Spread Analysis and Prediction of Covid-19 in India using Machine Learning

• Published in: 2023 International Conference on Advancement in Computation & Computer Technologies (InCACCT) pp. 421 - 426
• Main Authors: Yenkikar, Anuradha, Babu, C. Narendra
• Format: Conference Proceeding
• Language: English
• Published: IEEE 05.05.2023
• Subjects: ARIMA model; COVID-19; Covid-l9; Government; Machine Learning; Machine learning algorithms; Pandemics; Polynomial Regression; Root Mean Squared Error; Silver; Support vector machines; Support Vector Regression; Tuberculosis; World Health Organization
• DOI: 10.1109/InCACCT57535.2023.10141756

Since its breakout, the coronavirus (covid-19) has wreaked devastation all over the world. There hasn't been a nation that hasn't been affected by it, and India is no exception. Finding a treatment for this sickness and stopping its spread is one of the hardest problems humanities has ever faced. World Health organization (WHO) figures show that the mortality rate and the number of people with covid-19 are both increased exponentially in some countries during the peak waves. In this study, we use machine learning approaches to forecast the number of covid-19 confirmations, recoveries, and mortality cases over a period of time and assess the coronavirus outbreak in India. The polynomial regression (PR), support vector regression (SVR), and an autoregressive integrated moving average (ARIMA) model are three techniques that are used. The findings demonstrate that, in terms of prediction outcomes, the ARIMA model provides the least Root Mean Squared Error (RMSE), closely followed by polynomial regression. SVR doesn't perform well since predictions are either too low or too high. Overall, the proposed system can significantly aid in comprehending the pattern of spread in other nations and assist governmental bodies in taking action to lessen its effects in future.