A Campus Carpooling System Based on GPS Trajectories
- 375 Downloads
College students are special because they relatively have tighter in economy but have greater consistency in leisure time. They prefer to go out together with schoolfellows due to higher trusts and closeness. Moreover, the electronic map is difficult to be updated. Campus-roads recently are updated rapidly. And many alleys in campuses are not shown in the electronic map. Therefore, we devise and implement a campus carpooling system based on GPS trajectories. It includes three parts. Firstly, the campus road network is extracted based on GPS trajectories. Next, the shortest sharing path in the campus is computed in terms of the campus road network. Then, passengers are matched automatically by the carpooling matching algorithm (CMA) in our system. Experiments show that our system is able to provide a safer and more comfortable carpooling experience for college students.
KeywordsTrajectory mining Campus carpooling Road network extraction Carpooling matching algorithm (CMA) The shortest sharing path
This work is supported by National Nature Science Foundation of China (Grant No. 41871320); the Provincial and Municipal Joint Fund of Hunan Provincial Natural Science Foundation of China (Grant No. 2018JJ4052); Hunan Provincial Natural Science Foundation of China (Grant No. 2017JJ2099 and 2017JJ2081); Hunan Provincial Education Department of China (Grant No. 18B200, 17C0646, and 10C0688); Undergraduate Scientific Research Innovation Plan of Hunan University of Science and Technology (Grant No. SYZ2018042).
- 1.Chen, L., et al.: Price-and-time-aware dynamic ridesharing. In: IEEE 34th International Conference on Data Engineering (ICDE), Paris, France, pp. 1061–1072 (2018)Google Scholar
- 2.Bozdog, N., Makkes, M., Halteren, A., Bal, H.: RideMatcher: peer-to-peer matching of passengers for efficient ridesharing. In: 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), Washington, DC, USA, pp. 263–272 (2018)Google Scholar
- 3.Madria, S., Yeung, S., Ward, K.: Ridesharing-inspired trip recommendations. In: 19th IEEE International Conference on Mobile Data Management (MDM), Aalborg, Denmark, pp. 34–39 (2018)Google Scholar
- 9.Luo, X.: Regional transfer service based on taxi carpooling. Sun Yat-Sen University (2015). (in Chinese)Google Scholar
- 10.Nie, C., Tang, D., Xu, T.: Research on taxi mixing scheduling mode based on calling platform. J. Wuhan Univ. Technol. (Transp. Sci. Eng.) 39(04), 807–809 (2015). (in Chinese)Google Scholar
- 14.Zhang, M., Liu, J., Liu, Y., Hu, Z., Yi, L.: Recommending pick-up points for taxi-drivers based on spatio-temporal clustering. In: Proceedings of the 2nd International Conference on Cloud and Green Computing (CGC 2012), pp. 67–72 (2012)Google Scholar
- 15.Zhang, J., Liao, Z., Liu, Y.: Fusing geographic information into latent factor model for pick-up region recommendation. In: Proceedings of 6th IEEE International Workshop on Mobile Multimedia Computing in conjunction with ICME 2019, Shanghai, China (2019)Google Scholar
- 16.Blerim, C., Athina, M., Nikolaos, L.: SORS: a scalable online ridesharing system. In: IWCTS 2016, Burlingame, CA, USA (2016)Google Scholar
- 18.Li, H., Liu, J., Liu, Y., Jin, L.: Evaluating roving patrol effectiveness by GPS trajectory. In: DASC 2011, pp. 832–837 (2011)Google Scholar
- 19.Zhang, L., Thiemann, F., Sester, M.: Integration of GPS traces with road map. In: Proceedings of the Second International Workshop on Computational Transportation Science, pp. 17–22. ACM (2010)Google Scholar
- 20.Liu, X., Zhu, Y., Wang, Y.: Road recognition using coarse-grained vehicular traces. Technical report HPL-2012-26, HP Labs (2012)Google Scholar