多源交通信息数据质量评价与控制方法研究

发布时间：2018-05-09 16:04

本文选题：交通信息 + 数据质量　；参考：《吉林大学》2014年硕士论文

【摘要】：城市交通是人类生活空间重要的组成部分，与人们的出行活动息息相关，对城市稳定、可持续的发展和人民生活水平的提高发挥着重要的作用。随着国家经济的发展、城市人口规模的扩大，机动车保有量的增长，路网规模已难以满足日益增长的交通需求，交通拥堵的现象越发严重。为提高现有路网的利用效率，当前全国很多大城市纷纷启动建设智能交通综合信息平台，实时反映道路交通流的运行状态、准确的为出行者和交通管理者提供出行参考和决策支持。智能交通综合信息平台有效发挥其应用功能的前提条件是拥有高质量的路网交通信息数据。然而，在实际交通信息采集过程中，由于种种检测系统故障因素的影响，往往获取的交通信息数据存在质量问题，其呈现的交通流运行状况与实际的路网交通流运行状况出现偏差或不符合交通流运行的长期趋势性，继而导致交通状态的误判。因此，在交通信息数据输入数据库之前，对不同交通信息采集方式获取的原始数据进行质量评价与控制，对智能交通信息平台功能的发挥具有重要的意义。本文针对以上问题，依托国家高技术研究发展计划（863计划）子课题“多源多维城市交通状态感知与交互处理”，通过分析当前国内外有关研究交通信息数据质量的评价与控制方法上存在的问题，结合智能交通综合信息平台对交通数据的应用需求，进一步研究了多源交通数据质量的评价与控制方法。具体研究内容如下：首先，以依托项目和选题背景为基础，，通过分析数据质量评价领域的研究成果及归纳总结交通数据质量评价与控制方法的研究现状，明确了论文的研究对象、目的及意义，确定了论文的研究内容与章节安排。其次，从时间序列的角度剖析交通流运行信息数据呈现的三种分布特性，继而界定交通信息数据质量的定义，同时基于多种数据源，借鉴国内外数据质量评价与控制方面研究的框架理论，设计了一套涵盖全面的交通信息数据质量评价与控制体系，其中包括体系的基本原理、整体架构以及运用决策学中主客观相结合的层次分析法（AHP）的思想和以历史数据的评价期望值为基准计算评价结果的方法构造体系的关键部分。然后，通过分别深入分析感应线圈和车载GPS检测数据的质量影响因素及有质量问题数据的表现特征，制定了反映各自数据源的数据质量评价指标并选择了相应的评价与控制方法，选用城市路网中这两种检测系统获取的交通数据对质量评价与控制的方法和体系进行了有效的实例验证。最后，总结了全文研究成果，并分析存在的不足及进一步的研究方向。
[Abstract]:Urban traffic is an important part of human living space, which is closely related to people's travel activities, and plays an important role in the stability of the city, sustainable development and the improvement of people's living standard. With the development of national economy, the expansion of urban population and the increase of the number of motor vehicles, the scale of road network has been unable to meet the increasing traffic demand, and the phenomenon of traffic congestion is becoming more and more serious. In order to improve the utilization efficiency of the existing road network, many large cities in China have started the construction of the Intelligent Transportation Integrated Information platform, which can reflect the running state of the road traffic flow in real time. Provide accurate travel reference and decision support for travelers and traffic managers. The precondition of intelligent transportation integrated information platform is to have high quality traffic information data. However, in the actual traffic information collection process, due to the impact of various detection system fault factors, the traffic information data often have quality problems. The traffic flow running condition is deviated from the actual road network traffic flow running condition or does not accord with the long-term trend of the traffic flow operation, which leads to the misjudgment of the traffic state. Therefore, before the traffic information data is input into the database, it is of great significance to evaluate and control the quality of the original data obtained by different traffic information collection methods, which is of great significance to the development of the function of the intelligent transportation information platform. In view of the above problems, this paper relies on the National High Technology Research and Development Program (NRDP) subproject "Multi-source and multidimensional urban traffic state perception and interactive processing". Based on the analysis of the existing problems in the evaluation and control methods of traffic information data quality at home and abroad, combined with the application requirements of intelligent transportation integrated information platform to traffic data, The evaluation and control methods of multi-source traffic data quality are further studied. The specific contents of the study are as follows: First of all, based on the project and the background of the topic, by analyzing the research results in the field of data quality evaluation and summarizing the current research situation of traffic data quality evaluation and control methods, the research object, purpose and significance of the paper are clarified. The research content and chapter arrangement are determined. Secondly, from the point of view of time series, this paper analyzes the three distribution characteristics of traffic flow information data, and then defines the quality of traffic information data, at the same time, it is based on a variety of data sources. Based on the frame theory of data quality evaluation and control research at home and abroad, a comprehensive evaluation and control system of traffic information data quality is designed, including the basic principles of the system. The whole structure and the key part of the system are constructed by using the thought of AHP which combines subjective and objective in decision science and the method of calculating the evaluation result based on the expected value of historical data. Then, through the in-depth analysis of the induction coil and the on-board GPS detection data quality factors and the performance characteristics of the quality problem data, The evaluation index of data quality reflecting their respective data sources is established and the corresponding evaluation and control methods are selected. The method and system of quality evaluation and control are validated by using the traffic data obtained from these two detection systems in urban road network. Finally, the paper summarizes the research results, and analyzes the shortcomings and further research direction.
【学位授予单位】：吉林大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：U495

【参考文献】