Discussing the impact of clinical data and online data for COVID research

  • Focussing on Advance intelligent systems on symptom based identification of COVID-19

Abstract

The World Health Organization (WHO) declared novel coronavirus 2019 (COVID-19), an infectious epidemic caused by SARS-CoV-2, as Pandemic in March 2020. It has affected more than 40 million people in 216 countries. Almost in all the affected countries, the number of infected and deceased patients has been enhancing at a distressing rate. As the early prediction can reduce the spread of the virus, it is highly desirable to have intelligent prediction and diagnosis tools. The inculcation of efficient forecasting and prediction models may assist the government in implementing better design strategies to prevent the spread of virus. In this paper, a state-of-the-art analysis of the ongoing machine learning (ML) and deep learning (DL) methods in the diagnosis and prediction of COVID-19 has been done. Moreover, a comparative analysis on the impact of machine learning and other competitive approaches like mathematical and statistical models on COVID-19 problem has been conducted. In this study, some factors such as type of methods(machine learning, deep learning, statistical & mathematical) and the impact of COVID research on the nature of data used for the forecasting and prediction of pandemic using computing approaches has been presented. Finally some important research directions for further research on COVID-19 are highlighted which may facilitate the researchers and technocrats to develop competent intelligent models for the prediction and forecasting of COVID-19 real time data.

Keywords

COVID-19
SARS-CoV-2
Statistical methods
Machine learning
Deep learning

Cited by (0)

View Abstract