SHORT-TERM PREDICTION OF AIR POLLUTION USING MULTI- LAYER PERCPTERON & GAMMA NEURAL NETWORKS

This paper considers the problem of air pollution data prediction using multi- layer perceptron and gamma memories neural networks. Air pollution data are available in the format of time series and these real data are used to train and predict the future air pollution condition. Due to the fast dynamics and complex behavior of the process governing the air pollution dynamics, the modeling and prediction of this process is difficult. Also, results are provided to give a comparison of the two proposed predictors.