ORSUM: a Machine Learning Approach for Intelligent Transportation

  • Authors

    • Imran Medi
    • Aida Mustapha
    • Vinothini Kasinathan
    2019-01-18
    https://doi.org/10.14419/ijet.v8i1.7.25972
  • Ride-Sharing, Carpooling, K-Means Clustering, Machine Learning

  • Ride-hailing applications such as Uber and Lyft responds to requests similar to taxis calls, whereby a driver drives from any location nearby to fetch passengers to make proï¬t. This paper presents ORSUM, a ride-sharing application which allows drivers and commuters to share the cost of a journey should be able to provide the desired convenience and costs for moving about in a city. In this study, the proposed application capitalizes on machine learning approach to learn users’ daily travel patterns and recommend “ride buddies†for which the ride is to be shared with. ORSUM has four distinct modules; Orsum Machine Learning module (ORSUMML), Azure Database, Orsum Web Application, and Orsum Application. The machine learning module runs as a standalone Django web applica-tion that is separate from the Orsum Web Application and only interacts with the Orsum Web Application. ORSUMML is developed using the Python based Sci-kit learn or C# based Accord.Net. Evaluation of ORSUM showed high user acceptance rate to the application, comparable to existing applications such as Uber and Lyft.

     

     

  • References

    1. [1] B. Herrendorf, J. A. Schmitz, Jr, and A. Teixeira, “The role of transporation in us economic development: 1840–1860,†International Economic Review, vol. 53, no. 3, pp. 693–716, 2012.

      [2] S. K. Guttikunda and R. Goel, “Health impacts of particulate pollution in a megacity—delhi, india,†Environmental Development, vol. 6, pp.8–20, 2013.

      [3] L. Redman, M. Friman, T. G¨ rling, and T. Hartig, “Quality attributes of public transport that attract car users: A research review,†Transport Policy, vol. 25, pp. 119–127, 2013.

      [4] U. T. T. Force, “The high cost of congestion in canadian cities,†Council of Ministers Transportation and Highway Safety, 2012.

      [5] T. Aprikyan, “New ride-share apps offer flexible commutes, but at what cost?â€https://q13fox.com/2017/04/21/ new-ride-share-apps-offer-flexible-commutes-but-at-what-cost/.

      [6] V. Kasinathan, A. Mustapha, Y. C. Seong, and A. Z. Z. Abidin, “Foot-print: Tourism information search based on mixed reality,†2015.

      [7] V. Kasinathan, A. Mustapha, and T. Subramaniam, “Smartg: Sponta neous malaysian augmented reality tourist guide,†in IOP Conference Series: Materials Science and Engineering, vol. 160, no. 1. IOP Publishing, 2016, p. 012103.

      [8] M. LIN and C. DULA, “Grab: Discovering new frontiers for growth in the southeast asian sharing economy,†2016.

      [9] A. Henao, Impacts of Ridesourcing-Lyft and Uber-on Transportation Including VMT, Mode Replacement, Parking, and Travel Behavior. University of Colorado at Denver, 2017.

      [10] A. Hartmans and N. McAlone, “The story of how travis kalanick built uber into the most feared and valuable startup in the world,†Business Insider, 2016

      [11] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg et al.,“Scikit-learn: Machine learning in python,†Journal of machine learning research, vol. 12, no. Oct, pp. 2825–2830, 2011.

  • Downloads

  • How to Cite

    Medi, I., Mustapha, A., & Kasinathan, V. (2019). ORSUM: a Machine Learning Approach for Intelligent Transportation. International Journal of Engineering & Technology, 8(1.7), 162-170. https://doi.org/10.14419/ijet.v8i1.7.25972