摘要
提出一种基于进化策略 (EvolutionaryStrategy ,ES)和自组织特征映射 (Self OrganizingFeatureMap ,SOFM)神经网络的混合模型进行水环境评价的新方法 .把SOFM网络嵌入到ES中 ,根据SOFM网络的运行状态构造ES的适应性函数 ,利用ES的强搜索能力克服SOFM网络对初始权向量和样本输入次序敏感的弱点 .在水环境评价中的应用效果表明 。
A new method for water quality assessment is put forward based on Evolutionary Strategy(ES) and Self Organizing Feature Map (SOFM) neural networks. With SOFM neural networks embedded into ES, the adaptability function of ES is constructed based on the state of SOFM neural networks. The sensitivity of SOFM neural networks to the initial weight matrix and sequence of exemplar input is overcome by the global optimization of ES. The application of the model to water quality assessment shows that the method is superior to the fuzzy cluster method.
出处
《河海大学学报（自然科学版）》
CAS
CSCD
北大核心
2002年第5期53-55,共3页
Journal of Hohai University(Natural Sciences)
