基于大数据规则挖掘的交通拥堵治理研究
|
摘要
随着中国城市机动车保有量的急剧增多,交通拥堵已经成为现代城市病。交通拥堵在道路网络中呈现向四周放射的传导特性,拥堵路段倾向于将拥堵扩散传导到其他相邻路段,该特性此前未被系统研究过,综合比较各种方法的适用性,从时间和大数据规则挖掘角度对拥堵建模;使用时间序列规则挖掘算法建立交通拥堵传导规律模型,并基于传导规则预测未来交通流状况;更重要的是,挖掘出来的拥堵传导规则直观可用,能够用于建立拥堵预警防治机制,完善道路路网建设规划中不合理的部分,从而达到提升交通效率的目的。研究结果证明本模型能够较好达到研究目的,挖掘出的拥堵传导规则可以精确分析交通拥堵状况并预测未来交通流状况,因此可以为交通拥堵治理决策提供重要参考。
With the amount of city vehicles increasing sharply,traffic congestion and travel difficulty has become a disease in modern metropolis.Traffic congestion in the traffic network presents the conduction characteristics of radiation phenomenon.Congested roads tend to transfer the congestion to other adjacent sections.This process of conducting maintains certain regularity which has not been thoroughly studied before.Comparing with other methods,this study decided to extract congestion conduction model from time perspective and using big data rule mining method.Therefore,a time-related association rule mining method was proposed to capture the traffic congestion conduction features which can be further utilized for future traffic prediction.Furthermore,the extracted congestion rules are intuitively useful for establishing early warning mechanism to prevent congestion,improve the unreasonable part of road network construction plan,so as to achieve the purpose of improving traffic efficiency.Result shows the proposed model can serve the purpose effectively.Extracted rules can be used for precise analysis of traffic congestion situation and predict future traffic situation,so it can provide important reference for decision-making of traffic congestion management.
With the amount of city vehicles increasing sharply,traffic congestion and travel difficulty has become a disease in modern metropolis.Traffic congestion in the traffic network presents the conduction characteristics of radiation phenomenon.Congested roads tend to transfer the congestion to other adjacent sections.This process of conducting maintains certain regularity which has not been thoroughly studied before.Comparing with other methods,this study decided to extract congestion conduction model from time perspective and using big data rule mining method.Therefore,a time-related association rule mining method was proposed to capture the traffic congestion conduction features which can be further utilized for future traffic prediction.Furthermore,the extracted congestion rules are intuitively useful for establishing early warning mechanism to prevent congestion,improve the unreasonable part of road network construction plan,so as to achieve the purpose of improving traffic efficiency.Result shows the proposed model can serve the purpose effectively.Extracted rules can be used for precise analysis of traffic congestion situation and predict future traffic situation,so it can provide important reference for decision-making of traffic congestion management.
引文
[1]孙华.大数据环境下实体零售业智能零售研究[J].西安财经学院学报,2016(2).
[2]Smith B L,Williams B M,Oswald R K.Comparison of Parametric and Nonparametric Models for Traffic Flow Forecasting[J].Transportation Research Part C:Emerging Technologies,2002(10).
[3]Hsu C W,Lin C J.A Comparison of Methods for Multiclass Support Vector Machines[J].IEEE Transactions on Neural Networks,2002(2).
[4]Bock M A,Bowman W,Ismail B.Estimation and Inference for Error Variance in Bivariate Nonparametric Regression[J].Statistics and Computing,2007(1).
[5]Yoon Byoungjo,Chang H.Potentialities of Data-Driven Nonparametric Regression in Urban Signalized Traffic Flow Forecasting[J].Journal of Transportation Engineering,2014(7).
[6]Lingras P J,Osborne P.Effect of Noise on Regression and Neural Network Predictions[C].In Proc.of the Conference of Canadian Society of Civil Engineers,Sherbrooke,Quebec,1997.
[7]高慧,赵建玉,贾磊.短时交通流预测方法综述[J].济南大学学报:自然科学版,2008(1).
[8]李佳蓓,朱永忠,王明刚.贝叶斯变量选择及模型平均的研究[J].统计与信息论坛,2015(8).
[9]郭敏,肖翔,蓝金辉.道路交通流短时预测方法综述[J].自动化技术与应用,2009(6).
[10]陆海亭,张宁,黄卫,夏井新.短时交通流预测方法研究进展[J].交通运输工程与信息学报,2009(4).
[11]张晓利,陆化普.非参数回归方法在短时交通流预测中的应用[J].清华大学学报:自然科学版,2009(9).
[12]周小鹏,冯奇,孙立军.基于最近邻法的短时交通流预测[J].同济大学学报:自然科学版,2006(11).
[13]杨世坚,贺国光.基于模糊C均值聚类和神经网络的短时交通流预测方法[J].系统工程,2004(8).
[14]Zhou H,Hirasawa K.Traffic conduction analysis model with time series rule mining[J].Expert Systems with Applications,2014(14).
[15]曹建美.私家车需求与地位寻求[J].统计与信息论坛,2015(10).
[2]Smith B L,Williams B M,Oswald R K.Comparison of Parametric and Nonparametric Models for Traffic Flow Forecasting[J].Transportation Research Part C:Emerging Technologies,2002(10).
[3]Hsu C W,Lin C J.A Comparison of Methods for Multiclass Support Vector Machines[J].IEEE Transactions on Neural Networks,2002(2).
[4]Bock M A,Bowman W,Ismail B.Estimation and Inference for Error Variance in Bivariate Nonparametric Regression[J].Statistics and Computing,2007(1).
[5]Yoon Byoungjo,Chang H.Potentialities of Data-Driven Nonparametric Regression in Urban Signalized Traffic Flow Forecasting[J].Journal of Transportation Engineering,2014(7).
[6]Lingras P J,Osborne P.Effect of Noise on Regression and Neural Network Predictions[C].In Proc.of the Conference of Canadian Society of Civil Engineers,Sherbrooke,Quebec,1997.
[7]高慧,赵建玉,贾磊.短时交通流预测方法综述[J].济南大学学报:自然科学版,2008(1).
[8]李佳蓓,朱永忠,王明刚.贝叶斯变量选择及模型平均的研究[J].统计与信息论坛,2015(8).
[9]郭敏,肖翔,蓝金辉.道路交通流短时预测方法综述[J].自动化技术与应用,2009(6).
[10]陆海亭,张宁,黄卫,夏井新.短时交通流预测方法研究进展[J].交通运输工程与信息学报,2009(4).
[11]张晓利,陆化普.非参数回归方法在短时交通流预测中的应用[J].清华大学学报:自然科学版,2009(9).
[12]周小鹏,冯奇,孙立军.基于最近邻法的短时交通流预测[J].同济大学学报:自然科学版,2006(11).
[13]杨世坚,贺国光.基于模糊C均值聚类和神经网络的短时交通流预测方法[J].系统工程,2004(8).
[14]Zhou H,Hirasawa K.Traffic conduction analysis model with time series rule mining[J].Expert Systems with Applications,2014(14).
[15]曹建美.私家车需求与地位寻求[J].统计与信息论坛,2015(10).