TY - GEN
T1 - HTTP
T2 - 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012
AU - Lee, Wang Chien
AU - Si, Weiping
AU - Chen, Ling Jyh
AU - Chen, Meng Chang
PY - 2012
Y1 - 2012
N2 - In this paper, we develop a new bus travel time prediction framework, called Historical Trajectory based Travel/Arrival Time Prediction (HTTP) for real-time prediction of travel time over future segments (and thus the arrival time at stops) of an on-going bus journey. The basic idea behind HTTP is to use a collection of historical trajectories "similar" to the current bus trajectory to predict the future segments. Specifically, the HTTP framework (1) samples a set of similar trajectories as the basis for travel time estimation instead of relying on only one historical trajectory best matching the on-going bus journey; and (2) explores different prediction schemes, namely, passed segments, temporal features, and hybrid methods, to identify the sample set of similar trajectories. We conduct a comprehensive empirical experimentation using real bus trajectory data collected from Taipei City, Taiwan to validate our ideas and to evaluate the proposed schemes. Experimental result shows that the proposed prediction schemes significantly outperforms the state-of-the-art and baseline techniques.
AB - In this paper, we develop a new bus travel time prediction framework, called Historical Trajectory based Travel/Arrival Time Prediction (HTTP) for real-time prediction of travel time over future segments (and thus the arrival time at stops) of an on-going bus journey. The basic idea behind HTTP is to use a collection of historical trajectories "similar" to the current bus trajectory to predict the future segments. Specifically, the HTTP framework (1) samples a set of similar trajectories as the basis for travel time estimation instead of relying on only one historical trajectory best matching the on-going bus journey; and (2) explores different prediction schemes, namely, passed segments, temporal features, and hybrid methods, to identify the sample set of similar trajectories. We conduct a comprehensive empirical experimentation using real bus trajectory data collected from Taipei City, Taiwan to validate our ideas and to evaluate the proposed schemes. Experimental result shows that the proposed prediction schemes significantly outperforms the state-of-the-art and baseline techniques.
UR - http://www.scopus.com/inward/record.url?scp=84872783298&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84872783298&partnerID=8YFLogxK
U2 - 10.1145/2424321.2424357
DO - 10.1145/2424321.2424357
M3 - Conference contribution
AN - SCOPUS:84872783298
SN - 9781450316910
T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
SP - 279
EP - 288
BT - 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012
Y2 - 6 November 2012 through 9 November 2012
ER -