Today portable devices as mobile phones, laptops, personal digital assistants(PDAs), and many other mobile devices are ubiquitous. Along with the rapid advances in positioning and wireless technologies, moving object position information has become easier to acquire. This availability of location information triggered the need for clustering and classifying location information to extract useful knowledge from it and to discover hidden patterns in moving objects' motion behaviors. Many existing

more »

... algorithms have studied clustering as an analysis technique to find data distribution patterns. In this paper we consider the clustering problem applied to moving object trajectory data. We propose a "time-based" clustering algorithm that adapts the k-means algorithm for trajectory data. We present two techniques: an exact, and an approximate technique. Besides, we present experimental results on both synthesized and real data that show both the performance and accuracy of our proposed techniques. KEYWORDS Moving object databases; mining moving object trajectories; clustering moving objects; and similarity search in moving object trajectories. For more details...