Environmental Time Series Prediction by Improved Classical Feed-Forward Neural Networks
The water quality at the issue of a wastewater treatment plant (WWTP) is a complex work because of its complexity and variability when conditions suddenly change. Two main techniques has been used to improve classical feed-forward neural network. First, a classical adaptative gradient learning rule has been complemented with a Kalman learning rule which is especially effective for noisy behavioral problems. Second, two independent variable selection components -based on genetic algorithms and fuzzy ranking- have been implemented to try to improve performance and generalization. The global study shows that reliable results are obtained which permit to guarantee that neural networks are a confidence tool on this subject.
KeywordsVariable Selection Wastewater Treatment Plant Hide Node Learning Rule Activate Sludge Model
Unable to display preview. Download preview PDF.
- 2.Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)Google Scholar
- 3.Fahlman, S.E., Lebiere, C.: The Cascade-Correlation Learning Architecture. In: Advances in Neural Information Processing Systems, vol. 2. Morgan Kaufmann, San Francisco (1988)Google Scholar
- 4.Henze, M., Grady, Jr., Gujer,W., Marais, G.v.R, and Matsuo, T.: Activated Sludge Model No. 1. IAWQ. Scientific nad Technical Report No. 1, IAWQ. London (1987)Google Scholar
- 5.Koza, J.R.: Genetic Programming. MIT Press, Cambridge (1993)Google Scholar
- 6.Mappa, G., Salvi, G., Tagliaferri, R.: A Fuzzy Neural Network for the On-Line Detection of the B.O.D. In: Marinaro, M., Tagliaferri, R. (eds.) Proceedings of the 7-th Italian Workshop on Neural Nets WIRN Vietri 1995, pp. 305–310. World Scientific Publishing, Singapore (1996)Google Scholar
- 7.Mappa, G., Tagliaferri, R., Tortora, D.: On line Monitoring based on Fuzzy Neural Techniques applied to existing hardware in Wastewater Treatment Plants. In: Morabitol, F.C., et al. (eds.) Proceedings of the International Sympsosium on Intelligent Systems, AMSE-ISIS 1997, pp. 339–342. IOS Press, Amsterdam (1997)Google Scholar
- 8.Morabito, C.F., Versaci, M.: The Use of Fuzzy Curves for the Reconstruction of the Plasma Shape and the Selection of the Magnetic Sensors. Fusion Technology 1, 937–940 (1996)Google Scholar
- 9.NeuralWare.: Neural Computing: A Technology Handbook for Professional II/PLUS, and NeuralWorks Explorer. NeuralWare (1993)Google Scholar