高平均效用co-location模式挖掘的一种有效算法  

An Effective Algorithm for Mining High Average-Utility Co-Location Patterns

作　　者：曾新 张晓玲 李晓伟 Zeng Xin;Zhang Xiaoling;Li Xiaowei(College of Mathematics and Computer,Dali University,Dali,Yunnan 671003,China)

机构地区：[1]大理大学数学与计算机学院,云南大理671003

出　　处：《大理大学学报》2022年第6期9-17,共9页Journal of Dali University

基　　金：云南省地方本科高校(部分)基础研究联合专项资金项目(2018FH001-062;2018FH001-063);大理大学数据安全与应用创新团队(ZKLX2020308)。

摘　　要：co-location模式是空间特征集合的一个子集,模式中不同特征的实例频繁出现在邻近区域内。纵观高效用co-location模式挖掘的相关研究报道,现存的高效用co-location模式挖掘方法没有考虑模式的长度对模式效用的影响。为了探索这一问题,提出一种从空间数据集中挖掘高平均效用co-location模式的算法(HAUCP),以便更好地评价co-location模式的真实效用。首先,基于空间数据集提出高平均效用co-location模式的完整定义;其次,构建了高平均效用co-location模式挖掘的基本算法,并探索了两种有效的剪枝策略以提升算法的运行效率;最后,在真实数据集和合成数据集上对算法的有效性和可扩展性进行了大量实验,实验结果表明HAUCP算法挖掘出的高效用co-location模式更加合理。Co-location pattern is a subset of spatial feature set,and some instances of different features in co-location pattern frequently appear in adjacent areas. Looking at relevant research reports on high utility co-location pattern mining,the existing high utility co-location patterns mining algorithms do not consider the impact of the length of pattern on the utility of pattern. To explore this issue,we propose an effective algorithm of mining high average-utility co-location patterns(HAUCP) from spatial dataset to provide a better evaluation of the real utility of co-location pattern. First,a comprehensive definition of high average-utility co-location patterns based on spatial dataset is proposed. Secondly,the basic algorithm of high average-utility co-location pattern mining is constructed. For improving the efficiency of the basic algorithm,two pruning strategies are developed to reduce the computing costs. Finally,extensive experiments on real dataset and synthetic dataset are carried out to prove the effectiveness of the proposed algorithm. Experimental results show that high-utility co-location patterns of HAUCP are more reasonable.

关 键 词：高平均效用 CO-LOCATION模式 模式长度 空间数据集 数据挖掘算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]