This paper proposes a centroid-slice-based uncertain high-dimensional indexing algorithm, called CU-Tree. In the CU-Tree,all ( n)data objects are first grouped into some clusters by a k-Means clustering algorithm. Then each object' s corresponding uncertain sphere is "sliced" in terms of the centroid-distance. Finally a unified key of each data object is canputed by adopting composite encoding scheme, which are inserted by a B + -tree. Thus, given a query object, its probabilistic range search in high-dimensional spaces is transformed into the search in the single dimemional space with the aid of the CU-Tree. Extensive performance studies are conducted to evaluate the effectiveness and efficiency of the proposed scheme.%提出一种基于质心片的(CU-Tree)不确定高维索引结构.对于高维空间中的不确定数据对象,首先通过k平均聚类算法将其聚成若干类,然后分别计算每个不确定超球进行质心"切片",并对其进行复合编码得到对应的统一索引键值,并且用B+树建立索引.这样,高维空间的概率查询就转变成对一维空间的启发式的范围查询及求精运算.实验证明该方法能更有效地缩小搜索空间,减少积分计算的代价.实验都表明,CU-Tree索引在查询效率方面要明显优于其它的索引方法,尤其适合海量高维不确定数据的查询.
展开▼
