Covid-19 Forecasting with Deep Learning-based Half-binomial Distribution Cat Swarm Optimization

About 170 nations have been affected by the COvid VIrus Disease-19 (COVID-19) epidemic. On governing bodies across globe, a lot of stress is created COVID-19 as there continuous rise in patient count testing positive, and they feel challenging to tackle this situation. Most researchers concentrate on data analysis using machine learning paradigm these situations. In previous works, Long Short-Term Memory (LSTM) was used predict future cases. According LSTM network data, outbreak expected finish June 2020. However, chance an over-fitting problem true positive; it may not produce required results. The dataset has lower accuracy higher error rate existing system. proposed method introduced overcome above-mentioned issues. For prediction, Linear Decreasing Inertia Weight-based Cat Swarm Optimization with Half Binomial Distribution based Convolutional Neural Network (LDIWCSO-HBDCNN) approach presented. suggested research study, predicting employed input, min-max normalization normalize it. Optimum features are selected (LDIWCSO) algorithm, enhancing classification. (CSO) algorithm’s convergence enhanced inertia weight LDIWCSO algorithm. It select essential best fitness function values. specified time India, death confirmed cases predicted (HBDCNN) technique features. As demonstrated empirical observations, system produces significant performance terms f-measure, recall, precision, accuracy.