An Effective Taxi Recommender System Based on A Spatiotemporal Factor Analysis Model

  • Mayuri Jadhav University of Pune
  • Varsha A Gadge
  • Vaishali Ghumare
Keywords: crowded, fleet, recommender, trajectory

Abstract

—For the effective Taxi business we developed the fleet management system based on GPS which is important tool, as well as its useful to provide information to taxi driver for earning profit by mining the historical GPS path of the projectiles. In the literature, distance between current place and recommended place, time for next passengers and exact fare of trip these three factors provide the similar objective have been considered in different work. In this paper, in addition to this factor we added one more factor that is based on driver’s experience which is most likely locations to pick up the passenger given the current passenger drop off location .the one location and another location graph model referred to as OFF-ON model is worked for define the relation between the get off location and next passengers get on location. To estimate the expected fare for a trip started at a recommended location we adopted an ON-OFF model. A real world dataset from CRAWDAD is used to evaluate the proposed system. A simulator has been developed for the simulate journey behavior of taxies in database. Our proposed system still effective on recommending better profitable cruising location.

References

[1] J. W. Powell, Y. Huang, F. Bastani, and M. Ji, Towards reducing taxicab cruising time using spatio-temporal profitability maps,” in Proceedings of the 12th international conference on Advances in spatial and temporal databases, Berlin, Heidelberg, 2011, pp. 242– 260.
[2] H.-W. Chang, Y. chin Tai, and J. Y. jen Hsu, “Contextaware taxi demand hotspots prediction,” IJBIDM, vol. 5, no. 1, pp. 3–18, 2010.
[3] L. Moreira-Matias, R. Fernandes, J. Gama, M. Ferreira, J. o. Mendes-Moreira, and L. Damas, “An online recommendation system for the taxi stand choice problem (poster).” in VNC, 2012, pp. 173–180.
[4] J. Yuan, Y. Zheng, L. Zhang, X. Xie, and G. Sun, “Where to find my next passenger,” in Proceedings of the 13th international conference on Ubiquitous computing, New York, NY, USA, 2011, pp. 109–118.
[5] [5] T. Takayama, K. Matsumoto, A. Kumagai, N. Sato, and Y. Murata, “Waiting/cruising location recommendation based on mining on occupied taxi data,” International ournal of Systems Applications, Engineering and Development, vol. 5, no. 2, pp. 224–236, 2011.
[6] J. Yuan, Y. Zheng, C. Zhang, W. Xie, X. Xie, G. Sun, and Y. Huang, “Tdrive: driving directions based on taxi trajectories,” in Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, New York, NY, USA, 2010, pp. 99–108. [7] Y. Yue, Y. Zhuang, Q. Li, and Q. Mao, “Mining timedependent attractive areas and movement patterns from
taxi trajectory data,” in the 17th International Conference on Geoinformatics, 2009, pp. 1–6.
[8] Y. Zheng, L. Zhang, X. Xie, and W.-Y. Ma, “Mining interesting locations and travel sequences from gps trajectories,” in the 18th international conference on World wide web, 2009, pp. 791–800.
[9] J. B. MacQueen, “Some methods for classification and analysis of multivariate observations,” in the fifth Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, 1967, pp. 281–297.
[10] M. Ester, H. peter Kriegel, J. S, and X. Xu, “A densitybased algorithm for discovering clusters in large spatial databases with noise,” in the 2nd International Conference on Knowledge Discovery and Data Mining, 1996, pp. 226–231.2014 International Conference on Computing, Networking and Communications, Mobile Computing & Vehicle Communications Symposium 433.
Published
2018-03-22
How to Cite
Jadhav, M., Gadge, V., & Ghumare, V. (2018). An Effective Taxi Recommender System Based on A Spatiotemporal Factor Analysis Model. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 3(3). Retrieved from http://asianssr.org/index.php/ajct/article/view/149
Section
Article

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.