Academic Journal of Computing & Information Science, 2021, 4(7); doi: 10.25236/AJCIS.2021.040702.
Yaxian Huang1, Yanping Liang1, Jiawen Xue2
1School of Traffic and Transportation, Beijing Jiaotong University, Beijing, China
2Shenzhen Urban Transport Planning Center, Shenzhen, China
Taxi, as one of the important passenger transportation modes in cities, has always had the problem of imbalance between supply and demand. Analyzing the characteristics of taxi travel distribution can effectively help relevant departments realize scientific taxi dispatch, thereby solving the contradiction between supply and demand between taxis and passengers. To achieve the above goals, this article takes Beijing as an example, and analyzes the temporal and spatial distribution characteristics of taxi travel based on the GPS data of taxis in Beijing from January 1 to January 14, 2019. The research results show that: in terms of time, the total number of taxi trips on weekdays is higher than that on weekdays. The peak average total number of trips on weekdays is 14,000 passengers/h, and on weekends it is 10,000 passengers/h. Spatially, the distribution of taxi trips is consistent, mainly in core areas such as essential transportation hubs.
Taxi, Time distribution, Spatial distribution, Traffic Planning
Yaxian Huang, Yanping Liang, Jiawen Xue. Analysis of Taxi Trip Distribution Characteristics Based on GPS Data. Academic Journal of Computing & Information Science (2021), Vol. 4, Issue 7: 7-10. https://doi.org/10.25236/AJCIS.2021.040702.
[1] S. L. Handy, M. G. Boarnet, R. Ewing, How the built environment affects physical activity: views from urban planning. American Journal of Preventive Medicine, 2002, 23(2-supp-S1):64-73.
[2] J. Gutierrez, O. D. Cardozo, J. C. Garcia, Transit ridership forecasting at station level: an approach based on distance-decay weighted regression. Journal of transport geography, 2011,19(06): 1081-1092.
[3] Zegrasc, The built environment and motor vehicle ownership and use: evidence from Santiago de Chile. Urban Studies, 2010,47(08): 1793-1817.
[4] L. M. Yang, B. X. Hua, W. L. Min, A method of two-stage clustering learning based on improved DBSCAN and density peak algorithm. Computer Communications, 2021,167(18): 101-124.
[5] R. Wanm, A review on data cleansing methods for big data. Procedia Computer Science, 2019,161: 731-738.
[6] B. Kuta, ST-DBSCAN: An algorithm for clustering spatial-temporal data. Data & Knowledge Engineering, 2007,60(1): 208-221.
[7] D. Liu, S. Cheng, Y. Yang. Density peaks clustering approach for discovering demand hot spots in city-scale taxi fleet dataset: IEEE, 2015.