一种可用于城市人居环境质量评价的基于神经网络的遗传算法

A genetic algorithm based on neural networks for quality evaluation of urban human settlements

试图在已有研究的基础上,综合考虑城市人居环境的内涵,在国内首次将遗传算法全局寻优和BP神经网络局部寻优相结合的改进神经网络模型应用在人居环境评价中,并对中国35个主要城市人居环境质量进行定量判定,揭示城市人居环境现状及各城市在国内人居环境中的相对水平.结果表明该模型取得了令人满意的结果,是一种有效的评价方法.

Basing on the previous research work, the paper explores the connotation of urban human settlements and sets up a model to evaluate human settlements by combining global optimization of GA （Genetic Algorithm） and local optimization of BP neural network. This model is applied to quality evaluation of main urban human settlements in China. The evaluation value indicates the current situation of urban human settlements and relative levels in china. The results show that this model for quality evaluation of urban human settlements is convenient, precise and feasible.