Fuzzy neural networks enhanced evaluation of wetland surface water quality

The quality of wetland surface water is a significant factor for the evaluation of the wetland ecological environment. It is also a vital basis for planning and developing wetland tourism. This paper has tried to use Fuzzy Neural Networks (FNN) as a water quality evaluation means, which combines fuzzy membership and neural network frame, to drive the model automatically update in training and leaning processes; thus it can be applied in the simulations of complex systems. The significant factors such as ammonia nitrogen, Dissolved Oxygen (DO), Chemical Oxygen Demand (COD), total nitrogen, total phosphorus and potassium permanganate are selected to indicate the evaluation performance. The experimental results show that the evaluation procedure is consistent with the objective law and the FNN increases the credibility in the assessment of wetland quality.

[1]  Albert T. Jones,et al.  Using neural networks to monitor supply chain behaviour , 2011, Int. J. Comput. Appl. Technol..

[2]  Y Ouyang,et al.  Assessment of seasonal variations in surface water quality. , 2006, Water research.

[3]  Guo Wei-hua,et al.  Water Quality Assessment of Main Rivers in Tianjin Based on Principal Component Analysis and Water Quality Identification Index , 2011 .

[4]  Haralambos Sarimveis,et al.  A classification technique based on radial basis function neural networks , 2006, Adv. Eng. Softw..

[5]  David G. Smith.  A better water quality indexing system for rivers and streams , 1990 .

[6]  Mohamed Faten Zhani,et al.  Analysis of prediction performance of training-based models using real network traffic , 2008, 2008 International Symposium on Performance Evaluation of Computer and Telecommunication Systems.

[7]  John R. Jones,et al.  Initial performance of a high capacity surface-flow treatment wetland , 2002, Wetlands.

[8]  Ian D. Pulford,et al.  Biotic indicators of riverine wetland ecosystem functioning , 1995 .

[9]  Gengdai Liu,et al.  A reactive and protective character motion generation algorithm , 2010, Int. J. Comput. Appl. Technol..

[10]  Zhenbao Liu,et al.  A 3D shape classifier with neural network supervision , 2010, Int. J. Comput. Appl. Technol..

[11]  Diego L. Cardoso,et al.  based on Fuzzy Theory , 2011 .

[12]  E. Nelson,et al.  Metal distribution and stability in constructed wetland sediment. , 2006, Journal of environmental quality.