城市多源交通数据分析处理关键技术研究  

Research on the key technology of urban multi-source traffic data analysis and processing

作　　者：徐卫[1] 朱翔宇 刘志[1] XU Wei;ZHU Xiangyu;LIU Zhi(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China)

机构地区：[1]浙江工业大学计算机科学与技术学院,浙江杭州310023

出　　处：《浙江工业大学学报》2018年第3期305-309,315,共6页Journal of Zhejiang University of Technology

基　　金：国家自然科学基金资助项目(61603339);浙江省科技厅公益技术研究工业项目(2015C31059)

摘　　要：城市交通大数据的有效分析利用,是城市交通智能化管控的关键.交通数据存在种类繁多,质量参差不齐,输出格式不规范等问题,数据并未被充分有效利用.同时,大量的缺失、冗余及异常数据还会影响到后续交通流指标计算的精度与可信度.基于此,提出了一套城市基于元胞自动机模型的多源交通数据重构,基于多维度的质量识别与诊断、时空修复以及置信分析算法流程,并利用城市内实际数据对算法合理性进行验证.该算法已在杭州"城市大脑"项目中得到有效应用,社会价值显著.The effective analysis and utilization of urban traffic big data is the key to the intelligent control of urban traffic.However,there are many problems in traffic data such as the too many kinds of traffic data,low data quality and non-standard output format.It will result in data not being fully and effectively utilized.At the same time,a large number of missing,redundant and abnormal data will also affect the accuracy and reliability of subsequent traffic flow calculation.Based on this problem,a set of multi-source traffic data reconstruction based on cellular automaton model,multi-dimensional quality identification and diagnosis,spatio-temporal restoration,confidence analysis algorithm flow is proposed.The reasonableness of the algorithm is verified by the actual data in the city.The algorithm has been effectively applied in Hangzhou“city brain”project,and the social value is significant.

关 键 词：智能交通 多源交通数据 数据诊断 数据分析处理 置信度 

分 类 号：U491[交通运输工程—交通运输规划与管理]