CAST²-Zone Wise Disease Outbreak Control Model for SARS-Cov 2

Disease spread is necessary to be controlled so that there is a chance to increase the survival rate of the people in particular zones. The outbreak of SARS-CoV-2 presents critical challenges exacerbated by atmospheric conditions and high population density. Existing time series methodologies for disease outbreak prediction lack spatial detail, hindering effective local-scale control measures. Addressing this gap, the Concomitant Automation of Space and Time Transformer encoder is proposed, which utilizing a Hybrid Aquila Genetic autoencoder to enhance image quality and spatial details. The accompanying Wide Window Lain Transformer extracts microclimate and microhabitat contextual characteristics from images. Furthermore, conventional statistical models fail to accurately determine reproductive indices for disease-prone areas. To overcome this limitation, the Particularly Prone Infected Relieve Model is introduced. In this employing the Susceptible-Infected-Recovered equation and transmission plot neural network to estimate stable reproductive numbers without demographic biases. Implemented in Python, this novel approach yields highly accurate epidemic predictions and timely warnings, surpassing existing time-series methods. When compared with the existing techniques, the proposed model has a high accuracy of 97%, a precision of 92%, a recall of 92%, and an F1-Score of 92%.