Prediction and Distribution of Disease Using Hybrid Clustering Algorithm in Big Data

COVID disease plague of 2019 (COVID19) has made an overall health related crisis with a very high gamble of spreading and influencing the whole planet. In essentially every nation, new cases have been accounted. To identify all countries expanding number of tests, the manual clustering of COVID-19 and clinical infection information tests becomes tedious and requires profoundly talented work. As of late, a few calculations have been utilized for clustering clinical datasets deterministically; nonetheless, these definitions have not been powerful in gathering and investigating clinical infections. To rank and score more than 200 nations as indicated by COVID-19 cases and casualty in 2020 and contrast the outcomes with existing pandemic weakness forecast models and results produced by standard Data clustering scoring methods. Information clustering is a course of orchestrating comparative information into gatherings. A clustering algorithm bundles an informational collection into a few several clusters such an extent that the similitude inside a gathering is better compared to among clusters. This paper propose new Hybrid clustering algorithm KMHC in view of K-Means and Hierarchical Clustering calculation. This calculation KMHC, First isolated into every nation gatherings or fragments in light of the COVID patients count, Secondly grouping models has been made across the nations on the planet and across the states in India, and the presentation investigation is analyzed. This paper likewise center figures the future COVID count for India. By utilizing this outcome, set of nations which are having higher COVID count can be effortlessly pictured and the proper moves will be made to diminish the count.