CLEAN: Frequent pattern-based trajectory compression and computation on road networks

摘要: The volume of trajectory data has become tremendously huge in recent years. How to effectively and efficiently maintain compute such a challenging task. In this paper, we propose spatial temporal compression framework, namely CLEAN. key is mine meaningful frequent patterns on road network. By treating the mined as dictionary items, long trajectories have chance be encoded by shorter paths, thus leading smaller space cost. And an error-bounded carefully designed top identified for much low Meanwhile, are also utilized improve performance two applications, range query clustering, without decompression overhead. Extensive experiments real datasets validate that CLEAN significantly outperforms existing state-of-art approaches terms spatial-temporal applications.