Title :
Research of Groundwater Environment Early Warning Based on Intelligent Algorithm
Author :
Wu, Yuchun ; Long, Xiaojian
Author_Institution :
Sch. of Electron. & Inf. Eng., Jinggangshan Univ., Ji´´an, China
Abstract :
According to the need for groundwater health evaluation and its non-linear computation difficulty, on the basis of the problem effectively solved by Intelligent algorithm, this paper focused on analyzing calculation principle and characteristics about the BP neural network and support vector machine algorithm in groundwater health prediction model, designed the calculation model of support vector machine based on multi-level classifier, rough set theory was introduced to support vector machine calculation process optimization. It solved complex non-linear relationship between the small sample and groundwater health degreed, and speeded up the convergence speed, effectively improved the prediction accuracy and stability.
Keywords :
backpropagation; condition monitoring; environmental science computing; groundwater; neural nets; pattern classification; rough set theory; support vector machines; BP neural network; backpropagation; calculation principle; groundwater environment early warning; groundwater health evaluation; groundwater health prediction model; intelligent algorithm; multilevel classifier; rough set theory; support vector machine algorithm; Artificial neural networks; Biological neural networks; Classification algorithms; Computational modeling; Kernel; Neurons; Support vector machines; BP neural network; Rough set theory; Support vector machine; early warning;
Conference_Titel :
Computer Science and Electronics Engineering (ICCSEE), 2012 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4673-0689-8
DOI :
10.1109/ICCSEE.2012.321