An Interval Type-2 Fuzzy-Markov Model for Prediction of Urban Air Pollution

Prediction is a very important problem that appears in many disciplines. Better weather forecasts can save lives in the event of a catastrophic hurricane; better financial forecasts can improve the return on an investment. The increasing rate of industrial development and urbanization, especially in developing countries, has led to increased levels of air pollution along with increased concern about air pollution effect on human health. This has taken about a diversity of strategies for air quality management, prediction and pollution control. Today’s applications of fuzzy systems are emerging in uncertain environments such as air quality assessments. A fuzzy system that accounts for all of the uncertainties that are present, namely, rule uncertainties due to training with noisy data and measurement uncertainties due to noisy measurements that are used during actual forecasting. The performance results on real data set show the superiority of the fuzzy-markov model in the prediction process with an average accuracy of 94.79% compared to other related works. These results are promising for early prediction of the natural disasters and prevention of its side effects