Effective data identification in travel time estimation based on cellular network signaling

The technology of travel time estimation based on cellular network has received much attention recently because of its low cost, wide spread of cellular networks, and a large number of phones as potential road traffic probes. However, in practice, low positioning precision and uncertain route determination caused by complex traffic network make it difficult to ensure the accuracy of travel time estimation. In this paper, we propose a complete set of travel time estimation model, including data preprocessing, map matching, route determination and traffic state calculation. In order to avoid the influence of the blindness of road route choice to the traffic state calculation, a effective data identification model based on SVM is established, so as to turn the problem of effective data identification into data classification problem. The experimental results show that, in the suburban environment the classification problem can be solved rather efficiently.