Author: Manh Le
Abstract: Predicting the location of a mobile user is one of the important issues in mobile computing systems. Applications of the location prediction include adjusting the bandwidth of the mobile network, the location based services (LSB), smart handover, etc. However, the applications require the execution time of the User Mobility Patterns Mining (UMPMining) algorithm be instantaneous. In this paper, we propose a new algorithm named Find_UMP for mining next location of a mobile user. Our algorithm includes two phase as follows. In the first phase (Find_UMP_1), we make to reduce the complexity of the UMPMining algorithm. In the second phase (Find_UMP_2), we perform to reduce the number of transactions of the paths database. Results of our experiments show that our proposed algorithm outperforms the UMPMining algorithm in terms of the execution time.