Abstract
SummaryThe foundation of urban landscape design optimization is the precise evaluation of the effectiveness. To address the issues of strong subjectivity, low efficiency, and poor accuracy in urban landscape design evaluation methods, an intelligent evaluation method combining improved genetic algorithm and error backpropagation neural network is proposed. First, based on Maslow's demand theory and questionnaire survey results, it selects indicators to construct an evaluation index system for urban landscape design. Second, in response to the performance defects of the error backpropagation neural network model, the moth flame algorithm is used to optimize it. Then, in response to the defect that the optimization effect of the moth flame algorithm is not ideal enough, a multiple strategy including improved genetic algorithm is adopted to optimize it. Finally, an urban landscape design evaluation model is constructed based on improved error backpropagation neural network. The experimental results show that the fitting coefficient of the model is 0.9523, with a minimum deviation of less than 1%. The above results indicate that the proposed model can effectively improve the accuracy and efficiency of urban landscape design evaluation, providing data support for urban landscape design optimization. The research on the intelligent development of urban landscape design is of reference significance and has to some extent promoted the development of urban landscape design.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have