基于多数据库的模糊元关联规则挖掘方法
|
摘要
分布式环境下,数据的特征是规模大、分布式存储。采用传统的数据挖掘技术分别对每个数据集进行分析一般都容易实现,但是要对全部数据进行整体决策时就比较困难。为此,提出一种新的挖掘方法,可以从多个数据集中挖掘规则。提出元关联规则生成模型,可以发现在每个独立的数据集中挖掘的规则之间的共同联系。设计清晰元关联规则和模糊元关联规则两种框架,对清晰元关联规则挖掘算法和模糊元关联规则挖掘算法做了对比。结果表明,模糊元关联规则挖掘方法在易用性和精确性方面比清晰方法要好。
In distributed environment,data is characterized by large scale and distributed storage. Generally,it is easy to achieve to use traditional data mining techniques to analyze each data set separately. However,it is more difficult to make an overall decision on all the data. Therefore,a new mining method is proposed in this paper,which can be used to mine rules from multiple data sets. A generation model is put forward based on meta association rule,finding out the relationship between the rules mined in each independent data set. Two kinds of frameworks,crisp meta association rules and fuzzy meta association rules,are designed. And comparison between their algorithms is also made. The results show that the mining method based on the fuzzy meta association rules is better than the crisp method in terms of ease of use and accuracy.
In distributed environment,data is characterized by large scale and distributed storage. Generally,it is easy to achieve to use traditional data mining techniques to analyze each data set separately. However,it is more difficult to make an overall decision on all the data. Therefore,a new mining method is proposed in this paper,which can be used to mine rules from multiple data sets. A generation model is put forward based on meta association rule,finding out the relationship between the rules mined in each independent data set. Two kinds of frameworks,crisp meta association rules and fuzzy meta association rules,are designed. And comparison between their algorithms is also made. The results show that the mining method based on the fuzzy meta association rules is better than the crisp method in terms of ease of use and accuracy.
引文
[1]Cheung D W,Ng V T,Fu A W,et al.Efficient Mining of Association Rules in Distributed Databases[J].Knowledge&Data Engineering IEEE Transactions on,1996,8(6):911-922.
[2]Delado M,Ruiz M D,Sánchez D.New Approaches for Discovering Exception and Anomalous Rules[J].International Journal of Uncertainty,Fuzziness and Knowledge-Based Systems,2011,19(2):361-399.
[3]李其轩,路艳丽.直觉模糊信息系统的规则提取方法[J].计算机应用与软件,2015,32(1):251-254.
[4]Saxena N,Arora R,Sikarwar R,et al.An Efficient Approach of Association Rule Mining on Distributed Database Algorithm[J].International Journal of Computer Applications,2014,81(3):12-16.
[5]翟悦,秦放.基于概念格的无冗余关联规则提取算法[J].计算机应用与软件,2015,32(4):46-49,66.
[6]刘玉龙,吴卫荣,王燕.多维信息融合方法及技术研究[J].计算机应用与软件,2017,34(6):101-105.
[7]周越.多域分布式网络中告警模糊关联规则挖掘的研究[D].成都:电子科技大学,2016.
[8]丁三军,薛宇,王朝霞,等.基于模糊数据挖掘的虚拟环境主机故障预测[J].计算机工程,2015,41(11):202-206.
[9]丁建立,王曼.基于关联规则挖掘的航班协同保障数据知识发现研究[J].计算机应用与软件,2016,33(11):21-23,61.
[10]段功豪.基于多结构数据挖掘的滑坡灾害预测模型研究[D].武汉:中国地质大学,2016.
[2]Delado M,Ruiz M D,Sánchez D.New Approaches for Discovering Exception and Anomalous Rules[J].International Journal of Uncertainty,Fuzziness and Knowledge-Based Systems,2011,19(2):361-399.
[3]李其轩,路艳丽.直觉模糊信息系统的规则提取方法[J].计算机应用与软件,2015,32(1):251-254.
[4]Saxena N,Arora R,Sikarwar R,et al.An Efficient Approach of Association Rule Mining on Distributed Database Algorithm[J].International Journal of Computer Applications,2014,81(3):12-16.
[5]翟悦,秦放.基于概念格的无冗余关联规则提取算法[J].计算机应用与软件,2015,32(4):46-49,66.
[6]刘玉龙,吴卫荣,王燕.多维信息融合方法及技术研究[J].计算机应用与软件,2017,34(6):101-105.
[7]周越.多域分布式网络中告警模糊关联规则挖掘的研究[D].成都:电子科技大学,2016.
[8]丁三军,薛宇,王朝霞,等.基于模糊数据挖掘的虚拟环境主机故障预测[J].计算机工程,2015,41(11):202-206.
[9]丁建立,王曼.基于关联规则挖掘的航班协同保障数据知识发现研究[J].计算机应用与软件,2016,33(11):21-23,61.
[10]段功豪.基于多结构数据挖掘的滑坡灾害预测模型研究[D].武汉:中国地质大学,2016.