6Analyzing Statewise COVID‑19 Lockdowns Using Support Vector Regression

Karpagam G. R.1*, Keerthna M.1, Naresh K.1, Sairam Vaidya M.1, Karthikeyan T.2 and Syed Khaja Mohideen2

1Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, Tamil Nadu, India

2Department of Information Technology, University of Technology and Applied Sciences - Salalah Thumrait Rd Thumrayt Street, Oman, Salalah, Dhofar


Since the advent of the COVID-19 pandemic, the Indian Government has resorted to various strategies to contain the spread of this virus. One of these was the introduction and implementation of the nation-wide lockdown. Initially, the nationwide lockdowns were instrumental in containing the spread, but during the first quarter of 2021 the second wave caused major problems across different states, which led to the introduction of state-wise lockdowns with different time spans based on the severity of the virus. This paper focuses on analyzing the effectiveness of the aforesaid state-wise lockdowns by using support vector regression (SVR) to forecast COVID-19 trends at different intervals, and to use the results generated to understand the effect of these state-wise lockdowns on the COVID-19 cases across various states. SVR is simple to update, has strong generalization capacity, and a high prediction accuracy, making it an appropriate solution for forecasting COVID-19 cases that fluctuate daily and require a high level of accuracy due to the severity ...

Get Artificial Intelligence for Sustainable Applications now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.