Contagious Disease Prediction using Random Forest Algorithm Interpolated with Fuzzy Model

Today there are various technologies of machine learning models for forecasting the Contagious Diseases (CD). In the proposed work, an intelligent model for medical systems to detect illnesses in volves learning in a significant way. These infectious diseases are the leading cause of the death worldwide during the last decade. Numerous hybrid approaches have been used in research to treat various disorders. In the suggested model, Predictive analysis is undergone to identify the disease with the nearest symptoms. The infectious disease dataset is downloaded from the Kaggle. The pre-processing method is undergone using mean median and mode data imputation (MMM-DI). Correlation based feature selection is carried out for selecting relevant disease symptoms and Disease analysis is performed using fuzzy model based Random Forest Algorithm (RFA) and the findings are contrasted with those from models already in use, such as Support Vector Machine (SVM) and Naive Bayes Classifier Algorithm (NBC), to demonstrate that the suggested model produces better accuracy up to 97.61%