Prediction of daily air pollution using wavelet decomposition and Adaptive Network-based fuzzy inference system

In this paper, forecasting of daily air pollution is presented using the method of wavelet decomposition and Adaptive-Network-Based Fuzzy Infer system (ANFIS). Daily averaged value of air pollution parameters Carbon Monoxide (CO) for the year 2007 is used for decomposition using daubechies 8 wavelet at level 3. To obtain the acceptable accuracy of forecast, the wavelet coefficients are predicted using Adaptive-Network-Based Fuzzy Infer system (ANFIS). ANFIS serve as a basis for constructing a set of fuzzy if-then rules with appropriate membership functions to generate the stipulated input-output pairs. On the basis of these predicted values the final forecasting is prepared.The result is compared with actual future data and relative performance of this procedure is investigated.