摘要
目前,城市道路交通拥堵问题是亟待解决的城市管理难题之一,而交通流拥堵的预测对城市的交通管理至关重要。交通流密度是交通流状态的重要指标,交通流密度的预测对交通流状态的预测具有重要的意义。本文采用模糊信息粒化和支持向量机的组合模型对交通流的拥堵情况进行预测,通过数据降噪、数据标准化、数据信息粒化等处理,然后利用支持向量机(SVM)分类回归预测模型对处理后的数据进行回归预测,预测结果较为精确,可以很好的预测交通流饱和度的发展趋势和区间范围,对交通管理具有很高的参考价值。
At present, traffic congestion is one of the challenges in urban management, while, prediction of traffic congestion is essential to traffic management. Traffic density is an important indicator of the traffic flow, density prediction of traffic flow is of important significance. This article uses a combined model of fuzzy information granulation and support vector machine to predict the traffic congestion, we carry out denoising, data normalization, data information granulation before using support vector machine to accomplish classification and regression prediction, prediction results is accurate. The model does better in prediction of trend and range of traffic density and has high reference value for traffic management.
引文
[1]Stutz C,Runkler T A.Classification And Prediction Of Road Traffic Using Application-Specific Fuzzy Clustering[J].IEEE Transactions on Fuzzy Systems,2002,10(3):297-308.
[2]Porikli,Li FX.Traffic Congestion Estimation Using Hmm Models Without Vehicle Tracking[J].Intelligent Vehicles Symposium IEEE,2004:188-193.
[3]廖瑞辉,周晶.基于云-支持向量机的道路交通拥挤预警模型[J].系统工程,2015,33(4):149-153.
[4]潘洋宇,李东波,童一飞,等.基于小波技术的数据降噪[J].机械科学与技术,2006,23(1):31-33.
[5]何韬,梁栋,李瑶,董瑞,等.小波变换在电力谐波分析中的应用[J].计算机技术与发展,2007,17(1):229-232.
[6]张钹,张铃.问题求解理论及应用[M].北京:清华大学出版社,1990.
[7]Zadeh L A.Towards a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic[J].Fuzzy Sets and Systems,1997,19(1):111-127.
[8]史峰,王小川,郁磊,李洋.Matlab神经网络30个案例分析[M].北京:北京航天航空大学出版社,2009.