A Big-Bang Big- Crunch Type 2-Fuzzy Logic Based System For Malaria Epidemic Prediction In Ethiopia

Abstract

ABSTRACT- Malaria is a life-threatening disease caused by Plasmodium parasite infection with huge medical, economic, and social impact. Malaria is one of a serious public health problem in Ethiopia since 1959, even if, its morbidity and mortality have been reduced starting from 2001. Various studies were conducted to predict the Malaria epidemic using mathematical and statistical regression approaches, nevertheless, they had no learning capabilities. In this paper, we presented a type-2 fuzzy logic-based system for Malaria epidemic prediction (MEP) in Ethiopia which has been optimized by the Big-Bang Big-Crunch (BBBC) approach to maximizing the model accuracy and interpretability to predict for the future occurrence of Malaria. We compared the proposed BBBC optimized type-2 fuzzy logic-based system against its counterpart T1FLS, non-optimized T2FLS, ANFIS and ANN. The results show that the optimized proposed T2FLS provides a more interpretable model that predicts the future occurrence of Malaria from one up to three months ahead with optimal accuracy. This helps to answer the question of when and where must make preparation to prevent and control the occurrence of Malaria epidemic since the generated rules from our system were able to explain the situations and intensity of input factors which contributed to the Malaria epidemic and outbreak.