Mobility Prediction And Semantic Inference Based On GPS Data

With the development of technology,we are able to acquire massive trajectory data.LBS based on trajectory-oriented data mining has been widely used in daily life,business decision and urban management.In this background,knowledge discovery through trajectory-oriented data mining has become the focus in the related subjects.The contents of this paper include:We built the mobility prediction model based on Markov Chains.we first extract the region-of-interest(ROI)from the historical location data.With plenty of statistics the original trajectory is represented by Markov chains composed by many ROIs.To improve the performance of the prediction,we extend 1st-order Markov chains to Kth-order Markov chains by reconstituting the structure of priori knowledge,which is intended to take more significant historical information into consideration.We evaluate the certainty of the prediction outcomes in terms of information entropy.We demonstrate that the prediction using a higher-order Markov chain can be more accurate compared with a 1st-order Markov chain.We introduced ontology into semantic mining.We constructed the position trajectory ontology,and then construct the priori knowledge for reasoning.Finally,We made an inference of identity characteristics based on ontology,making the position semantic inference more normalized,more standardized,more easy to share.We wrote position data mining and visualization platform software.The software abstracted common trajectory data mining procedure and realized many core functions,such as heat map,data management,trajectory structuring,O/D analysis,personalized regional construction,and so on,which laid a solid foundation for more complex trajectory data analysis application.