© The Institution of Engineering and Technology
The use of stored public transportation data facilitates the identification of potential issues with urban traffic flow. Focusing on buses, the authors proceed from a city-level delay distribution analysis to a detailed understanding of the factors that cause the delays on an example bus line. First, a database of bus data in Tampere was mined to detect any regular patterns in the distribution of delays in time, location or according to bus line throughout the city. The results allow the authors to focus on those areas and lines which are most prone to delays. In a case study, they illustrate that the most important reasons for tardy journeys are the long waiting times at traffic signals and bus stops, rather than slow driving speeds. The results are then further deepened to show spatially on a map which bus stops and intersections tend to be the ones where the time variances are high. The same methods can be applied to any other city for which the same kind of data are available.
References
-
-
1)
-
15. Pu, W., Lin, J.: ‘Urban travel time estimation using real time bus tracking data’. Transport, Chicago, 2008.
-
2)
-
17. Tan, P.-N.S.: ‘Introduction to data mining’ (Addison-Wesley, Boston, Massachusetts 2006).
-
3)
-
4)
-
8. Coffey, C., Pozdnoukhov, A., Calabrese, F.: ‘Time of arrival predictability horizons for public bus routes’. Fourth ACM SIGSPATIAL Int. Workshop on Computational Transportation Science, pp. 1–5.
-
5)
-
6)
-
7)
-
8)
-
9. Guangtao, X.Z.: ‘Traffic-known urban vehicular route prediction based on partial mobility patterns’. 15th Int. Conf. on Parallel and Distributed Systems (ICPADS), 2009, pp. 369–375.
-
9)
-
18. Han, J.K.: ‘Data mining: concepts and techniques slides of the book’ (Morgan Kauffman, 2006).
-
10)
-
6. Hardy, N.: ‘Moving to and automated bus performance monitoring regime’. Proc. Tenth ITS European Congress, Helsinki, Finland, June 2014.
-
11)
-
11. Zhu, F.: ‘Mining ship spatial trajectory patterns from AIS database for maritime surveillance’. Second IEEE Int. Conf. on Emergency Management and Management Sciences (ICEMMS) 2011, pp. 772–775.
-
12)
-
10. Jae-Gil, L.J.: ‘Mining discriminative patterns for classifying trajectories on road networks’, IEEE Trans. Knowl. Data Eng., 2011, pp. 713–726.
-
13)
-
14)
-
7. Hounsell, N., Shrestha, B., D'Souza, C.: ‘Using automatic vehicle location (AVL) data for evaluation of bus priority at traffic signals’. IET and ITS Conf. on Road Transport and Control (RTIC 2012), pp. 1–6.
-
15)
-
12. Bejan, A., Gibbens, R., Evans, D., Beresford, A., Bacon, J., Friday, A.: ‘Statistical modelling and analysis of sparse bus probe data in urban areas’. 13th Int. Conf. on Intelligent Transportation Systems 2010, pp. 1256–1261.
-
16)
-
4. Kerminen, R., Hakulinen, E., Nummenmaa, J., et al: ‘Analysis of bus delays in Tampere using real-time data’. Proc. Tenth ITS European Congress, Helsinki, Finland, June 2014.
-
17)
-
16. Baptista, A.T., Bouillet, E., Calabrese, F., Verscheure, O.: ‘Towards building an uncertainty-aware personal journey planner’. 14th Int. IEEE Conf. on Intelligent Transportation Systems, Washington, DC, USA, 5–7 October 2011, pp. 378–383.
-
18)
-
19)
-
20)
-
5. Thanisch, P., Nummenmaa, J., Syrjärinne, P., et al: ‘Risking the public transportation connection’. Proc. Tenth ITS European Congress, Helsinki, Finland, June 2014.
-
21)
-
13. Bejan, A., Gibbens, R.: ‘Evaluation of velocity fields via sparse bus probe data in urban areas’. 14th Int. Conf. on Intelligent Transportation Systems, 2011, pp. 746–753.
-
22)
-
14. Uno, N., Kurauchi, F., Tamura, H., Iida, Y.: ‘Using bus probe data for analysis of travel time variability’, J. Intell. Transp. Syst., Technol. Plan. Oper., 2009, 13, (1), pp. 2–15 (doi: 10.1080/15472450802644439).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2014.0192
Related content
content/journals/10.1049/iet-its.2014.0192
pub_keyword,iet_inspecKeyword,pub_concept
6
6