摘要
交通流预测的实时性和准确性直接影响到交通流诱导系统的高效性,是智能交通领域研究的热点。为了进一步提高短时交通流预测的精度,提出一种基于时空特征分析的短时交通流预测模型。在分析路段时空相关性的基础上,利用云模型改进的遗传算法对支持向量机的参数进行优化,得到最优的支持向量机模型,并实现短时交通流预测。以长春市局部路网的实测数据为基础,验证了所提出模型的有效性和可行性。
The real-time and accuracy of traffic flow prediction directly affect the efficiency of traffic flow guidance system, which is a hot issue of intelligent transportation system research. In order to improve the accuracy of short-term traffic flow forecasting further, a short-term traffic flow prediction model based on spatio-temporal characteristics analysis was proposed. On the basis of spatio-temporal correlativity analysis of section, the parameters of support vector machine (SVM) were opti- mized by using the genetic algorithm improved by cloud model. At last, the optimal SVM model was obtained, and it realized the short-term traffic flow prediction. Based on the measured data of local road network in Changchun city, the feasibility and effectiveness of the proposed model were verified.
出处
《重庆交通大学学报(自然科学版)》
CAS
北大核心
2016年第3期105-109,182,共6页
Journal of Chongqing Jiaotong University(Natural Science)
基金
河南省交通运输厅科技计划项目(2014G21)
关键词
交通运输工程
交通量预测
时空特征分析
云模型
遗传算法
支持向量机
traffic and transportation engineering
traffic flow forecasting
spatio-temporal characteristics analysis
cloud model
genetic algorithm
support vector machine