A real time forecasting tool for dynamic travel time from clustered time series

摘要: This paper addresses the problem of dynamic travel time (DT T) forecasting within highway traffic networks using speed measurements. Definitions, computational details and properties in construction DT T are provided. is dynamically clustered a K-means algorithm then information on level trend centroid clusters used to devise predictor computationally simple be implemented. To take into account lack cluster assignment for new predicted values, weighted average fusion based similarity measurement proposed combine predictions each model. The deployed real application performance evaluated data from South Ring Grenoble city France.