Traffic congestion and travel time prediction based on historical congestion maps and identification of consensual days

In this paper, a new practice-ready method for the real-time estimation of traffic conditions and travel times on highways is introduced. First, after principal component analysis, observation days historical dataset are clustered. Two different methods compared: Gaussian Mixture Model k-means algorithm. The clustering results reveal that congestion maps same group have substantial similarity in their dynamic. Such map binary visualization propagation freeway, giving more importance to dynamics. Second, consensus day identified each cluster as most representative community according maps. Third, information obtained from data used predict times. Thus, first measurements determine which consensual closest day. past observations recorded then future This tested using ten months collected French freeway shows very encouraging results.