Concentric Hyperspaces and Disk Allocation for Fast Parallel Range Searching \Lambda

Efficient retrieval of data is a well-studied problem intraditional databases. Several index structures are proposed for efficient range, partial match, and similarity searchingin traditional databases. As databases increasingly integrate multimedia information in the form of image, video, and au-dio data, it becomes necessary to support efficient retrieval of high dimensional data. It has been shown that the tech-niques based on indexing do not perform well for high dimensional data [3, 5]. An alternative technique to indexingis to use I/O parallelism for efficient data retrieval. In this approach, the data space is partitioned into disjoint regions,and data is allocated to multiple disks. When users issue a query, data falling into disjoint partitions is retrieved in par-allel from multiple disks. This technique is referred to as disk declustering and has been very effective in relationaldatabases. good way of declustering goo