TY  - JOUR
T1  - Prediction of SO<SUB>2</SUB> Ground Level Concentrations by Means of RBF Neural Networks
AU - , A. Boumerah AU - , A. Abidi AU - , S. Chenikher AU - , T. Bouchami AU - , M. Ramdani 
JO  - Asian Journal of Information Technology
VL  - 6
IS  - 11
SP  - 1148
EP  - 1153
PY  - 2007
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2007.1148.1153
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2007.1148.1153
KW  - Air pollution
KW  -ground level SO2
KW  -multiple regression
KW  -analysis
KW  -RBF network
KW  -hybrid learning
AB  - In this study, a nonlinear model for forecasting the SO<SUB>2</SUB> ground level concentrations is build by using a Radial Basis Function Network (RBFN) based on hybrid learning algorithm. Ground level concentrations of pollutants were analysed in the area under study, in particular the high levels of SO<SUB>2</SUB> occuring during relatively rare episodes. These events are influenced by many factors, such as local meteorology aspects, topography and industrial emissions. The model structure is identified by using a fuzzy C-means clustering algorithm. The proposed RBFN is trained by hybrid learning algorithm to obtain the centre and width of each radial basis function and the least squares method to obtain the output weights. An improved learning scheme is used to avoid the local minima. The developed model concerns an urban area in the Annaba City (North-East Algeria), but it can be adapted to other locations.
ER  -