首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于贝叶斯网络的停车收费政策评价
引用本文:宗芳,张慧永,贾洪飞.基于贝叶斯网络的停车收费政策评价[J].华南理工大学学报(自然科学版),2010,38(7).
作者姓名:宗芳  张慧永  贾洪飞
作者单位:吉林大学,交通学院,吉林,长春,130022
基金项目:国家自然科学基金资助项目,教育部博士点基金--新教师基金资助项目,吉林大学基本科研业务费项目 
摘    要:应用K2算法和贝叶斯参数估计方法,进行了贝叶斯网络的结构和参数学习,建立了停车行为分析的贝叶斯网络。应用连接树传播算法推断停车费率影响下的停车开始时间、停车时长和停车场类型等选择行为的变化,预测停车收费政策的实施效果,评价政策的可行性.结果表明:随着停车费率的提高,停车者更趋向于选择短时间停车;对不同时段和不同停车场类型实施不均衡收费制度,即高峰停车费率大于非高峰停车费率,路内停车费率大于路外停车费率,可以促使停车者选择非高峰时段停车和路外停车.

关 键 词:贝叶斯网络  停车收费  停车行为  K2算法  
收稿时间:2009-12-14
修稿时间:2010-4-21

Evaluation of Parking Pricing Policy Based on Bayesian Network
Zong Fang,Zhang Hui-yong,Jia Hong-fei.Evaluation of Parking Pricing Policy Based on Bayesian Network[J].Journal of South China University of Technology(Natural Science Edition),2010,38(7).
Authors:Zong Fang  Zhang Hui-yong  Jia Hong-fei
Abstract:In this paper, the parking pricing was examined based on parking behavior analysis and forecasting. A Bayesian network for parking behavior analysis was developed by structure and parameter learning, using K2 algorithm and Bayesian method. With the junction tree algorithm, the changes of parking starting time, parking duration and parking facility location under the influence of the parking fee were infered. The effect of the parking pricing strategy was predicted and the feasibility of the policy was analyzed. The results indicate that the higher parking charge for long-time parking or for parking during the peak periods or for parking at on-ground parking facilities can encourage the parking patrons to select short-time parking or to park during non-peak periods or to park at underground parking garages.
Keywords:Bayesian network  Parking pricing  Parking behavior  K2 method
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《华南理工大学学报(自然科学版)》浏览原始摘要信息
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号