An Experimental Analysis to Measure the Impact of Data Size on Accuracy of Deep Learning Model to Detect and Classify Monkey-Pox Using Skin Lesion Images

As a zoonotic disease, Monkey pox is caused by an orthodox virus. This is communicable disease and highly contagious. Detection of the virus at the early stage may stop its spread in the large community. Rapid and accurate diagnosis of monkey-pox is important for effective management and control of outbreaks. Deep learning techniques, a sub-branch of AI, are especially fruitful in visual detection research and many researchers have done fruitful effort in this area. In this study, with the help of experiments, we are doing comparative analysis of detection techniques based on size of dataset. The objective behind is to validate the relationship between accuracy and size of the data. In this study, the analysis is based on the relationship of the size of dataset and accuracy of the model. In order to make observations we have used two different sized datasets and observed that the increase of data of dataset size increases the accuracy of the model.