摘要
公交到站时间预测是实现智能化公交信息服务的基础,可靠地预测公交到站时间有利于提高公共交通的服务水平,以吸引更多的城市居民选择公共交通。以某城市公交系统海量的历史数据为基础,建立了基于SVM的集合了静态和动态数据的公交预测模型,该模型引入上游路段速度、下游路段最新速度、下游路段最新花时、时间段和路况拥挤程度等动态信息作为模型特征。在此基础上,根据大量公交到站时间历史数据的波动性,提出了一个基于波动性的自适应预测模型。实验结果表明,自适应预测模型优于现有模型,提高了预测的精确度和效率。
Bus arrival time prediction is the foundation of realizing intelligent bus information service.Reliable prediction of bus arrival time is beneficial to improve the public transport service level,so that it attracts more and more city residents to use public transportation.In this paper,based on the massive historical data of a city bus system in real time,SVM （Support Vector Machine） was applied to establish a bus forecasting model on the static and dynamic information.And the speed of upstream,the latest speed of downstream,the latest travel time of downstream,time-of-day,traffic congestion,etc were introduced into our dynamic model.Besides,this paper put forward an adaptive prediction model to improve the efficiency of prediction based on a lot of volatility of bus arrival time historical data.The experimental results show that the adaptive model outperforms those existing static models.
出处
《计算机科学》
CSCD
北大核心
2015年第1期253-256,289,共5页
Computer Science
基金
国家自然科学基金(61070123)
江苏省自然基金(BK2011282)
江苏省高校自然科学重大基础研究项目(11KIJ520003)资助
