基于均值化主成分分析的交通安全评价方法研究  

Evaluation of Road Traffic Safety Based on Equalization Method of the Principal Component Cluster Analysis

作　　者：孙健[1] 魏丽英[1] 

机构地区：[1]北京交通大学交通运输学院,北京100044

出　　处：《交通信息与安全》2012年第1期90-93,98,共5页Journal of Transport Information and Safety

基　　金：中央高校基本科研业务费专项资金项目(批准号:2009JBM043);国家自然科学基金青年科学基金项目(批准号:71101008)资助

摘　　要：为对我国各地日趋严峻的道路交通安全现状进行科学、合理的评价,选择适用的安全评价方法是非常必要的,对主成分分析法进行了改进研究,充分考虑了主成分自身存在指标差异性被忽略、因子载荷存在负值等影响,通过采用均值法处理数据、选取较少主成分等途径有效改进了主成分法。构造了可以综合反映交通安全状况的6项相对指标为主体的道路交通安全综合评价指标体系,并以我国2009年东部省份的道路交通安全状况数据为例进行实例分析,采用传统主成分法和改进后的主成分法分别进行了道路交通安全综合评价,通过聚类分析法对改进前后评价结果的差异进行了比较研究。It is highly necessary to scientifically and reasonably evaluate the worsening road traffic safety in China by selecting an appropriate safety assessment method.Given full consideration to the impact of the ignored data diversity and negative factor loading,this paper improves the Principal Component analysis method by taking average and selecting less principal components.Firstly,the comprehensive evaluation indicators system is constructed based on six relative indicators which could comprehensively reflect the safety of road traffic.Then,the data from eastern provinces of China in 2009 are synthetically evaluated step by step as an example by applying the traditional and improved Principal Component analysis methods.Lastly,the evaluation results are compared and analyzed according to the differences between these two methods using the Cluster analysis method.

关 键 词：主成分 均值化 综合评价 指标 聚类 

分 类 号：U491[交通运输工程—交通运输规划与管理]