基于k-NN和SCATS交通数据的路段行程时间估计方法

姜桂艳; 李琦; 董硕

doi:10.3969/j.issn.0258-2724.2013.02.024

基于k-NN和SCATS交通数据的路段行程时间估计方法

doi: 10.3969/j.issn.0258-2724.2013.02.024

姜桂艳^1,2,
李琦²,
董硕²

基金项目:

国家自然科学基金资助项目(51278257)

高等学校博士学科点专项科研基金资助项目(20110061110034)

计量
- 文章访问数: 1131
- HTML全文浏览量: 66
- PDF下载量: 325
- 被引次数: 0
出版历程
- 收稿日期: 2011-11-03
- 刊出日期: 2013-04-25

Travel Time Estimation Method Using SCATS Traffic Data Based on k-NN Algorithm

摘要

摘要: 为了改善利用SCATS交通数据估计路段行程时间的效果,通过分析SCATS实际交通数据获取时间间隔不一致的特征,构建了SCATS交通数据虚拟时间序列,将利用因子分析法提取的累计贡献率在85%以上的主因子作为交通模式特征向量的构成要素,用欧氏距离作为当前交通模式特征向量和历史交通模式特征向量相似性的测度指标,以路段行程时间估计误差最小为目标选取当前交通模式的近邻数,对交通模式之间距离的倒数进行归一化处理,确定了相似交通模式的行程时间权重,设计了基于SCATS交通数据的路段行程时间估计方法.实例结果表明:与多元线性回归方法相比,本文方法估计的路段行程时间平均绝对误差、平均绝对百分比误差和均方根误差分别平均减少了9.68 s、8.07%和4.5 s.
- 悉尼自适应交通控制系统 /
- 路段行程时间估计 /
- k近邻算法 /
- 因子分析
Abstract: A new method was designed to improve the effect of travel time estimation using SCATS traffic data. In this method, by analyzing the characteristics of SCATS traffic data that their acquisition intervals are not strictly consistent, the virtual time series of SCATS traffic data was constructed first. Then, factors of cumulative squared loading over 85% extracted by factor analysis were included in the traffic state feature vector, and the Euclidean distance was used to measure the closeness between current traffic state and historical traffic state. Finally, the number of nearest neighbors that correspond to the minimum error of travel time estimation was selected, and the weights of k-nearest neighbors were identified by normalizing the reciprocal of the distance between traffic states, based on which the travel time estimation method was established. The results indicate that compared with the multiple linear regression (MLR) method, the proposed method can reduce the mean absolute error (MAE), mean absolute percentage error (MAPE) and root-mean-square error (RMSE) of travel time estimation by an average of 9.68 s, 8.07% and 4.5 s, respectively.
- Sydney coordinated adaptive traffic system (SCATS) /
- travel time estimation /
- k-nearest neighbor (k-NN) /
- factor analysis

HTML全文

参考文献(14)

SMITH B L, HOLT R B, PARK B B. Travel time estimation for urban freeway performance measurement: understanding and improving upon the extrapolation method[C]//Transportation Research Board 83rd Annual Meeting. Washington D C: National Research Council, 2004: 1-20.

TURNER S M, EISELE W L, BENZ R J, et al. Travel time data collection handbook, VA 22161 USA. Springfield: National Technical Information Service, 1998.

PALACHARLA P V, NELSON P C. Application of fuzzy logic and neural networks for dynamic travel time estimation[J]. International Transactions in Operational Research, 1999(6): 145-160.

NAM D H, DREW D R. Traffic dynamics: methods for estimating freeway travel times in real-time from flow measurements[J]. Journal of Transportation Engineering, ASCE, 1996, 122(3): 185-191.

VAN A B, VAN J M, MUSTE M R, et al. Travel time estimation in the GERDIEN project[J]. International Journal of Forecasting, 1997(13): 73-85.

XIE C, CHEU R L, LEE D H. Calibration-free arterial link speed estimation model using loop data[J]. Journal of Transportation Engineering, ASCE, 2001, 127(6): 507-514.

张和生,张毅,胡东成. 路段平均行程时间估计方法[J]. 交通运输工程学报,2008,8(1): 89-96. ZHANG Hesheng, ZHANG Yi, HU Dongcheng. Estimation method of average travel time for road sections[J]. Journal of Traffic and Transportation Engineering, 2008, 8(1): 89-96.

CHEU R L, LIU Q, LEE D. Arterial travel time estimation using SCATS detectors[C]//Proceedings of the 7th International Applications of Advanced Technologies in Transportation Engineering. Cambridge: American Society of Civil Engineers, 2002: 32-39.

姜桂艳,李继伟,张春勤. 城市主干路拥挤路段基于地点交通参数的行程速度估计[J]. 吉林大学学报:工学版,2010,40(5): 1203-1208. JIANG Guiyan, LI Jiwei, ZHANG Chunqin. Travel speed estimation for congested arterial road segment based on spot traffic parameters[J]. Journal of Jilin University: Engineering and Technology Edition, 2010, 40(5): 1203-1208.

MACK Y P. Local properties of k-NN regression estimates[J]. SIAM, Journal Algebraic and Discrete Methods, 1981, 2(3): 311-323.

姜桂艳,李继伟,张春勤. 城市主干路路段行程时间估计的BPR修正模型[J]. 西南交通大学学报,2010,45(1): 124-129. JIANG Guiyan, LI Jiwei, ZHANG Chunqin. Modified BPR functions for travel time estimation of urban arterial road segment[J]. Journal of Southwest Jiaotong University, 2010, 45(1): 124-129.

CHANG W A, RAMAKRISHNA R S. A genetic algorithm for shortest path routing problem and the sizing of populations[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(6): 566 -579.

张赫,杨兆升,王炜. 基于实时交通流信息的中心式动态路径诱导系统行车路线优化技术研究[J]. 公路交通科技,2004,21(9): 91-94. ZHANG He, YANG Zhaosheng, WANG Wei. Research on vehicle route optimization of centrally dynamic route guidance systems based on real time traffic flow information[J]. Journal of Highway and Transportation Research and Development, 2004, 21(9): 91-94.

薛薇. SPSS统计分析方法及应用[M]. 北京:电子工业出版社,2004: 132-156.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1131
HTML全文浏览量: 66
PDF下载量: 325
被引次数: 0

基于k-NN和SCATS交通数据的路段行程时间估计方法

doi: 10.3969/j.issn.0258-2724.2013.02.024

计量

出版历程

Travel Time Estimation Method Using SCATS Traffic Data Based on k-NN Algorithm

计量

出版历程

目录