Novel deep learning approach to model and predict the spread of COVID-19

SARS-CoV2, which causes coronavirus disease (COVID-19) is continuing to spread globally, producing new variants and has become a pandemic. People have lost their lives not only due the virus but also because of lack counter measures in place. Given increasing caseload uncertainty spread, there an urgent need develop robust artificial intelligence techniques predict COVID-19. In this paper, we propose deep learning technique, called Deep Sequential Prediction Model (DSPM) machine based Non-parametric Regression (NRM) Our proposed models are trained tested on publicly available novel dataset. The evaluated by using Mean Absolute Error compared with existing methods for prediction experimental results demonstrate superior performance models. DSPM NRM achieve MAEs 388.43 (error rate 1.6%) 142.23 (0.6%), respectively 6508.22 (27%) achieved baseline SVM, 891.13 (9.2%) Time-Series (TSM), 615.25 (7.4%) LSTM-based Data-Driven Estimation Method (DDEM) 929.72 (8.1%) Maximum-Hasting (MHEM).