Travel time is an inevitable and significant parameter in urban transportation planning and management. Due to the limitations of detectors and missing data, it is difficult to get complete travel time information in urban road networks. Here, we treat travel time estimation as a tensor completion problem, and propose a collaborative block term decomposition model using monitoring data in Ruian City. We model different drivers’ travel time on road segments in various time slots with a three dimensional tensor. Meanwhile, a historical travel time tensor is built to help to discovery underlying information and relieve the problem of data sparsity. Then, three feature matrices are extracted to capture the contextual information of travel time. The three matrices and the historical tensor are aided by the object function to solve the travel time estimation problem. Finally, experiments show that our model is an effective approach.
Personalized Travel Time Estimation Based on Collaborative Block Term Decomposition
20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)
CICTP 2020 ; 1-12
2020-08-12
Aufsatz (Konferenz)
Elektronische Ressource
Englisch