Learning Trajectory Information with Neural Networks and the Markov Model to Develop Intelligent Location-Based Services

In the development of location-based services, various location-sensing techniques and experimental/commercial services have been used. However, conventional location-based services are limited in terms of flexibility because they depend on the current location of the user. We propose a novel method of predicting the user's future movements in order to develop advanced location-based services. The user's movement trajectory is modelled using a combination of recurrent self-organising maps (RSOM) and the Markov model. Future movement is predicted based on past movement trajectories. A prototype application based on location prediction is also presented. This application is a mobile user assistant targeted to university students. To verify the proposed method, a GPS dataset was collected on the Yonsei University campus. The results were promising enough to confirm that the application works flexibly even in ambiguous situations.