Short-term free parking berths prediction based on multitask - DBN neural network.

Aiming at the problem of low prediction accuracy and slow training time for Neural network with single hidden layer forecast, this paper proposes a combination of Multitask and DBN Neural network used to predict the short-term free parking berths. Firstly, the DBN Neural Network is used to carry out auto correlation analysis of the original data, and the characteristics of the data inclusion are obtained. Combined with Multitask Learning, the paper studies several related tasks simultaneously, the Neural Network can have the knowledge to new things for forecasting, and compared with the existing Neural network with single hidden layer, the data preprocessing process is reduced and better prediction results are obtained. The results show that this method shortens the training time and improves the prediction results.