基于K最近邻算法的城市路段行程时间短时预测
|
摘要
为了对城市路段行程时间进行短时预测,构建了基于KNN算法和汽车电子标识数据的城市路段行程时间短时预测方法。首先介绍了汽车电子标识数据的采集原理,以及通过汽车电子标识数据集进行路段行程时间估计的方法。然后构建基于KNN算法的城市路段行程时间的短时预测模型,包括构建特征向量、交叉验证方法确定K值以及局部估计方法等。实验结果表明:预测模型在城市快速路和主干路的平均相对误差百分比达到了6. 58%左右,取得了较好的预测效果;与历史均值模型和自回归移动平均模型相比,该模型在城市快速路和主干路的预测结果分别提升了39. 6%和16. 8%。
In order to make a short-term prediction of travel time on urban roads,a short-term prediction method for the travel time of urban road segments based on KNN algorithm and electronic registration identification of the motor vehicle( ERI) data was proposed. Firstly,it introduces the collection principle of RFID ERI data and the estimation method of the travel time of the urban roads through the ERI data set. Then the short-term prediction model on urban road segment travel time based on KNN algorithm was constructed,including steps such as constructing eigenvectors,crossvalidation method to determine K value and local estimation method. The percentage of the average relative error on the urban expressway and the arterial road in the experimental result table prediction model reached about 6. 58%,which achieved a good prediction effect. Compared with the historical average model and the autoregressive moving average model,the prediction results of this model for urban expressway and trunk road are improved by 39. 6% and 16. 8% respectively.
In order to make a short-term prediction of travel time on urban roads,a short-term prediction method for the travel time of urban road segments based on KNN algorithm and electronic registration identification of the motor vehicle( ERI) data was proposed. Firstly,it introduces the collection principle of RFID ERI data and the estimation method of the travel time of the urban roads through the ERI data set. Then the short-term prediction model on urban road segment travel time based on KNN algorithm was constructed,including steps such as constructing eigenvectors,crossvalidation method to determine K value and local estimation method. The percentage of the average relative error on the urban expressway and the arterial road in the experimental result table prediction model reached about 6. 58%,which achieved a good prediction effect. Compared with the historical average model and the autoregressive moving average model,the prediction results of this model for urban expressway and trunk road are improved by 39. 6% and 16. 8% respectively.
引文
[1] ZHENG Y,CAPRA L,WOLFSON O,et al. Urban Computing:Concepts,Methodologies,and Applications[J].Acm Transactions on Intelligent Systems&Technology,2014,5(3):1-55.
[2] PAN G,QI G,ZHANG W,et al. Trace analysis and mining for smart cities:Issues,methods,and applications[J].IEEE Communications Magazine,2013,51(6):120-126.
[3] TANG K,CHEN S,LIU Z. Citywide Spatial-Temporal Travel Time Estimation Using Big and Sparse Trajectories[J]. IEEE Transactions on Intelligent Transportation Systems,2018(99):1-12.
[4] MA Z,KOUTSOPOULOS H N,FERREIRA L,et al. Estimation of trip travel time distribution using a generalized Markov chain approach[J]. Transportation Research Part C,2017(74):1-21.
[5] ZHENG X,CHEN W,WANG P,et al. Big Data for Social Transportation[J]. IEEE Transactions on Intelligent Transportation Systems,2016,17(3):620-630.
[6] RAHMANI M,JENELIUS E,KOUTSOPOULOS H N.Non-parametric estimation of route travel time distributions from low-frequency floating car data[J]. Transportation Research Part C,2015,58:343-362.
[7] ROBINSON S,POLAK J. Modeling Urban Link Travel Time with Inductive Loop Detector Data by Using the k-NN Method[J]. Transportation Research Record Journal of the Transportation Research Board,2005,1935(1):47-56.
[8] DAVIS G A,NIHAN N L. Nonparametric Regression and Short-Term Freeway Traffic Forecasting[J]. Journal of Transportation Engineering,1991,117(2):178-188.
[9] XIE Y,ZHANG Y,YE Z. Short-Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition[J]. Computer-Aided Civil and Infrastructure Engineering,2007,22(5):326-334.
[10] GANG X,KANG W,WANG F,et al. Continuous Travel Time Prediction for Transit Signal Priority Based on a Deep Network[C]//IEEE,International Conference on Intelligent Transportation Systems. IEEE,2015:523-528.
[11] WANG J Y,WONG K I,CHEN Y Y. Short-term travel time estimation and prediction for long freeway corridor using NN and regression[C]//International IEEE Conference on Intelligent Transportation Systems. IEEE,2012:582-587.
[12] ZHAN X,UKKUSURI S V,YANG C. A Bayesian mixture model for short-term average link travel time estimation using large-scale limited information trip-based data[J].Automation in Construction,2016,72:237-246.
[13] HOFLEITNER A,HERRING R,BAYEN A. Arterial travel time forecast with streaming data:A hybrid approach of flow modeling and machine learning[J]. Transportation Research Part B,2012,46(9):1097-1122.
[14] QIAO W X,ALI H,MASOUD H. A Nonparametric Model for Short-Term Travel Time Prediction Using Bluetooth Data[J]. Journal of Intelligent Transportation Systems,2013,17(2):165-175.
[15] LIM S H,LEE H M,PARK S L,et al. A Study of Travel Time Prediction using K-Nearest Neighborhood Method[J]. Korean Journal of Applied Statistics,2013,26(5):835-845.
[16] ALI K,HASSANEIN H. Passive RFID for intelligent transportation systems[C]//Consumer Communications and NETWORKING Conference,2009. Ccnc. USA:IEEE,2009:1-2.
[17] WANT R. An Introduction to RFID Technology[J]. IEEE Pervasive Computing,2006,5(1):25-33.
[2] PAN G,QI G,ZHANG W,et al. Trace analysis and mining for smart cities:Issues,methods,and applications[J].IEEE Communications Magazine,2013,51(6):120-126.
[3] TANG K,CHEN S,LIU Z. Citywide Spatial-Temporal Travel Time Estimation Using Big and Sparse Trajectories[J]. IEEE Transactions on Intelligent Transportation Systems,2018(99):1-12.
[4] MA Z,KOUTSOPOULOS H N,FERREIRA L,et al. Estimation of trip travel time distribution using a generalized Markov chain approach[J]. Transportation Research Part C,2017(74):1-21.
[5] ZHENG X,CHEN W,WANG P,et al. Big Data for Social Transportation[J]. IEEE Transactions on Intelligent Transportation Systems,2016,17(3):620-630.
[6] RAHMANI M,JENELIUS E,KOUTSOPOULOS H N.Non-parametric estimation of route travel time distributions from low-frequency floating car data[J]. Transportation Research Part C,2015,58:343-362.
[7] ROBINSON S,POLAK J. Modeling Urban Link Travel Time with Inductive Loop Detector Data by Using the k-NN Method[J]. Transportation Research Record Journal of the Transportation Research Board,2005,1935(1):47-56.
[8] DAVIS G A,NIHAN N L. Nonparametric Regression and Short-Term Freeway Traffic Forecasting[J]. Journal of Transportation Engineering,1991,117(2):178-188.
[9] XIE Y,ZHANG Y,YE Z. Short-Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition[J]. Computer-Aided Civil and Infrastructure Engineering,2007,22(5):326-334.
[10] GANG X,KANG W,WANG F,et al. Continuous Travel Time Prediction for Transit Signal Priority Based on a Deep Network[C]//IEEE,International Conference on Intelligent Transportation Systems. IEEE,2015:523-528.
[11] WANG J Y,WONG K I,CHEN Y Y. Short-term travel time estimation and prediction for long freeway corridor using NN and regression[C]//International IEEE Conference on Intelligent Transportation Systems. IEEE,2012:582-587.
[12] ZHAN X,UKKUSURI S V,YANG C. A Bayesian mixture model for short-term average link travel time estimation using large-scale limited information trip-based data[J].Automation in Construction,2016,72:237-246.
[13] HOFLEITNER A,HERRING R,BAYEN A. Arterial travel time forecast with streaming data:A hybrid approach of flow modeling and machine learning[J]. Transportation Research Part B,2012,46(9):1097-1122.
[14] QIAO W X,ALI H,MASOUD H. A Nonparametric Model for Short-Term Travel Time Prediction Using Bluetooth Data[J]. Journal of Intelligent Transportation Systems,2013,17(2):165-175.
[15] LIM S H,LEE H M,PARK S L,et al. A Study of Travel Time Prediction using K-Nearest Neighborhood Method[J]. Korean Journal of Applied Statistics,2013,26(5):835-845.
[16] ALI K,HASSANEIN H. Passive RFID for intelligent transportation systems[C]//Consumer Communications and NETWORKING Conference,2009. Ccnc. USA:IEEE,2009:1-2.
[17] WANT R. An Introduction to RFID Technology[J]. IEEE Pervasive Computing,2006,5(1):25-33.