一种用于多属性范围查询的聚簇方法  

Clustering Method for Multiple Attributes Range Query

作　　者：马慧[1] 吴凌坤 

机构地区：[1]电子科技大学中山学院计算机工程系,广东中山528402 [2]腾讯计算机系统有限公司,广东深圳518057

出　　处：《计算机工程》2011年第19期41-43,46,共4页Computer Engineering

基　　金：电子科技大学中山学院科研启动基金资助项目(409YKQ04)

摘　　要：为提高多属性区域的查询效率,在物理层重新安排记录排列顺序,以减少查询访问磁盘块数。在此基础上,构造数学模型,将待查询记录按属性值映射至多维坐标空间中的点,以求解一个线性序,使空间中相距越远的点在线性序中也相距越远,并提出一种适用于多属性范围查询的聚簇方法。实验结果表明,与光谱算法及传统聚簇算法相比,该方法查询性能更优。To improve the query performance of range queries on multiple attributes in a static data file,a possible solution is to better reorganize the data in the data file so that it can reduce the I/O visiting times.A mathematical model is constructed for this problem.A record can be mapped to a point in a multi-dimensional space according to its queried attributes values.The aim is to find a linear order of these points so that the closer the points are in the multi-dimensional space the closer they are in the linear order.A heuristic method called FPF is proposed.Experimental results show the method performs better than spectrum algorithm and the traditional clustering algorithm.

关 键 词：多维聚簇 数据重组 区域查询 聚簇索引 查询效率 

分 类 号：N945[自然科学总论—系统科学]