Authors:
Liu Zaiwen
;
Wu Qiaowei
and
Lv Siying
Affiliation:
Beijing Technology and Business University, China
Keyword(s):
Predicting Method, Water Bloom, RBF Neural Network, Squares Support Vector Machine, Intelligence.
Abstract:
Water bloom is one phenomena of eutrophication, and water bloom prediction is always a challenge. A short-term intelligent predicting method based on RBF neural network (RBFNN), and medium-term intelligent predicting method based on least squares support vector machine (LSSVM) for water bloom are proposed in this paper. Including research on the monitoring learning algorithms to the center, width and weight of basis function of RBF network, the width of RBF and fitting and generalization abilities of network, and the function and influence, which the number of RBF hidden level nodes brings to the performance of network, as well as error-corrected algorithm based on gradient descent are analyzed. Least squares support machine, which has long prediction period and high degree of prediction accuracy, needs a small amount of sample can be used to predict the medium-term change discipline of Chl-a (Chlorophyll-a) well. The results of simulation and application show that: RBF neural netwo
rk can be used to forecast the change of Chl-a in short term well, and LSSVM improves the algorithm of support vector machine (SVM), and it has long-term prediction period, strong generalization ability and high prediction accuracy; and this model provides an efficient new way for medium-term water bloom prediction.
(More)