Detection and prediction of monkey pox disease by enhanced convolutional neural network approach

Abstract

Monkeypox is an infectious viral disease affecting both humans and animals. All symptoms are accompanied by a fever, swollen lymph nodes, and a rash that blisters before crusting. The interval between exposure and the development of symptoms is 5 to 21 days. Typically, symptoms last between two and four weeks. Although it is unknown to what degree it can happen without any signs. It has been found that not all outbreaks display the typical symptoms of fever, aches in the muscles, enlarged glands, and lesions appearing simultaneously. Cases may be severe, especially in children, pregnant women, or people with compromised immune systems. The problem can be detected and monitored at the early stages using some engineering solutions. Therefore, there is a necessity to develop accurate machine learning models for accurate interpretation before applying them in clinical trials. Hence, the proposed work has developed a model to diagnose monkey pox at the best accurate levels for accurate interpretation. The proposed enhanced convolutional neural network model is compared with the exisiting approaches. The obtained results were compared and indicate the superiority of the proposed algorithm.