摘要
为解决大型磁盘数据集上对象间语义贴近度的计算 ,在已有嵌套循环算法RNL的基础上提出了 2个改进算法 :基于三阵列的嵌套循环算法TRNL和基于四阵列的嵌套循环算法FRNL .形式讨论及实验证明 ,TRNL算法和FRNL算法比RNL算法效率高 ,其中FRNL算法效率最高 .最后分析了划分内存阵列的数目与时间效益的关系 .
In order to solve calculating of semantic proximity between objects in large Datasets,two algorithms on the basis of the Nested-loop algorithm(RNL) are presented.One of them is nested-loop algorithm based on three arrays(TRNL),and the other one is nested-loop algorithm based on four arrays(FRNL).By discussing formally and experiment,executing times of the FRNL and the FRNL are more efficient.Of all,the efficiency of the FRNL is highest.Finally,we analyze the relations between time cost and arrays which have been divided.
出处
《云南大学学报（自然科学版）》
CAS
CSCD
2001年第5期331-335,340,共6页
Journal of Yunnan University(Natural Sciences Edition)
基金
云南省自然科学基金资助项目 ( 1999F0 0 15M )
关键词
数据挖掘
大型磁盘数据集
三阵列嵌套循环算法TRNL
四阵列嵌套循环算法FRNL
data mining
the large dataset
nested-loop algorithm(RNL)
nested-loop algorithm based on three arrays(TRNL)
nested-loop algorithm based on four arrays(FRNL)
