当前位置: X-MOL 学术Int. J. Pattern Recognit. Artif. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Evaluation of Livable City Based on GIS and PSO-SVM: A Case Study of Hunan Province
International Journal of Pattern Recognition and Artificial Intelligence ( IF 0.9 ) Pub Date : 2021-05-21 , DOI: 10.1142/s0218001421590308
Qizhen Li 1 , Qian Fu 1 , Yi Zou 2 , Xijun Hu 1
Affiliation  

Under the background of accelerating urbanization and increasing stress of ecological environment, the construction of livable city has attracted extensive attention and become a hot spot in the study of urban problems in the world. The evaluation of livable city is a reference for the comparison of urban development and also one of the evaluation criteria for the comparison of urban competitiveness. This paper focuses on three different evaluation factors of ecological environment, economic development and public service to construct an evaluation model of environmental quality of livable cities. Then particle swarm optimization (PSO) is introduced to optimize the parameters of support vector machine (SVM), and a SVM algorithm based on PSO (PSO-SVM) is proposed to solve the livable city evaluation model. Finally, the spatial analysis combined with ArcGIS software obtained the livable city evaluation and division results of Hunan Province. The results show that PSO-SVM algorithm is superior to SVM, BA-SVM, GA-SVM, and has the advantages of faster speed and higher classification accuracy.

中文翻译:

基于GIS和PSO-SVM的宜居城市评价——以湖南省为例

在城市化进程加快、生态环境压力加大的背景下,宜居城市建设受到广泛关注,成为世界各国研究城市问题的热点。宜居城市评价是比较城市发展的参考,也是比较城市竞争力的评价标准之一。本文围绕生态环境、经济发展和公共服务三个不同评价因素构建宜居城市环境质量评价模型。然后引入粒子群优化(PSO)对支持向量机(SVM)的参数进行优化,提出了一种基于PSO的支持向量机算法(PSO-SVM)求解宜居城市评价模型。最后,空间分析结合ArcGIS软件得出湖南省宜居城市评价划分结果。结果表明,PSO-SVM算法优于SVM、BA-SVM、GA-SVM,具有速度更快、分类准确率更高的优点。
更新日期:2021-05-21
down
wechat
bug