| 90 | 2 | 91 |
| 下载次数 | 被引频次 | 阅读次数 |
在相关矩阵理论的研究基础上,将网格与Web服务技术融合,以分布式问题求解环境和开源数据挖掘类库weka为底层支撑,构建了网格环境下面向服务的分布式数据挖掘体系,提出一种基于矩阵的分布式关联规则算法.该算法不需要进行复杂的寻找频繁项集的过程,直接通过关联矩阵就可以判断出,给出了算法的理论证明,并通过实例验证了算法的正确性、有效性和体系结构的可行性,对于解决分布式关联规则挖掘问题有了一个新的突破.
Abstract：On the basis of in-depth research of the matrix theory and the association of grid and Web service technology,the paper presents a service-oriented distributed data mining system under grid environment,which is supported by distributed solution environment and Weka library.A matrix-based association rule algorithm is given,which can be judged directly by association matrix rather than by complicated seeking of frequent item sets.The algorithm is theoretically and practically proved to be correct,valid and feasible,which indicates a breakthrough in dealing with the distributed mining problem of association rule.
[1]Foster I,Kesselman C,Nick J,et al.The physiology of thegrid[C]//Berman F,Fox G,Hey A,eds.Grid Computing:Making the Global Infrastructure a Reality,Wiley,2003:217-249.
[2]Talia D,Trunfio P,Verta O.Weka4WS:a WSRF-enabledweka toolkit for distributed data mining on Grids[C]//9th European Conference on Principles and Practice of Knowl-edge Discovery in Databases,LNCS 3721,2005:309-320.
[3]The Weka4WS user guide[EB/OL].[2010-01-09].http://grid.deis.unical.it/weka4ws.
[4]Cannataro M,Congiusta A,Mastroianni C,et al.Grid-Based Data Mining and Knowledge Discovery[C]//Zhong N,Liu J.Intelligent Technolo gies for Information Analysis.Berlin:Springer-Verlag,2004:19-45.
[5]Liu Y A,Yang B.An improved apriori algorithm for miningassociation rules[J].Journal of Computer Applications,2007,20(4):52-55.
[6]程云鹏.矩阵论[M].西安:西北工业大学出版社,2003.
[7]Zhang Z.A fast algorithm for mining association rules basedon boolean matrix.International Computer Science Institute[C]//Proceedings of the 20th International Conference onVLDB,2005:1-3.
[8]Han J W,Micheline K.Data mining concepts and tech-niques[M].Beijing:China Machine Press,2007:146-183.
[9]Wang B,Li S Y.Simulation research on of fuzzy immune nonlinear PID control[J].Journal of Harbin University of Commerce,2006,22(6):72-75.
基本信息:
中图分类号:TP311.13
引用信息:
[1]郑世明,苗壮,宋自林,等.网格环境下基于WEKA4WS的分布式矩阵关联规则挖掘算法[J].南通大学学报(自然科学版),2010,9(03):76-82.
基金信息:
国家高技术研究发展计划(863计划)项目(2007AA01Z126);; 总装武器装备预研基金(9140A0605409JB8102);; 解放军理工大学预研基金(2009JSJ11)