基于智能遗传算法与复合最小二乘支持向量机的长江水质预测与评价  

Forecasting and evaluating water quality of Changjiang River based on composite least square SVM with intelligent genetic algorithms

作　　者：戴宏亮[1,2] 

机构地区：[1]广东商学院数学与计算科学学院,广州510320 [2]中山大学数学与计算科学学院,广州510275

出　　处：《计算机应用研究》2009年第1期79-81,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(NSFC#60575004;NSFC#10771220);国家教育部高等学校博士点科研基金资助项目(SRFDP-20070558043)

摘　　要：由于水质的非线性、不确定性等特性,水质预测与评价是很复杂的一个问题;最小二乘支持向量机已经成功地应用于解决非线性问题和时间级数问题。提出一种新的IGALSSM模型,即基于一种新型遗传算法——智能遗传算法参数优选的最小二乘支持向量机模型,并且将提出的模型应用于长江水质的分类识别和预测。实验结果表明,所提出的模型比神经网络有更准确的识别率和更高的预测精度,具有较强的实用价值。Forecasting and evaluation water quality is a complicated problem due to its nonlinearity and uncertainty. Least square support vector machine（LSSVM） has been successfully employed to solve regression and time series problem. This paper proposed a novel IGALSSVM model. The model based on a new genetic algorithm, intelligent genetic algorithm to optitnize the parameters of LSSVM. In addition, applied the model to classify and forecast water quality of Changjiang River. Experimental results show that IGALSSVM model performs better than neural networks ,implying that IGALSSVM is very practical.

关 键 词：最小二乘支持向量机 智能遗传算法 水质 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]