Parking Space Information Prediction Based on Phrase Construction and Elman Neural Network

With respect to the prediction of short-term unoccupied parking space of parking guidance and information system(PGIS),phrase construction is proposed to be used in combination with Elman neural network to predict the chaotic time series.Based on an analysis of the principle of phrase construction,the time series prediction model is established and then simulated by Elman neural network.The detailed process and steps of this prediction method of combining phrase construction with Elman neural network are introduced and evaluation indices of short-term unoccupied parking space prediction are presented.An application study shows that this method is effective and can be used in the prediction of short-term unoccupied parking space of parking guidance and information system.