無樁共享單車系統為用戶提供了一種便捷的交通方式，讓用戶可以在任何地方租用或歸還自行車。由於用戶可能會將自行車歸還到非法位置，對他人造成困擾。為了解決這個問題，地理圍欄技術被引入了無樁共享單車系統，並裝備在共享單車系統中來限制使用者借還車的區域。然而，地理資源利用不夠妥善和分佈不合理，影響了地理圍欄站點的有效性。
本論文提出了一種動態調度地理圍欄站點方法，此方法首先根據歷史流量密度對區域進行流量排名，然後將地理圍欄分配給排名靠前的區域，最後系統根據使用情況調整地理圍欄用戶申請的區域選擇系統性能較好的位置，並將剩餘的地理圍欄分配給用戶。這個演算法旨在優化城市中每一個地理圍欄的分佈位置和用戶滿意度，並在不改變滿意度的情況下盡可能減少地圖上的地理圍欄數量，實驗結果顯示，這個演算法用於地理圍欄站點分佈具有較高的滿意度和利用率。

Dockless bike-sharing systems provide users with a convenient means of transportation to use, rent, or return bikes anywhere using GPS-based mobile devices.
In this system, user satisfaction is defined as the probability of all users renting a bicycle and having a place to return the bicycle.

Making the system troublesome for others as the user may return the bike to an illegal location. To solve this problem, some people introduced geofence technology into the dockless shared bicycle system and then equipped geofence with the shared bicycle system.
However, the underutilization of geographic resources severely affects the effectiveness of geofencing sites.

A scheduling dynamic geofence sites algorithm (SDGS) is proposed in this thesis. First, areas are ranked by traffic based on historical traffic density. Geofences are assigned to the top-ranked areas.
Finally, the system selects a location with better system performance based on the usage adjustment geofence area that the user applies for. The algorithm improves the usage of each geofence in the city, increases user satisfaction, and reduces the number of geofences on the map without reducing satisfaction.

The experimental results show that SDGS has high satisfaction and utilization rate for geofencing site distribution.

[1] Z. Liu, Y. Shen, and Y. Zhu, “Where will dockless shared bikes be stacked? — parking hotspots detection in a new city,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Aug. 2018, pp. 566–575.
[2] Y. Li, Y. Zheng, and Q. Yang, “Dynamic bike reposition: A spatio-temporal reinforcement learning approach,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Aug. 2018, pp. 1724– 1733.
[3] E. Fishman, “Bikeshare: A review of recent literature,” Transport Reviews, vol. 36, no. 1, pp. 92–113, Dec. 2016.
[4] A. Greenwald, G. Hampel, C. Phadke, and V. Poosala, “An economically viable solution to geofencing for mass-market applications,” Bell Labs Technical Journal, vol. 16, no. 2, pp. 21–38, Sept. 2011.
[5] Y. Chen, P. Lv, D. Guo, T. Zhou, and M. Xu, “A survey on task and participant matching in mobile crowd sensing,” Journal of Computer Science and Technology, vol. 33, no. 4, pp. 768–791, July 2018.
[6] ——, “Trajectory segment selection with limited budget in mobile crowd sensing,” Pervasive and Mobile Computing, vol. 40, pp. 123–138, Sept. 2017.
[7] G. Cheng, Y. Guo, Y. Chen, and Y. Qin, “Designating city-wide collaborative geofence sites for renting and returning dock-less shared bikes,” Ieee Access, vol. 7, pp. 35 596–35 605, Mar. 2019.
[8] S. J. Kim and S. H. Lee, “An improved computation of the pagerank algorithm,” in European Conference on Information Retrieval. Springer, Mar. 2002, pp. 73–85.
[9] J. Froehlich, J. Neumann, and N. Oliver, “Sensing and predicting the pulse of the city through shared bicycling,” in International Joint Conferences on Artificial In telligence, vol. 9, July 2009, pp. 1420–1426.
[10] Y. Li, Y. Zheng, H. Zhang, and L. Chen, “Traffic prediction in a bike-sharing system,” in Proceedings of the 23rd SIGSPATIAL international conference on advances in geographic information systems, Nov. 2015, pp. 1–10.
[11] Y. Zhou and Y. Huang, “Context aware flow prediction of bike sharing systems,” in 2018 IEEE International Conference on Big Data, Dec. 2018, pp. 2393–2402.
[12] P. Lin, J. Weng, S. Hu, D. Alivanistos, X. Li, and B. Yin, “Revealing spatio-temporal patterns and influencing factors of dockless bike sharing demand,” IEEE Access, vol. 8, pp. 66 139–66 149, Apr. 2020.
[13] Y. Duan and J. Wu, “Optimizing the crowdsourcing-based bike station rebalancing scheme,” in 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS). IEEE, July 2019, pp. 1559–1568.
[14] Y. Teng, H. Zhang, X. Li, and X. Liang, “Optimization model and algorithm for dockless bike-sharing systems considering unusable bikes in china,” IEEE Access, vol. 8, pp. 42 948–42 959, Jan. 2020.
[15] H. Jia, H. Miao, G. Tian, M. Zhou, Y. Feng, Z. Li, and J. Li, “Multiobjective bike repositioning in bike-sharing systems via a modified artificial bee colony algorithm,” IEEE Transactions on Automation Science and Engineering, vol. 17, no. 2, pp. 909– 920, Apr. 2019.
[16] J. Bao, T. He, S. Ruan, Y. Li, and Y. Zheng, “Planning bike lanes based on sharing bikes’ trajectories,” in Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, Aug. 2017, pp. 1377–1386.
[17] P. Vogel, T. Greiser, and D. C. Mattfeld, “Understanding bike-sharing systems using data mining: Exploring activity patterns,” Procedia-Social and Behavioral Sciences, vol. 20, pp. 514–523, Aug. 2011.
[18] P. Vogel and D. C. Mattfeld, “Strategic and operational planning of bike-sharing systems by data mining–a case study,” in International conference on computational logistics. Springer, Sept. 2011, pp. 127–141.
[19] S. Ghosh, M. Trick, and P. Varakantham, “Robust repositioning to counter unpredictable demand in bike sharing systems,” Proceedings of the 25th International Joint Conference on Artificial Intelligence IJCAI, pp. 3096–3102, July 2016.
[20] A. Waserhole and V. Jost, “Pricing in vehicle sharing systems: Optimization in queuing networks with product forms,” EURO Journal on Transportation and Logistics, vol. 5, no. 3, pp. 293–320, May 2016.