-
摘要: 为了从海量动态交通数据中快速识别路网中存在的交通拥挤, 通过分析拥挤的特征模式和各种数据挖掘技术的特点后, 设计了一种适用于城市快速路的交通拥挤自动识别方法。该方法将占有率、速度和流量三个基础交通流参数进行组合得到新的特征变量, 运用优化的多层前馈神经网络模型对特征变量进行处理来判断是否有拥挤发生, 通过分析模型输出结果的变化趋势区分常发性拥挤和偶发性拥挤。模拟数据和实测数据对比结果表明, 该方法可以识别城市快速路上发生的交通拥挤, 具有良好的实用性。Abstract: In order to quickly identify traffic congestion from mass dynamic traffic information, traffic congestion pattern and the characteristics of various data mining technologies were analyzed, an auto-identifying method of urban expressway traffic congestion was designed.The flow, speed and occupancy of expressway were combined into several new eigenvectors, optimized multi-layer feedforward perceptron model was adopted to classify the eigenvectors during congestion and non-congestion, recurrent congestion and non-recurrent congestion could be distinguished by analyzing the variances of the model outputs, the method was tested with simulated data and actual data from an urban expressway. The result shows that the method has great practicability and can identify congestion states on urban expressway correctly.
-
表 1 ANN模型优化结果
Table 1. Optimal result of ANN model
序号 系统误差 输入层节点数 隐层节点数 1 0.01646 2 1 2 0.01642 4 7 3 0.01544 4 10 4 0.01456 3 7 5* 0.01172 4 18 
下载: 导出CSV
表 2 识别结果
Table 2. Indentification result
测试数据 阈值 拥挤识别率/% 拥挤误识率/% 模拟数据 T1=[0.3, 0.6] [86.55, 100.00] [0.83, 1.32] T2=[0.3, 0.5] [89.99, 100.00] [0.24, 0.97] 实际数据 T1=[0.3, 0.6] [88.99, 100.00] [1.54, 1.90] T2=[0.3, 0.5] [90.70, 100.00] [1.32, 1.53] T3=[0.3, 0.5] [94.12, 100.00] [0.91, 1.08]
下载: 导出CSV
-
[1] 陆化普, 袁虹, 王建伟. 北京交通拥挤对策研究[J]. 清华大学学报: 哲学社会科学版, 2000, 15 (6): 87-90. https://www.cnki.com.cn/Article/CJFDTOTAL-QHDZ200006013.htmLu Hua-pu, Yuan Hong, Wang Jian-wei. The study on the traffic congestion countermeasures of Beijing[J]. Journal of Tsinghua University: Philosophy and Social Sciences, 2000, 15 (6): 87-90. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QHDZ200006013.htm [2] 朱明. 数据挖掘[M]. 合肥: 中国科技大学出版社, 2002. [3] 邵峰晶, 于忠清. 数据挖掘原理与算法[M]. 北京: 中国水利水电出版社, 2003. [4] 陈文伟, 黄金才, 赵新昱. 数据挖掘技术[M]. 北京: 北京工业大学出版社, 2002. [5] 姜桂艳. 道路交通状态判别技术与应用[M]. 北京: 人民交通出版社, 2004. [6] Razavi A. Development of a new automatic incident detection system for freeway using a BI-classifier approach[D]. British Columbia: University of British Columbia, 1998. [7] 易继锴, 侯媛彬. 智能控制技术[M]. 北京: 北京工业大学出版社, 1999. [8] 权太范. 神经网络-模糊推理理论与应用[M]. 北京: 国防工业出版社, 2002. [9] 刘伟铭, 尹湘源, 管丽萍. 基于检测器脉冲数据的高速公路事件自动检测算法研究[J]. 中国公路学报, 2004, 17 (2): 90-93. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL200402020.htmLiu Wei-ming, Yin Xiang-yuan, Guan Li-ping. Freeway incident detection algorithm based on pulse data of loop detector[J]. China Journal of Highway and Transport, 2004, 17 (2): 90-93. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL200402020.htm [10] 樊小红, 荆便顺. 基于遗传算法的交通事件检测[J]. 长安大学学报: 自然科学版, 2005, 25 (4): 70-72. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200504018.htmFan Xiao-hong, Jing Bian-shun. Freeway automatic incident detection with genetic algorithm[J]. Journal of Chang'an University: Natural Science Edition, 2005, 25 (4): 70-72. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200504018.htm [11] 姜桂艳, 冮龙晖, 张晓东. 动态交通数据故障识别与修复方法[J]. 交通运输工程学报, 2004, 4 (1): 121-125. http://transport.chd.edu.cn/article/id/200401030Jiang Gui-yan, Gang Long-hui, Zhang Xiao-dong. Malfunction identifying and modifying of dynamic traffic data[J]. Journal of Traffic and Transportation Engineering, 2004, 4 (1): 121-125. (in Chinese) http://transport.chd.edu.cn/article/id/200401030 -
点击查看大图
图(5) / 表(2)
计量
- 文章访问数: 294
- HTML全文浏览量: 79
- PDF下载量: 283
- 被引次数: 0
