Probabilistic Threshold Range Aggregate Query Processing over Uncertain Data

Large amount of uncertain data is inherent in many novel and important applications such as sensor data analysis and mobile data, management. A probabilistic threshold range aggregate (PTRA) query retrieves summarized information about the uncertain objects satisfying a range query, with respect to a given probability threshold. This paper is the first one to address this important type of query. We develop a new index structure a,U-tree and propose an exact querying algorithm based on all-tree. For the pursue of efficiency, two techniques SingleSample and DoubleSample are developed. Both techniques provide approximate answers to a PTRA query with accuracy guarantee. Experimental study demonstrates the efficiency and effectiveness of our proposed methods.