Location Extraction and Prediction Method Based on Floating Car Spatial-Temporal Trajectory

Abstract

Predicting the next important location by mining the user’s historical spatial-temporal trajectory can be done for behavioral analysis and path planning. Since extracting the important location precisely is the premise of next location prediction, an enhanced location extraction algorithm is proposed to meet the requirements of dynamic trajectory via dynamic parameter estimation. To realize the estimation of parameters dynamically, the differences of floating car velocity in terms of spatial distribution and behavior in time distribution are considered in the location extraction algorithm. Then, an improved recurrent neural network (RNN) model is designed to mine the variation law of floating car trajectories to improve the accuracy of important location prediction under different conditions. Different from the traditional prediction model considering only the constraint of distance, the attention mechanism and semantic information are considered simultaneously by the proposed prediction model. Finally, the floating car trajectory of Beijing is selected for our experiments, and the results show that the proposed location extraction algorithm can meet the requirements of a dynamic environment and our model achieves high prediction accuracy.