Predicting Growth and Trends of COVID-19 by Implementing Machine Learning Algorithms

DOI

10.2991/ahis.k.210913.075How to use a DOI?

Keywords

Artificial Intelligence (AI), AI Solution, Covid-19, Deep Learning (DL), Health Care Solution, Machine Learning (ML)

Abstract

Artificial Intelligence has absolutely revolutionized the world in which we live, and with the passing of time it advances exponentially. The applications of AI are tremendous like healthcare and medical solutions, disease diagnostics, agriculture, developing security infrastructures, Autonomous vehicles, intelligent systems, industrial manufacturing, robotics and so much more. COVID19 is a deadly virus that started from china in 2019 and started to spread rapidly and within time spread throughout various countries of world and in 2020 the world went to a huge pandemic and many lives were lost due to this deadly virus causing to a major health hazard. Moreover, in 2021 many countries experience other new forms of the Covid19 that are faster to spread and more deadly. The spread and growth need to me monitored and evaluated to control the spread. The paper states the proposed methodology to evaluate insights of the growth rate or number of cases along with the death rate of COVID19 to getter better visualization to impose lockdown and area evacuation for population safety. We have applying popular Machine Learning algorithms for the forecast of COVID19 including Naive Bayes, Bayes Net, Decision Tree, Random Forest, Logistic Regression. Moreover, the technique will help to evaluate the trend to get better insights for behaviour analysis of COVID19. This study would aid policymakers in taking the required steps in advance, such as preparing isolation wards, ensuring the supply of drugs and paramedical staff, deciding partial or complete lockdown strategies, recruiting volunteers, and developing economic strategies. Out of all techniques, Random Forest algorithm outstands others with the highest accuracy of 87.28% with precision and recall of 89% and 85% respectively.

Copyright

© 2021, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Daniel Mago Vistro
AU  - Muhammad Shoaib Farooq
AU  - Attique Ur Rehman
AU  - Muhammad Omer Aftab
PY  - 2021
DA  - 2021/09/13
TI  - Predicting Growth and Trends of COVID-19 by Implementing Machine Learning Algorithms
BT  - Proceedings of the 3rd International Conference on Integrated Intelligent Computing Communication & Security (ICIIC 2021)
PB  - Atlantis Press
SP  - 587
EP  - 595
SN  - 2589-4900
UR  - https://doi.org/10.2991/ahis.k.210913.075
DO  - 10.2991/ahis.k.210913.075
ID  - Vistro2021
ER  -