TY - JOUR AU - Pokkuluri Kiran Sree, AU - Smt. S. S. S. N Usha Devi. N, PY - 2020/12/30 Y2 - 2024/03/29 TI - COVID-19 Hotspot Trend Prediction Using Hybrid Cellular Automata in India JF - Engineering Science & Technology JA - Engineering Science & Technology VL - 2 IS - 1 SE - Methodology DO - 10.37256/est.212021610 UR - https://ojs.wiserpub.com/index.php/EST/article/view/610 SP - 54-60 AB - <p style="text-align: justify;">The coronavirus disease 2019 (COVID-19) is an infectious disease identified at Wuhan, China, in December 2019 caused by new Coronavirus. The Indian government has taken many initiatives to mitigate the effect of COVID by encouraging the standard mechanisms of social distancing, the use of masks, and various safety parameters. COVID-19 hotspot identifies regions in India where COVID-19 severity is very high. We propose a novel hybrid cellular automata classifier for predicting the trend of various Hotspots in India, processing different parameters including infection control, virus reproduction rate, critical correlation, safety parameters, and social distancing. The proposed classifier was named Hybrid Cellular Automata-Hotspot (HCA-HS), predicts the number of hotspots in various districts of states, and also gives the status of each city marked either as Totally Safe or Marginally Safe or Unsafe. This will alert the state authorities to take necessary action to mitigate the COVID effect and help the people for possibly refraining from going to the infected areas, i.e., hotspots. The data sets were collected from Kaggle and the local Indian database for more adaptability. The accuracy of the predictions of Hotspots is reported as 91.58%, which is considerable at this moment. The developed classifier is compared with Support Vector Mechanism (SVM), K-Means, Decision Tree, and HCA-HS has reported an accuracy of 10.69% higher than the existing literature.</p> ER -