Adapting Travel Time Estimates to Current Traffic Conditions
The paper demonstrates drifts in travel time estimates of a floating car data based car navigation system. The operation of such a navigation system starts with collecting floating car data, i.e. multi-channel stream data sent in from moving cars. These dynamic data are then processed in an elaborate, multistage procedure, aimed at estimating the travel time and constituting an essential component of optimal route planning, which can effectively find not only the shortest, but also the fastest road connections, always taking into account the current traffic conditions. The experiments present the ability of the navigation system to detect and handle unusual traffic situations, like unexpected jams caused by sudden road accidents, which manifest themselves in the drifts of travel time estimates. All experiments were conducted on exclusively real-life data, provided by NaviExpert, a Polish car navigation company.
Keywordsfloating car data travel time prediction concept drift
Unable to display preview. Download preview PDF.
- 1.Brosch, P.: A service oriented approach to traffic dependent navigation systems. In: IEEE Congress on Services - Part I, pp. 269–272 (2008)Google Scholar
- 2.Du, B., Xu, L., Ma, D., Lv, W., Zhu, T.: Missing data compensation model in real-time traffic information service system. In: Fifth International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2008, vol. 5, pp. 371–378 (2008)Google Scholar
- 3.de Fabritiis, C., Ragona, R., Valenti, G.: Traffic estimation and prediction based on real time floating car data. In: 11th International IEEE Conference on Intelligent Transportation Systems, ITSC 2008, pp. 197–203 (2008)Google Scholar
- 6.Hastie, T., Tibshirani, R., Friedman, J.H.: Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer (2003)Google Scholar