Advertisement

The Self-Adapted Taxi Dispatch Platform Based on Geographic Information System

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 236)

Abstract

In order to improve the efficiency of taxi dispatching, we build a center-controlled, real-time management system. With the help of the real-time data collected by recorders in taxis and the wavelet neural network utilized to predict passenger current, the whole system can work more precisely. Besides, the exceptional situations are also taken into consideration in this system. Thus, the whole system is able to distribute taxis efficiently in any situation. Simulation results indicate that the wavelet neural network could make more accurate prediction than former methods and the self-adapting distribution strategy can increase load rate effectively.

Keywords

Taxi dispatching Passenger flow prediction Dynamic model 

Notes

Acknowledgments

The project was supported by the Fundamental Research Founds for National University, China University of Geosciences (Wuhan) 1210491B08.

References

  1. 1.
    An, S., Qi, L.: Assessment and prediction of the number of taxicab. Technol. Econ. Areas Commun. 3, 34–37 (2010)Google Scholar
  2. 2.
    Tao, C.C.: Dynamic taxi-sharing service using intelligent transportation system technologies. Wirel. Commun. Netw. Mobile Comput. Conf. 5, 3209–3212 (2007)Google Scholar
  3. 3.
    Qian, S., Zhang, Y., Huang, S.: Intelligent transport clouds: ITS based on cloud computing. Comput. Modern. 183, 168–171 (2010)Google Scholar
  4. 4.
    Yi, L., Wang, L.-z, Lu, X.: Study on the simulation and prediction model for urban Taxi’s demand. J. Changsha Commun. Univ. 23(4), 23–27 (2007)MathSciNetGoogle Scholar
  5. 5.
    Ren, C., Cao, C., Li, J., Shi, W.-W.: Research for short-term passenger flow forecasting based on wavelet neural network. Sci. Technol. Engi. 11(21), 5099–5103 (2011)Google Scholar
  6. 6.
    Li, S., Jiang, H., Wang, F. Application of heredetary neural net in public transport passenger volume forecast. Commun. Stand. 160, 161–165 (2006)Google Scholar
  7. 7.
    Hang, J., Han, B.: Comprehensive post-evaluation for the passenger prediction of urban rail based onPSR. Urban Mass Transit. 8, 31–35 (2011)Google Scholar
  8. 8.
    Wang, J., Lu, X., Li, J.: Multi-Layer BP neural network comprehensive evalution on the ability ot interated passenger transportation on the urban and rural roads. Dystems Eng. 25(3), 83–86 (2007)Google Scholar
  9. 9.
    Zhang, Y.: Road transportation systems engineering. China Commun. Press 5, 101–105 (2004)Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Faculty of Information EngineeringChina University of GeosciencesWuhanChina

Personalised recommendations