Design of an Emergency Ferrying Service for Effective Distribution of Healthcare Equipment Analyzing COVID-19 Cases

Abstract

The recent global epidemic of the novel coronavirus infection 2019 (COVID-19) has created a catastrophic situation all over the world. To monitor and limit the spread of such infections, Machine Learning algorithms are used. In this research study, exponential and time-series Machine Learning algorithms are used to predict the number of infected people of COVID-19 in the upcoming days for a densely populated country like Bangladesh. Besides this, an emergency transportation system, i.e. Emergency Ferry is proposed, which uses the predicted data to supply essential equipment to COVID-19 infected regions. The performance of six different Machine learning algorithms is compared in terms of their predictive accuracy for forecasting COVID19 future cases of consecutive 33 days. The highest accuracy of 93.1% is achieved using the Holt-Winter model. The calculations for best utilization of the Emergency Ferry are also performed based on the distribution rate and distribution time of essential equipment. The calculations and analysis performed in this study show that combining the predictive analysis of COVID-19 infection along with the appropriate allocation of essential resources using Emergency Ferry can benefit the community to take preventive measures for any sudden spike in the outbreak of COVID-19.