南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (2): 252256.
许 榕, 缪李囡, 施静静, 陈启美 *
Traffic flow prediction model based on spatial clustering
摘要: 交通流预测对于路径诱导、路网管控有着重要的作用。目前预测数据源未充分挖掘调用已有的沿路视频资源,而需特地另埋设专用地感线圈;在考虑上下游空间关系时,往往将关系并不密切的点也包含进来。为此,文中分析了路口交通流上下游关系,解析了BP神经网络模型机理及局限,提出了基于空间聚类的短时交通流预测Cluster-NN模型,选取了遥控视频摄像数据作为预测模型的输入,对区域内交通流进行了聚类分析预测。实验结果表明,短时交通流预测值优于神经网络模型6.5%以上。
[1].王进, 史其信. 短时交通流预测模型综述. 中国公共安全, 2005, 1(6): 9495. [2].Park J, Li D, Murphey Y L, et al. Real time vehicle speed prediction using a neural network traffic model. In: Neural Networks (IJCNN), The 2011 International Joint Conference on. New York: IEEE Press, 2011: 2991~2996. [3].Castro-Neto M, Jeong Y S, Jeong M K, et al. Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions. Expert systems with applications, 2009, 36(3): 6164~6173. [4].韩超, 宋苏, 王成红. 基于 ARIMA 模型的短时交通流实时自适应预测. 系统仿真学报, 2004, 16(7): 15301532. [5].Sun S, Zhang C, Yu G. A bayesian network approach to traffic flow forecasting. In: Intelligent Transportation Systems, IEEE Transactions on. New York: IEEE Press, 2006, 7(1): 124~132. [6].聂佩林, 余志, 何兆成. 基于约束卡尔曼滤波的短时交通流量组合预测模型. 交通运输工程学报, 2008, 8(5): 8690. [7].宫晓燕, 汤淑明. 基于非参数回归的短时交通流量预测与事件检测综合算法. 中国公路学报, 2003, 16(1): 8286. [8].Hsieh J W, Yu S H, Chen Y S, Automatic traffic surveillance system for vehicle tracking and classification. In: Intelligent Transportation Systems, IEEE Transactions on. New York: IEEE Press, 2006, 7(2): 175~187. [9].Wu C, Li B, Shen S, et al. Vehicle classification in pan-tilt-zoom videos via sparse learning. Journal of Electronic Imaging, 2013, 22(4): 041102~041102. [10].Ren C, Wang C, Yin C, et al. The prediction of short-term traffic flow based on the niche genetic algorithm and BP neural network. In: Proceedings of the 2012 International Conference on Information Technology and Software Engineering. Springer Berlin Heidelberg, 2013, 775~781. [11].南京大学. LDM3-VS高速路网运管平台. http:// its.nju.edu.cn/jshighway/, 2014-3-18. |
No related articles found! |
|