ETCPS: An Effective and Scalable Traffic Condition Prediction System
Real-time prediction of the traffic condition is an important ingredient for a variety of applications. In this paper, we propose an Ensemble based Traffic Condition Prediction System (ETCPS) for predicting the traffic conditions of any roads in a city based on the current and historical GPS data collected from floating vehicles. We have observed two useful correlations in the traffic condition time series, which are the bases of our design. In order to exploit these two correlations for prediction, we propose two different models called Predictive Regression Tree (PR-Tree) and Spatial Temporal Probabilistic Graphical Model (STPGM). Our best quality prediction is achieved by a careful ensemble of the two models. Our system provides high-quality prediction and can easily scale to very large datasets. We conduct extensive experimental evaluations with a large GPS data set collected from more than 12,000 taxis in Beijing during two months. The experimental results demonstrate the effectiveness, efficiency, and scalability of our system.
KeywordsRoad Network Leaf Node Road Segment Traffic Condition Discrete Time Markov Chain
This work was supported in part by the National Basic Research Program of China grants 2015CB358700, 2011CBA00300, 2011CBA00301, and the National NSFC grants 61033001, 61361136003.
- 1.Asghari, M., Emrich, T., Demiryurek, U., Shahabi, C.: Probabilistic estimation of link travel times in dynamic road networks. In: ACM SIGSPATIAL (2015)Google Scholar
- 4.Hunter, T., Herring, R., Abbeel, P., Bayen, A.: Path and travel time inference from GPS probe vehicle data. NIPS Anal. Netw. Learn. Graphs 12(1) (2009)Google Scholar
- 5.Kwon, J., Murphy, K.: Modeling freeway traffic with coupled HMMs. Technical report, University of California, Berkeley (2000)Google Scholar
- 7.Lou, Y., Zhang, C., Zheng, Y., Xie, X., Wang, W., Huang, Y.: Map-matching for low-sampling-rate GPS trajectories. In: Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 352–361. ACM (2009)Google Scholar
- 8.Ma, S., Zheng, Y., Wolfson, O.: T-share: a large-scale dynamic taxi ridesharing service. In: 2013 IEEE 29th International Conference on Data Engineering (ICDE), pp. 410–421. IEEE (2013)Google Scholar
- 10.Wang, Y., Zheng, Y., Xue, Y.: Travel time estimation of a path using sparse trajectories. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 25–34. ACM (2014)Google Scholar
- 14.Yuan, J., Zheng, Y., Zhang, C., Xie, X., Sun, G.Z.: An interactive-voting based map matching algorithm. In: Proceedings of the 2010 Eleventh International Conference on Mobile Data Management, pp. 43–52. IEEE Computer Society (2010)Google Scholar