Traffic congestion prediction is one of the solution to overcome congestion problem. In this paper, we propose a development of system that can predict traffic speed with help of GPS data from history of taxi trip in Bandung city. GPS data from taxi trip in Bandung city does not have data speed and sometimes the location detected from GPS device is less accurate so additional steps required in data preprocessing phase. We proposed using Map Matching with topological information method in pre-processing phase. Map Matching will produce a new trajectory that has corresponded to the road. Then, from that new trajectories we calculate speed for each road segment. To predict traffic speed in the future we utilize Support Vector Regression (SVR) method. The results of this study indicate that Map Matching can help to obtain more accurate traffic speed and SVR has good performance to predict the traffic speed.
Traffic speed prediction from GPS data of taxi trip using support vector regression
2017-11-01
532327 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Bayesian Support Vector Regression for traffic speed prediction with error bars
DSpace@MIT | 2013
|