论文部分内容阅读
综合考虑人、车、路及社会经济发展水平对道路交通安全的影响,构建12个相对指标的道路交通安全宏观评价指标体系。针对现有的道路交通安全宏观评价主观评价法和客观评价法的不足,基于投影寻踪的基本原理和求解过程,提出一种新的道路交通安全宏观评价法。该方法运用投影寻踪技术,把多指标的道路交通安全宏观评价问题中的高维数据投影到低维空间,同时采用遗传算法优化投影指标函数,寻求最优的投影方向向量,即客观权重。通过增加主观约束条件,又适当兼顾决策者对某些评价指标的偏好,实现了评价指标的主、客观权重的综合考虑。最后选取2006年全国部分省份的道路交通事故统计数据为实例样本,通过与主成分分析法和模糊综合评价法的比较研究发现,不同评价方法的道路交通安全状况排序有所差别。
Considering the impact of people, vehicles and roads and the level of socio-economic development on road traffic safety, a macro-evaluation index system for road traffic safety based on 12 relative indicators is constructed. Aiming at the shortcomings of subjective evaluation method and objective evaluation method of macroeconomic evaluation of road traffic safety, this paper proposes a new method of macroeconomic evaluation of road traffic safety based on the basic principles and solving process of projection pursuit. This method uses projection pursuit technology to project high-dimensional data of multi-indicator macro-assessment of road traffic safety into low-dimensional space. At the same time, the genetic algorithm is used to optimize the projection index function to find the optimal projection direction vector, namely objective weight. By increasing the subjective constraints and giving due consideration to the preferences of some decision makers, the comprehensive consideration of the subjective and objective weights of the evaluation indicators is achieved. Finally, the statistical data of road traffic accidents in some provinces in 2006 are selected as an example. By comparison with the principal component analysis and fuzzy comprehensive evaluation, it is found that there are some differences in road traffic safety among different evaluation methods.