The need to measure urban link travel time (ULTT) is becoming increasingly important for network management and traveler information provision. This paper proposes the use of the k nearest neighbors (k-NN) technique to estimate ULTT with the use of single loop inductive loop detector (ILD) data. Real-world data from London is used. This paper explores the sensitivity of travel time estimates to various k-NN design parameters. It finds that the k-NN method is not particularly sensitive to the distance metric, although care must be taken in selecting the right combination of local estimation method (LEM) and value of k. A robust LEM should be used. The optimized k-NN model is found to provide more accurate estimates than other ULTT methods. To obtain a more accurate estimate of ULTT, a potential application of this approach could be to aggregate GPS probe vehicle ULTT records from different times but the same underlying travel time distribution.
Get full access to this article
View all access options for this article.
References
1.
van LintH.Reliable Travel Time Prediction for Freeways.Trail Research School, Delft, Netherlands, 2004.
2.
RobinsonS., and PolakJ. W.. Modelling Urban Link Travel-Time Using Data from Inductive Loop Detectors. Presented at 10th World Conference on Transport Research (WCTR 2004) (CD-ROM of unrevised papers), Istanbul, Turkey, July 4–8, 2004.
3.
van der ZijppN.Dynamic Origin-Destination Matrix Estimation from Traffic Counts and Automated Vehicle Identification Data. In Transportation Research Record, 1607, TRB, National Research Council, Washington, D.C., 1997, pp. 87–94.
4.
WigginsA. E.Helsinki Journey Time Monitoring System.IEE Seminar on CCTV and Road Surveillance, 1999.
5.
GühnemannA., SchaferR.-P., ThiessenhusenK.-U., and WagnerP.. New Approaches to Traffic Monitoring and Management by Floating Car Data. Presented at 10th World Conference on Transport Research (WCTR 2004) (CD-ROM of unrevised papers), Istanbul, Turkey, July 4–8, 2004.
6.
PapagianniS.Using Automatic Number Recognition Data to Estimate Vehicle Speeds in Central London. MSc dissertation Centre for Transport Studies, Imperial College London,2003.
7.
SrinivasanK. K., and JovanisP. P.. Determination of Number of Probe Vehicles Required for Reliable Travel Time Measurement in Urban Network. In Transportation Research Record, 1537, TRB, National Research Council, Washington, D.C., 1996, pp. 15–22.
8.
TurnerS., EiseleW. L., BenzR. J., and HoldenerD. J.. Travel Time Data Collection Handbook. FHWA-PL-98-035. Research Report 07470-1F. Final Report. Federal Highway Administration, 1998.
9.
IshimaruJ. M., and HallenbeckM. E.. Flow Evaluation Design— Technical Report.Washington State Transportation Center, 1999.
10.
DaileyD. J.A Statistical Algorithm for Estimating Speed from Single Loop Volume and Occupancy Measurements.Transportation Research Part B, Vol. 33, 1999, pp. 313–322.
11.
CoifmanB.Improved Velocity Estimation Using Single Loop Detectors.Transportation Research Part A, Vol. 35, 2001, pp. 863–880.
12.
BarbosaH., TightM., and MayA. D.. A Model of Speed Profiles for Traffic Calmed Roads.Transportation Research Part A, Vol. 34, 2000, pp. 103–123.
13.
WardropJ. G.Journey Speed and Flow in Central Urban Areas.Traffic Engineering + Control, Vol. 9, 1968, pp. 528–539.
14.
GaultH. E., and TaylorI. G.. The Use of the Output from Vehicle Detectors to Assess Delay in Computer-Controlled Area Traffic Control Systems. Research Report No. 37. Transport Operations Research Group, University of Newcastle, United Kingdom,1981.
15.
SisiopikuV., and RouphailN.. Travel Time Estimation from Loop Detector Data for Advanced Traveler Information Systems Applications. Technical Report in Support of the ADVANCE Project, Urban Transportation Center, University of Illinois, Chicago,1994.
16.
ZhangM., and HeJ. C.Estimating Arterial Travel Time Using Loop Data.Public Policy Center, University of Iowa, Iowa City,1998.
17.
PalacharlaP., and NelsonP.. On-Line Travel Time Estimation Using Fuzzy Neural Network.Proceedings 2nd World Congress on Intelligent Transport Systems, Vol. 1, Yokohama, Japan, 1995, pp. 112–116.
18.
AndersonJ., and BellM. G. H.. Travel Time Estimation in Urban Road Networks. Presented at IEEE Conference on Intelligent Transportation Systems, Boston, Mass., 1997.
19.
ParkD. J., RilettL. R., and HanG. H.. Spectral Basis Neural Networks for Real-Time Travel Time Forecasting.Journal of Transportation Engineering, Vol. 125, No. 6, 1999, pp. 515–523.
20.
CherrettT., BellH. A., and McDonaldM.. Estimating Vehicle Speed Using Single Inductive Loop Detectors.Proceedings of the Institution of Civil Engineers, Transport, Vol. 147, 2001, pp. 23–32.
21.
DaileyD. J.Travel Time Estimation Using Cross-Correlation Techniques.Transportation Research Part B, Vol. 27B, No. 2, 1993, pp. 97–107.
22.
PettyK. F., BickelP., OstlandM., RiceJ., SchoenbergF., and JiangJ.. Accurate Estimation of Travel Times from Single Loop Detectors.Transportation Research Part A, Vol. 32, No. 1, 1998, pp. 1–17.
23.
DavisG. A., and NihanN. L.. Nonparametric Regression and Short-Term Freeway Traffic Forecasting.Journal of Transportation Engineering, Vol. 117, No. 2, 1991, pp. 178–188.
24.
SmithB. L., and DemetskyM. J.. Traffic Flow Forecasting: Comparison of Modeling Approaches.Journal of Transportation Engineering, Vol. 123, No. 4, 1997, pp. 261–266.
25.
SmithB. L., WilliamsB. M., and OswaldK.. Comparison of Parametric and Nonparametric Models for Traffic Flow Forecasting.Transportation Research Part C, Vol. 10, 2002, pp. 303–321.
26.
ClarkS.Traffic Prediction Using Multivariate Nonparametric Regression.Journal of Transportation Engineering, Vol. 129, No. 2, 2003, pp. 161–168.
27.
HandleyS., LangleyP., and RauscherF. A.. Learning to Predict the Duration of an Automobile Trip.Proc., 4th International Conference on Knowledge Discovery and Data Mining, New York, 1998, pp. 219–223.
28.
YouJ., and KimT. J.. Development and Evaluation of a Hybrid Travel Time Estimation Model.Transportation Research Part C, Vol. 8, 2000, pp. 231–256.
29.
BajwaS. u. I., ChungE., and KuwaharaM.. A Travel Time Prediction Method Based on Pattern Matching Technique. 21st Australian Road Research Board and 11th Road Engineering Association of Asia and Australasia Conference, Cairns, Australia, 2003.
30.
BajwaS. u. I., ChungE., and KuwaharaM.. Sensitivity Analysis of Short Term Travel Time Prediction Model's Parameters. Presented at 10th World Congress on Intelligent Transport Systems, Madrid, Spain, 2003.
31.
OswaldK., SchererW. T., and SmithB. L.. Traffic Flow Forecasting Using Approximate Nearest Neighbor Nonparametric Regression.Research Report No. UVA-CE-ITS-01-4. National ITS Implementation Research Center, George Mason University,Fairfax, Va.,2000.
32.
DevijverP. A., and KittlerJ.. Pattern Recognition: A Statistical Approach.Prentice Hall International, London, 1982.
33.
CoverT. M., and HartP. E.. Nearest Neighbor Patter Classification.IEEE Transactions on Information Theory, Vol. 13, No. 1, 1967, pp. 21–27.
34.
CoverT. M.Estimation by the Nearest Neighbor Rule.IEEE Transactions on Information Theory, Vol. 14, No. 1, 1968, pp. 50 –55.
35.
DasarathyB. V.Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques.IEEE Computer Society Press, 1991.
36.
SimonoffJ. S.Smoothing Methods in Statistics.Springer-Verlag, New York, 1996.
37.
FixE., and HodgesJ. L.. Discriminatory Analysis: Nonparametric Discrimination: Consistency Properties. Project 21-49-004. Report No. 4. USAF School of Aviation Medicine,Randolph Field, Tex.,1951, pp. 261–279.
38.
FixE., and HodgesJ. L.. Discriminatory Analysis: Nonparametric Discrimination: Small Sample Performance. Project 21-49-004. Report No. 11. USAF School of Aviation Medicine,Randolph Field, Tex.,1952, pp. 280–322.
39.
FukunagaK., and HostetlerL.. Optimization of k Nearest Neighbor Density Estimates.IEEE Transactions on Information Theory, Vol. 19, No. 3, 1973, pp. 320–326.
40.
FukunagaK.Introduction to Statistical Pattern Recognition.Academic Press Limited, 1990.
41.
LiuH., and MotodaH.. Feature Selection for Knowledge Discovery and Data Mining.Kluwer Academic Publishers, 1998.
42.
KittlerJ.Feature Set Search Algorithms. In Pattern Recognition and Signal Processing (ChenC. H., ed.). Sijthoff & Noordhoff, Netherlands, 1978, pp. 41–60.
43.
KudoM., and SklanskyJ.. Comparison of Algorithms That Select Features for Pattern Classifiers.Pattern Recognition, Vol. 33, 2000, pp. 25–41.
44.
MathWorks.MATLAB Release 12 User Documentation. Mathswork, Limited,2000.
45.
QiY., and SmithB. L.. Identifying Nearest Neighbors in a Large-Scale Incident Data Archive. In Transportation Research Record: Journal of the Transportation Research Board, No. 1879, Transportation Research Board of the National Academies, Washington, D.C., 2004, pp. 89–98.
46.
HärdleW.Applied Nonparametric Regression.Cambridge University Press, 1990.
47.
RobinsonS., and PolakJ.. Overtaking Rule Approach for the Cleaning of Matched License Plate Data.Journal of Transportation Engineering, forthcoming.
48.
BegonC.Using Automatic Number Plate Recognition Data to Estimate Vehicle Speeds in Central London. MSc dissertation Imperial College London, 2004.
49.
ChenC., KwonJ., RiceJ., SkabardonisA., and VaraiyaP.. Detecting Errors and Imputing Missing Data for Single-Loop Surveillance Systems. In Transportation Research Record: Journal of the Transportation Research Board, No. 1855, Transportation Research Board of the National Academies, Washington, D.C., 2003, pp. 160–167.
50.
RobinsonS., and PolakJ. W.. Some New Perspectives on Urban Link Travel Time Models: Is the k-Nearest Neighbours Approach the Solution? Presented at 36th Annual Conference of the Universities Transport Studies Group, Newcastle, UK, Jan. 5–7, 2004.
51.
XieC., CheuR. L., and LeeD.-H.. Improving Arterial Link Travel Time Estimation by Data Fusion. Presented at 83rd Annual Meeting of the Transportation Research Board, Washington, D.C., 2004.
