Abstract
A machine-learning based methodology has been developed to investigate its applicability in enhancing capacity utilization of freight services. Freight services employ vehicles for picking and delivering goods from and to retailers, and better utilization of freight capacity can save fuel, time and encourage environment friendly operations. The methodology developed here involves identifying the regions in the map where the services are expected to experience lower freight capacity and have good opportunity to enhance this capacity by considering the presence of nearby retailer density. For this, we compare ability of various machine learning models for (a) predicting the weight of freight in the van along various stops in its given freight route, and for (b) predicting the freight traffic counts of vehicles at a location. The data used for this work involves all the freight routes used by a commercial company for freight transport in the Oslo city in a given month along with corresponding freight weight data, as well as data on location of all the retailers in the city. The ML methods compared are Artificial Neural network, Support Vector Machine (SVM), Random forest and linear regression using cross-validation and learning curves. The random forest model performs better than most models for our data, and is used to predict freight weight at stops along new unseen routes. In unseen test scenario (new unseen freight routes), the ML-based methodology is able to predict two out of actual seven best locations for enhancing capacity utilization, thus showing its usefulness. The challenges lies in enhancing accuracy of ML models as the prediction of freight weight is expected to be dependent on input features that are not easy to measure (for example, unseen traffic congestion, local demand/supply changes, etc.). The scope and challenges encountered in this work can help in outlining future work with focus on relevant data acquisition and for integrating the proposed methodology in vehicle route optimization tools.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alex, J.S., Bernhard, S.: A tutorial on support vector regression. Stat. Comput. Arch. 14(3), 199–222 (2004)
Bakhtyar, S., Holmgren, J.: A data mining based method for route and freight estimation. Procedia Comput. Sci. 52, 396–403 (2015)
Barua, L., Zou, B., Zhou, Y.: Machine learning for international freight transportation management: a comprehensive review. Res. Transp. Bus. Manag. 34, 100453 (2020)
Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 437–478. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_26
Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, COLT 1992, pp. 144–152. Association for Computing Machinery, New York (1992)
Boukerche, A., Wang, J.: Machine learning-based traffic prediction models for intelligent transportation systems. Comput. Netw. 181, 107530 (2020)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Gao, Y.: Forecasting of freight volume based on support vector regression optimized by genetic algorithm. In: 2009 2nd IEEE International Conference on Computer Science and Information Technology, pp. 550–553 (2009)
Guo, Z., Fu, J.Y.: Prediction method of railway freight volume based on genetic algorithm improved general regression neural network. J. Intell. Syst. 28(5), 835–848 (2019)
Hassan, L.A.H., Mahmassani, H.S., Chen, Y.: Reinforcement learning framework for freight demand forecasting to support operational planning decisions. Transp. Res. Part E: Logist. Transp. Rev. 137, 101926 (2020)
Jiang, H., Chang, L., Li, Q., Chen, D.: Trajectory prediction of vehicles based on deep learning. In: 2019 4th International Conference on Intelligent Transportation Engineering (ICITE), pp. 190–195 (2019)
Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Ruesch, M., Schmid, T., Bohne, S., Haefeli, U., Walker, D.: Freight transport with VANs: developments and measures. Transp. Res. Procedia 12, 79–92 (2016)
Rumelhart, D., Hinton, G., Williams, R.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Taniguchi, E., Thompson, R., Yamada, T., Van Duin, J.: City logistics. In: Network Modelling and Intelligent Transport Systems, January 2001
Acknowledgment
The authors acknowledge the financial support from the Norwegian Research council’s DigiMOB project (project number: 283331).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tabib, M.V., Stene, J.K., Rasheed, A., Langeland, O., Gundersen, F. (2022). Machine Learning for Capacity Utilization Along the Routes of an Urban Freight Service. In: Sanfilippo, F., Granmo, OC., Yayilgan, S.Y., Bajwa, I.S. (eds) Intelligent Technologies and Applications. INTAP 2021. Communications in Computer and Information Science, vol 1616. Springer, Cham. https://doi.org/10.1007/978-3-031-10525-8_33
Download citation
DOI: https://doi.org/10.1007/978-3-031-10525-8_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10524-1
Online ISBN: 978-3-031-10525-8
eBook Packages: Computer ScienceComputer Science (R0)