Author : Srinath Vallakirthy 1
Date of Publication :20th August 2020
Abstract: This study analyzes COVID-19 data and predicts the recovered cases in the US using machine-learning models. We employ three most common base learners, namely, linear regression, MLP and SVM, for analyzing and predicting COVID-19 recovered cases. Utilizing these linear regression and SVM base learners, we predict the recovered cases that are very satisfying and close to the exact recovered case. However, the MLP model predicted values are lower than that of actual values because of the low number of recovered cases data available. The predicted values are compared for their accuracy in predicting future recovery cases in the US. The linear regression model is found to be most accurate in comparison to the other models in this study. The key findings of this study will help in understanding the trend in coronavirus spread in the US and its recovery rate. It can help by providing a piece of valuable information to healthcare authorities and workers to design appropriate strategies for reducing the death toll and understanding the recovery rate of coronavirus patients in the US.
- Mahase, E. (2020). Coronavirus: Covid-19 has killed more people than SARS and MERS combined, despite lower case fatality rate. BMJ 368, m641.
- World Health Organization (2020). Coronavirus Disease 2019 (COVID-19): Situation Report, 61. https://apps.who.int/iris/handle/10665/331605?sh ow=full.
- Coronavirus Update (Live), https://www.worldometers.info/coronavirus/ Last accessed on August 05, 2020
- Capricornus EinBlick, COVID-19 Time Series Analysis, https://medium.com/@thecapricornuseinblick/co vid-19-time-series-analysis-e6f3f2235e43 last accessed August 05, 2020.
- Kaggle competition, Novel Corona Virus 2019 Dataset, https://www.kaggle.com/sudalairajkumar/novelcorona-virus-2019- dataset?select=time_series_covid_19_confirmed. csv last accessed August 05, 2020.
- Grenfell R., Drew T..Here’s why it’s taking so long to develop a vaccine for the new coronavirus. Science Alert Archived from the original on 28 2020.
- Wang L , Li J , Guo S , Xie N , Yao L , Cao Y , et al. Real-time estimation and prediction of mortality caused by COVID-19 with patient information based algorithm. Sci Total Environ 2020:138394 .
- Gupta S ,Raghuwanshi GS , Chanda A . Effect of weather on COVID-19 spread in the US: a prediction model for India in 2020. Sci Total Environ 2020:138860.
- AhmarAS , del Val EB . Sutte ARIMA: shortterm forecasting method, a case: COVID-19 and stock market in spain. Sci Total Environ 2020:138883.
- CeylanZ . Estimation of COVID-19 prevalence in Italy, Spain, and France. Sci Total Environ 2020:138817.
- FanelliD , Piazza F . Analysis and forecast of COVID-19 spreading in China, Italy and France. Chaos Solitons Fractals 2020;134:109761.