A Research Of Vehicle Trajectory Destination Prediction Method Based On Neural Network

Vehicle destination prediction,which is to predict the final destination based on initial partial trajectories,plays an important role in location-based services(LBSs)and urban computing.Several studies on destination prediction make use of extra information which is often unavailable.Many existing approaches are based on various Markov chain models,while they have significant drawbacks due to the Markov property.In general,the solution based on neural networks performs much better than the above approaches,in which Recurrent Neural Networks(RNNs)provide an effective temporal processing capacity for destination prediction.The Echo State Network(ESN)is the state-of-the-art approach for the design of efficiently trained RNNs,which provides an architecture and supervised learning principle.In this work,we adapt the deep Echo State Network(deepESN)model to taxi destination prediction,which uses only historic trajectories and achieves good results.Based on the original deepESN,we propose a novel model called deepESN with Dual Input(deepESN-DI)to address the time consuming limitation of deepESN in training with large amount of data,and achieve better prediction results.Experimental results using the dataset provided by the Kaggle taxi trajectory prediction challenge show that our deepESN-DI approach outperforms other destination prediction models based on neural networks,namely the Multi-Layer Perceptron(MLP),RNN and the shallow ESN architectures.The performance of the Dual Input Deep Echo State Network combined with Multi-Layer Perceptron(deepESN-DI-MLP)we proposed is the best among all kinds of models.As the application and exploration of the research work,this paper uses the real traj ectory data of Didichuxing to build a Bubble-Call Rate prediction model based on trajectory features.The model achieves good prediction results,which will effectively improve the accuracy of Didichuxing's user subsidies and save the subsidy cost.