%0 Book Section %1 lippi2010collective %A Lippi, Marco %A Bertini, Matteo %A Frasconi, Paolo %B ECML/PKDD (2) %D 2010 %E Balcázar, José L. %E Bonchi, Francesco %E Gionis, Aristides %E Sebag, Michèle %I Springer %K ilp intelligenzaartificiale machinelearning relazione2010 %P 259-273 %R 10.1007/978-3-642-15883-4_17 %T Collective Traffic Forecasting %U http://dx.doi.org/10.1007/978-3-642-15883-4_17 %V 6322 %X Traffic forecasting has recently become a crucial task in the area of intelligent transportation systems, and in particular in the development of traffic management and control. We focus on the simultaneous prediction of the congestion state at multiple lead times and at multiple nodes of a transport network, given historical and recent information. This is a highly relational task along the spatial and the temporal dimensions and we advocate the application of statistical relational learning techniques. We formulate the task in the supervised learning from interpretations setting and use Markov logic networks with grounding-specific weights to perform collective classification. Experimental results on data obtained from the California Freeway Performance Measurement System (PeMS) show the advantages of the proposed solution, with respect to propositional classifiers. In particular, we obtained significant performance improvement at larger time leads.

@incollection{lippi2010collective, abstract = {Traffic forecasting has recently become a crucial task in the area of intelligent transportation systems, and in particular in the development of traffic management and control. We focus on the simultaneous prediction of the congestion state at multiple lead times and at multiple nodes of a transport network, given historical and recent information. This is a highly relational task along the spatial and the temporal dimensions and we advocate the application of statistical relational learning techniques. We formulate the task in the supervised learning from interpretations setting and use Markov logic networks with grounding-specific weights to perform collective classification. Experimental results on data obtained from the California Freeway Performance Measurement System (PeMS) show the advantages of the proposed solution, with respect to propositional classifiers. In particular, we obtained significant performance improvement at larger time leads.}, added-at = {2010-12-16T17:56:13.000+0100}, affiliation = {Dipartimento Sistemi e Informatica, Università degli Studi di Firenze}, author = {Lippi, Marco and Bertini, Matteo and Frasconi, Paolo}, biburl = {https://www.bibsonomy.org/bibtex/29950270842cd1c0d99072ec57b095de6/naufraghi}, booktitle = {ECML/PKDD (2)}, doi = {10.1007/978-3-642-15883-4_17}, editor = {Balcázar, José L. and Bonchi, Francesco and Gionis, Aristides and Sebag, Michèle}, interhash = {1a0925cfca772def2e81178aec31d060}, intrahash = {9950270842cd1c0d99072ec57b095de6}, keywords = {ilp intelligenzaartificiale machinelearning relazione2010}, pages = {259-273}, publisher = {Springer}, timestamp = {2010-12-16T17:56:13.000+0100}, title = {Collective Traffic Forecasting}, url = {http://dx.doi.org/10.1007/978-3-642-15883-4_17}, volume = 6322, year = 2010 }