Senor based traffic flow prediction

Senor based traffic flow prediction

Official trade and traffic statistics are typically published periodically, i.e. monthly or bi-monthly, and have traditionally been based on questionnaires sent to transporting companies. The process of data collection, preparation and reporting is labour intensive, but also comes with delays between the activities and their publication. At the same time, traffic behaviour is intensely monitored in a variety of ways, through sensors in pavements, cameras, and weighing installations. The main question of this project has been how to combine data from various sources, monitoring data as well as official statistics, to estimate and forecast origin destination (OD) patterns of transportation. Research has led to enhancements of existing origin destimation estimation models, but also to innovative approaches to combine different data sources in a unified Bayesian network model.

External Partners

CBS: Statistics Netherlands


The project began in 2010 and was finished in 2014. The centre invites companies for new studies in this application domain.

Working/Published Papers

Ma, Y., Van Dalen, J., De Blois, C., Kroon, L., 2011. Estimation of dynamic traffic densities for official statistics. Transportation Research Record: Journal of the Transportation Research Board 2256 (-1), 104-111.

Ma, Y., van Dalen, J., Zuidwijk, R., de Blois, C., 2012. Dynamic weight capacity utilization and efficiency in freight transport: An application of weigh-in-motion data. In: Transportation Research Board 91st Annual Meeting. No. 12-3427.

Ma, Y., van Zuylen, H., Chen, Y., van Dalen, J., 2010. Allocating departure time slots to optimize dynamic network capacity. Transportation Research Record: Journal of the Transportation Research Board 2197 (-1), 98-106.

Ma,Y., Kuik, R. and Zuylen, H.J. van. Freight Origin Destination Estimation based on Multiple Data Sources (2012). The 15th International IEEE Conference on Intelligent Transportation Systems, USA.

Ma,Y., Kuik, R. and Zuylen, H.J. van. Day-to-day Origin Destination Tuple Estimation And Prediction with Hierarchical Bayesian Networks Using Multiple Data Sources, Journal of Transportation Research Record (accepted)

PhD Thesis

Yinyi Ma, n.d., The Use of Advanced Monitoring System Data of Freight Transport for Official Statistics