Authors: Dongxiao Niu, Weijun Wang, Desheng Wu
Addresses: School of Economy Management, North China Electric Power University, Beijing, 100020, China. ' School of Economy Management, North China Electric Power University, Beijing, 100020, China. ' Reykjavik University, Kringlunni 1, IS-103 Reykjavik, Iceland; RiskLab, University of Toronto, 1 Spadina Crescent, Toronto, ON, M5S 3G3, Canada
Abstract: Due to the excess consumption of natural resources and the severe deterioration of the environment, people are having a growing consciousness of environmental protection and more concerned of air pollution problems. However, the thermal power plant, as one of the main pollution sources, burns a large amount of fossil fuels and discharge pollutants which cause serious atmospheric pollution. Therefore, it is of great importance to evaluate the environmental impact accurately in order to support administrators on decision making. In this paper, a new assessment model through combining the support vector machine and the BP networks based on particle swarm optimisation is presented. This model makes more accurate evaluation by taking the advantage of both SVM and BP networks and avoiding their defects. An actual instance addressed in the paper shows that this method is effective and practicable.
Keywords: environmental assessment; neural networks; PSO; SVM; combined assessment; environment impact; thermal power plants; air pollution; air quality; support vector machine; particle swarm optimisation; impact assessment.
International Journal of Global Energy Issues, 2009 Vol.32 No.4, pp.361 - 371
Published online: 31 Mar 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article