Real-time road traffic states estimation based on kernel-KNN matching of road traffic spatial characteristics

Abstract

The accurate estimation of road traffic states can provide decision making for travelers and traffic managers. In this work, an algorithm based on kernel-k nearest neighbor (KNN) matching of road traffic spatial characteristics is presented to estimate road traffic states. Firstly, the representative road traffic state data were extracted to establish the reference sequences of road traffic running characteristics (RSRTRC). Secondly, the spatial road traffic state data sequence was selected and the kernel function was constructed, with which the spatial road traffic data sequence could be mapped into a high dimensional feature space. Thirdly, the referenced and current spatial road traffic data sequences were extracted and the Euclidean distances in the feature space between them were obtained. Finally, the road traffic states were estimated from weighted averages of the selected k road traffic states, which corresponded to the nearest Euclidean distances. Several typical links in Beijing were adopted for case studies. The final results of the experiments show that the accuracy of this algorithm for estimating speed and volume is 95.27% and 91.32% respectively, which prove that this road traffic states estimation approach based on kernel-KNN matching of road traffic spatial characteristics is feasible and can achieve a high accuracy.

Keywords

road traffic / kernel function / k nearest neighbor (KNN) / state estimation / spatial characteristics

References

[1] XuD-weiMulti-dimensional and multi-granularity acquisition of road traffic states [D], 2014BeijingBeijing Jiaotong University

[2] ZhongM, SharmaS, LiuZ-bin. Assessing robustness of imputation models based on data from different jurisdictions: Examples of Alberta and Saskatchewan, Canada [J]. Transportation Research Record: Journal of the Transportation Research Board, 2005, 1917(1): 116-126

[3] YinW-h, Murray-TuiteP, RakhaH. Imputing erroneous data of single-station loop detectors for nonincident conditions: Comparison between temporal and spatial methods [J]. Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, 2012, 16(3): 159-176

[4] HaworthJ, ChengTao. Non-parametric regression for space–time forecasting under missing data [J]. Computers, Environment and Urban Systems, 2012, 36(6): 538-550

[5] RayR D, DouglasB C. Experiments in reconstructing twentieth-century sea levels [J]. Progress in Oceanography, 2011, 91(4): 496-515

[6] QuL, LiL, ZhangY, HuJ-ming. PPCA-based missing data imputation for traffic flow volume: a systematical approach [J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(3): 512-522

[7] SchneiderT. Analysis of incomplete climate data: estimation of mean values and covariance matrices and imputation of missing values [J]. Journal of Climate, 2001, 14(5): 853-871

[8] LiL, LiY-b, LiZ-heng. Efficient missing data imputing for traffic flow by considering temporal and spatial dependence [J]. Transportation Research Part C: Emerging Technologies, 2013, 34: 108-120

[9] WhitlockM E, QueenC M. Modelling a traffic network with missing data [J]. Journal of Forecasting, 2000, 19(7): 561-574

[10] van LintJ W C, HoogendoornS P, van ZuylenH J. Accurate freeway travel time prediction with states-space neural networks under missing data [J]. Transportation Research Part C: Emerging Technologies, 2005, 13(5/6): 347-369

[11] XuD-w, DonhH-h, JiaL-m, TianYin. A traffic state estimation method based on the road traffic information templates [C]. ICTIS 2013@ sImproving Multimodal Transportation Systems-Information, Safety, and Integration, 2013934-940

[12] XuD-w, DongH-h, JiaL-m, TianYin. Road traffic states estimation algorithm based on matching of the regional traffic attracters [J]. Journal of Central South University, 2014, 21(5): 2100-2107

[13] RoughanM, ZhangY, WillingerW, QiuL-li. Spatio-temporal compressive sensing and internet traffic matrices (extended version) [J]. IEEE/ACM Transactions on Networking, 2012, 20(3): 662-676

[14] XuD-w, DongH-h, JiaL-m, LiH-j, FengY-jing. The estimation of road traffic states based on compressive sensing [J]. Transportmetrica B: Transport Dynamics, 2015, 3(2): 131-152

[15] XuD-w, DongH-h, JiaL-m, QinYong. Virtual speed sensors based algorithm for expressway traffic states estimation [J]. Science China: Technological Sciences, 2012, 55(5): 1381-1390

[16] XuD-w, WangY-d, LiH-j, QinY, JiaL-min. The measurement of road traffic states under high data loss rate [J]. Measurement, 2015, 69: 134-145

[17] WuTaoKernels’ properties, tricks and its applications on obstacle detection [D], 2003ChangshaNational University of Defense Technology

[18] LinM-l, ChenC-yu. A performance comparison of SVMs based on Fourier kernel and RBF kernel [J]. Journal of Chongqing University of Posts and Telecommunications, 2005, 17(6): 647-650