2020/11/10 by Nicolas Chiabaut, Chiabaut, Nicolas, Rémi Faitout +1 · 1 citation
Engineering · Social Sciences · #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Physics and Society (physics.soc-ph) #Traffic Prediction and Management Techniques #Traffic control and management #Transportation Planning and Optimization
paper · pdf · doi:10.48550/arxiv.2011.05073
openalex publication_date 2020/11/10 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
In this paper, a new practice-ready method for the real-time estimation of\ntraffic conditions and travel times on highways is introduced. First, after a\nprincipal component analysis, observation days of a historical dataset are\nclustered. Two different methods are compared: a Gaussian Mixture Model and a\nk-means algorithm. The clustering results reveal that congestion maps of days\nof the same group have substantial similarity in their traffic conditions and\ndynamic. Such a map is a binary visualization of the congestion propagation on\nthe freeway, giving more importance to the traffic dynamics. Second, a\nconsensus day is identified in each cluster as the most representative day of\nthe community according to the congestion maps. Third, this information\nobtained from the historical data is used to predict traffic congestion\npropagation and travel times. Thus, the first measurements of a new day are\nused to determine which consensual day is the closest to this new day. The past\nobservations recorded for that consensual day are then used to predict future\ntraffic conditions and travel times. This method is tested using ten months of\ndata collected on a French freeway and shows very encouraging results.\n