International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064

Downloads: 2 | Views: 62 | Weekly Hits: ⮙1 | Monthly Hits: ⮙2

Research Paper | Computer Science and Information Technology | India | Volume 11 Issue 5, May 2022

COVID Cases Prediction using Time Series Models

Aksh Mehta [2] | Ayush Mattoo | Dylan Pereira

Abstract: The disastrous outbreak of Covid-19 has brought a global threat to the living society. This incident of COVID-19 in India was conveyed on 30th January 2020 instigated discovery in Wuhan, China. Every nation is putting incredible efforts into the fight against the spread of this deadly disease in terms of infrastructure, finance, data sources, protective gears, important treatments and several other resources. Artificial intelligence researchers are focusing their specialised knowledge to develop mathematical models to analyse the situation using nationwide shared data. To contribute towards the well-being of living society, this article proposes to utilise machine learning and deep learning models to understand its everyday Behaviour to be exponential along with the prediction of the outbreak across the nations by utilising the real-time information from the live covid website( Machine Learning can be called one Such area that uses various algorithms to understand the correlation between the given data, visualise and predict the future forecast. The whole world is currently facing a devastating situation due to the covid-19.To control the spread and rising number of active cases in India, we did some research to demonstrate the future forecasting of the total number of active cases in India in the upcoming few days. We did our research on various time series models such as the Arimamodel, Fb-prophet model, LSTM, out of which LSTM proved to give the best result. We collected the real-time data from the live covid website. After which we did data pre-processing and data wrangling. The data set is then turned into the training set and testing set. Finally, the model is trained and tested for accuracy. After completion of testing and training, the model is ready to predict future forecasts.

Keywords: COVID-19, ARIMA Model, FB Prophet, Machine Learning, Time Series Analysis, forecasting, R-squared score, Root Mean Squared Error, Mean Squared Error

Edition: Volume 11 Issue 5, May 2022,

Pages: 1148 - 1156

How to Download this Article?

Type Your Valid Email Address below to Receive the Article PDF Link

Verification Code will appear in 2 Seconds ... Wait