An algorithm for city transport arrival time estimation using adaptive elementary predictions composition

The problem of precise arrival time of public transport is considered in this paper. There is proposed a new prediction algorithm based on adaptive composition model using elementary prediction. A small number of adaptive parameters characterizes each elementary prediction algorithm. Adaptability means that parameters of the constructed compositions depend on a number of control parameters of the model, which includes the following factors: weather conditions, traffic density, driving dynamics, prediction horizon, etc. Adaptability is achieved by introducing a hierarchical decomposition range of control parameters used in regression tree. We made experimental investigations on real routes of city public transport in Samara to evaluate the prediction accuracy of the proposed algorithm. We also explain the advantages of the proposed solution in comparison with existing ones.