基于最大间隙空间映射的高维数据索引技术  

A High Dimensional Data Indexing Technique Based on Max Gap Space Mapping

作　　者：王国仁[1] 黄健美[1] 王斌[1] 韩东红[1] 乔百友[1] 于戈[1] 

机构地区：[1]东北大学信息科学与工程学院

出　　处：《软件学报》2007年第6期1419-1428,共10页Journal of Software

基　　金：国家自然科学基金Nos.60273079;60473074;60573089;国家重点基础研究发展计划(973)No.2006CB303103;国家教育部博士点基金No.DP0345710~~

摘　　要：在基于高维索引技术的相似性查询处理中,通常通过过滤那些不包含任何查询结果的非活动子空间来不断缩减搜索空间.但是在活动子空间中,有些可能根本就不包含任何查询结果,这样的活动子空间被称为假活动子空间.显然,查询处理性能会随着假活动子空间访问次数的增加而下降.这一问题在高维数据情况下将会变得更加严重,实验显示出随着维数的增加,假活动子空间的访问次数也会增加.为了解决这一问题,提出了一种空间映射方法来减少这种不必要的访问.对于一个给定的查询,可以通过在映射空间内进一步精炼该查询来过滤假活动子空间.为了提高映射空间内查询精炼的处理效率,提出了一个最大间隙空间映射策略——MaxGapMapping.基于这种映射方法,设计并实现了一种新的索引结构——MS-tree,给出了索引的构建算法和范围查询处理算法.最后对MS-tree及其他索引结构的性能进行了详细的比较和分析.In the similarity query processing based on high dimensional indexing, the searching space is usually narrowed down by pruning the inactive subspaces which do not contain any query results. However, among the active subspaces, some of them do not contain any query results at all, those are called false active subspaces. It is obvious that the performance of query processing degrades in the presence of false active subspaces, The problem becomes seriously in the case of high dimensional data. The experiment in this paper shows that the number of accesses to false active subspaces increases as the dimensionality increases. In order to overcome the problem, a space mapping approach is proposed to reduce such unnecessary accesses. For a given query, it can be refined by filtering within its mapped space. A maximal gap space mapping strategy, MaxGapMapping, is proposed to improve the efficiency of the refinement processing. An index structure——MS-tree, the algorithms of construction, and query processing based on this refining method are designed and implemented. Finally, the performance of MS-tree is systemically compared with that of other competitors in terms of range queries based on a real data set.

关 键 词：高维索引 查询精炼 假活动子空间 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]