Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Travel time prediction in transport and logistics

Travel time prediction in transport and logistics Many transport and logistics companies nowadays use raw vehicle GPS data for travel time prediction. However, they face difficult challenges in terms of the costs of information storage, as well as the quality of the prediction. This paper aims to systematically investigate various meta-data (features) that require significantly less storage space but provide sufficient information for high-quality travel time predictions.Design/methodology/approachThe paper systematically studied the combinatorial effects of features and different model fitting strategies with two popular decision tree ensemble methods for travel time prediction, namely, random forests and gradient boosting regression trees. First, the investigation was conducted using pseudo travel time data that were generated using a pseudo travel time sampling algorithm, which allows generating travel time data using different noise processes so that the prediction performance under different travel conditions and noise characteristics can be studied systematically. The results and findings were then further compared and evaluated through a real-life case.FindingsThe paper provides empirical insights and guidelines about how raw GPS data can be reduced into a small-sized feature vector for the purposes of vehicle travel time prediction. It suggests that, add travel time observations from the previous departure time intervals are beneficial to the prediction, particularly when there is no other types of real-time information (e.g. traffic flow, speed) are available. It was also found that modular model fitting does not improve the quality of the prediction in all experimental settings used in this paper.Research limitations/implicationsThe findings are primarily based on empirical studies on limited real-life data instances, and the results may lack generalisabilities. Therefore, the researchers are encouraged to test them further in more real-life data instances.Practical implicationsThe paper includes implications and guidelines for the development of efficient GPS data storage and high-quality travel time prediction under different types of travel conditions.Originality/valueThis paper systematically studies the combinatorial feature effects for tree-ensemble-based travel time prediction approaches. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png VINE Journal of Information and Knowledge Management Systems Emerald Publishing

Travel time prediction in transport and logistics

Download PDF
30 pages

Loading next page...
 
/lp/emerald-publishing/travel-time-prediction-in-transport-and-logistics-EH0qpBauAl
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
2059-5891
DOI
10.1108/vjikms-11-2018-0102
Publisher site
See Article on Publisher Site

Abstract

Many transport and logistics companies nowadays use raw vehicle GPS data for travel time prediction. However, they face difficult challenges in terms of the costs of information storage, as well as the quality of the prediction. This paper aims to systematically investigate various meta-data (features) that require significantly less storage space but provide sufficient information for high-quality travel time predictions.Design/methodology/approachThe paper systematically studied the combinatorial effects of features and different model fitting strategies with two popular decision tree ensemble methods for travel time prediction, namely, random forests and gradient boosting regression trees. First, the investigation was conducted using pseudo travel time data that were generated using a pseudo travel time sampling algorithm, which allows generating travel time data using different noise processes so that the prediction performance under different travel conditions and noise characteristics can be studied systematically. The results and findings were then further compared and evaluated through a real-life case.FindingsThe paper provides empirical insights and guidelines about how raw GPS data can be reduced into a small-sized feature vector for the purposes of vehicle travel time prediction. It suggests that, add travel time observations from the previous departure time intervals are beneficial to the prediction, particularly when there is no other types of real-time information (e.g. traffic flow, speed) are available. It was also found that modular model fitting does not improve the quality of the prediction in all experimental settings used in this paper.Research limitations/implicationsThe findings are primarily based on empirical studies on limited real-life data instances, and the results may lack generalisabilities. Therefore, the researchers are encouraged to test them further in more real-life data instances.Practical implicationsThe paper includes implications and guidelines for the development of efficient GPS data storage and high-quality travel time prediction under different types of travel conditions.Originality/valueThis paper systematically studies the combinatorial feature effects for tree-ensemble-based travel time prediction approaches.

Journal

VINE Journal of Information and Knowledge Management Systems – Emerald Publishing

Published: Sep 12, 2019

Keywords: Machine learning; Random forests; GPS data management; Gradient boosting; Travel time prediction

References

  • Random forests
    Breiman, L.
  • Dynamic freeway travel-time prediction with probe vehicle data: link based versus path based
    Chen, M.; Chien, S.
  • Random forests for classification in ecology
    Cutler, D.R.; Edwards, T.C.; Beard, K.H.; Cutler, A.; Hess, K.T.; Gibson, J.; Lawler, J.J.
  • Gene selection and classification of microarray data using random forest
    Díaz-Uriarte, R.; De Andres, S.A.
  • Dynamic travel time prediction using data clustering and genetic programming
    Elhenawy, M.; Chen, H.; Rakha, H.A.
  • Greedy function approximation: a gradient boosting machine
    Friedman, J.H.
  • Stochastic gradient boosting
    Friedman, J.H.
  • Traveling time prediction in scheduled transportation with journey segments
    Gal, A.; Mandelbaum, A.; Schnitzler, F.; Senderovich, A.; Weidlich, M.
  • Batch Bayesian optimization via local penalization
    Gonzalez, J.; Dai, Z.; Hennig, P.; Lawrence, N.
  • Gradient boosting trees for auto insurance loss cost modeling and prediction
    Guelman, L.
  • Predicting travel times with context-dependent random forests by modeling local and aggregate traffic flow
    Hamner, B.
  • Local online kernel ridge regression for forecasting of urban travel times
    Haworth, J.; Shawe-Taylor, J.; Cheng, T.; Wang, J.
  • The two most important algorithms in predictive modeling today
    Howard, J.; Bowles, M.
  • Robust regression: asymptotics, conjectures and Monte Carlo
    Huber, P.J.
  • Travel-time prediction using Gaussian process regression: a trajectory-based approach
    Idé, T.; Kato, S.
  • Space-time modeling of traffic flow
    Kamarianakis, Y.; Prastacos, P.
  • Memory properties and fractional integration in transportation time-series
    Karlaftis, M.G.; Vlahogianni, E.I.
  • A genetic algorithm-based method for improving quality of travel time prediction intervals
    Khosravi, A.; Mazloumi, E.; Nahavandi, S.; Creighton, D.; Lint, J.V.
  • On more robust estimation of skewness and kurtosis
    Kim, T.H.; White, H.
  • Rilett, L.R.: travel time prediction by advanced neural network
    Kisgyörgy, L.
  • The bellkor solution to the Netflix grand prize
    Koren, Y.
  • Traffic flow prediction using adaboost algorithm with random forests as a weak learner
    Leshem, G.; Ritov, Y.
  • Combination of feature engineering and ranking models for paper-author identification in KDD cup 2013
    Li, C.L.; Su, Y.C.; Lin, T.W.; Tsai, C.H.; Chang, W.C.; Huang, K.H.; Kuo, T.M.; Lin, S.W.; Lin, Y.S.; Lu, Y.C.
  • Freight vehicle travel time prediction using gradient boosting regression tree
    Li, X.; Bai, R.
  • Freight vehicle travel time prediction using sparse Gaussian processes regression with trajectory data
    Li, X.; Bai, R.
  • Prediction intervals to account for uncertainties in neural network predictions: Methodology and application in bus travel time prediction
    Mazloumi, E.; Rose, G.; Currie, G.; Moridpour, S.
  • Comparing state-of-the-art regression methods for long term travel time prediction
    Mendes-Moreira, J.; Jorge, A.M.; de Sousa, J.F.; Soares, C.
  • Real-time road traffic prediction with spatio-temporal correlations
    Min, W.; Wynter, L.
  • Application of probe-vehicle data for real-time traffic-state estimation and short-term travel-time prediction on a freeway
    Nanthawichit, C.; Nakatsuji, T.; Suzuki, H.
  • A comparison of random forests, boosting and support vector machines for genomic selection
    Ogutu, J.O.; Piepho, H.P.; Schulz-Streeck, T.
  • Duchesnay, E.: scikit-learn: Machine learning in python
    Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; Vanderplas, J.; Passos, A.; Cournapeau, D.; Brucher, M.; Perrot, M.
  • Taking the human out of the loop: a review of Bayesian optimization
    Shahriari, B.; Swersky, K.; Wang, Z.; Adams, R.P.; de Freitas, N.
  • Comparison of parametric and nonparametric models for traffic flow forecasting
    Smith, B.L.; Williams, B.M.; Oswald, R.K.
  • GPyOpt: a Bayesian optimization framework in python
  • Bayesian committee of neural networks to predict travel times with confidence intervals
    van Hinsbergen, C.; van Lint, J.; van Zuylen, H.
  • Accurate freeway travel time prediction with state-space neural networks under missing data
    van Lint, J.; Hoogendoorn, S.; van Zuylen, H.
  • Short-term traffic and travel time prediction models. Artificial intelligence applications to critical transportation issues
    van Lint, J.; van Hinsbergen, C.
  • Travel time unreliability on freeways: Why measures based on variance tell only half the story
    van Lint, J.; van Zuylen, H.J.; Tu, H.
  • Big data: New tricks for econometrics
    Varian, H.R.
  • Travel-time prediction with support vector regression
    Wu, C.H.; Ho, J.M.; Lee, D.
  • A gradient boosting method to improve travel time prediction
    Zhang, Y.; Haghani, A.
  • Univariate volatility-based models for improving quality of travel time reliability forecasting
    Zhang, Y.; Sun, R.; Haghani, A.; Zeng, X.
  • A hybrid short-term traffic flow forecasting method based on spectral analysis and statistical volatility model
    Zhang, Y.; Zhang, Y.; Haghani, A.
  • Urban link travel time estimation based on sparse probe vehicle data
    Zheng, F.; Zuylen, H.V.
  • A reliable hybrid prediction model for real-time travel time prediction with widely spaced detectors
    Zou, N.; Wang, J.; Chang, G.L.