Comparison of Artificial Neural Network, Fuzzy Logic and Adaptive Neuro-Fuzzy Inference System on Air Pollution Prediction

Abstract

Air pollution can have major impacts on living being and society. Different systems has been developed to predict upcoming air pollution. These prediction systems use different types of models for predicting the air pollution. This paper aims to compare the popular models being used to predict air pollution. The significant models are Artificial Neural Network (ANN), Fuzzy Logic and Adaptive Neuro- Fuzzy Inference System (ANFIS). These models are not only being applied in air pollution prediction, but they were applied in different fields such as fuel consumption and pattern recognition. The structure of each model are discussed in terms of their advantages and disadvantages. Base on comparison of each model and their structures, Adaptive Neuro-Fuzzy Inference System (ANFIS) is considered to be the best solution for air pollution prediction systems.