Air Quality Prediction in Smart Cities: A Fuzzy-logic based Approach

In the present context, quality of air is of great significance, as it is important for human health and environment. Prediction of pollution according to changing environment is an important pre requisite for estimating and monitoring the unknown pollutants. Fuzzy Inference systems find their significance in solving many environmental engineering problems and have produced good results. The main aim of this paper is to predict the Air Quality Index (AQI) in the area of interest since the pollution concentration is imprecise or uncertain in those areas. The predicted AQI values are compared with the standard values provided by the Central Pollution Control Board of India and it is found that the proposed method gives accurate prediction. We evaluate the proposed system with case studies by varying the concentration of air pollutants NO2 and SO2. The simulation results have shown that the mean square error is less when compared with the feed-forward neural network model and it is found that the proposed system gives better prediction. The proposed Fuzzy Inference System simplifies and speeds up the computation of AQI.