杭州电子科技大学学报
杭州電子科技大學學報
항주전자과기대학학보
Journal of Hangzhou Dianzi University
2015年
5期
79-83
,共5页
关联规则%Apriori算法%遗传算法
關聯規則%Apriori算法%遺傳算法
관련규칙%Apriori산법%유전산법
association rules%Apriori algorithm%genetic algorithm
提出了一种基于遗传算法的关联规则改进算法,使用支持度、置信度、理解度和兴趣度等多度量标准,从确定性、有用性、简洁性和新奇性等方面综合度量关联规则,对关联规则Apriori算法进行优化,解决传统的关联规则挖掘算法产生大量规则集的问题. 实验结果表明,改进算法在发现有效规则的精准率方面具有一定优势,并且能够减少规则数量.
提齣瞭一種基于遺傳算法的關聯規則改進算法,使用支持度、置信度、理解度和興趣度等多度量標準,從確定性、有用性、簡潔性和新奇性等方麵綜閤度量關聯規則,對關聯規則Apriori算法進行優化,解決傳統的關聯規則挖掘算法產生大量規則集的問題. 實驗結果錶明,改進算法在髮現有效規則的精準率方麵具有一定優勢,併且能夠減少規則數量.
제출료일충기우유전산법적관련규칙개진산법,사용지지도、치신도、리해도화흥취도등다도량표준,종학정성、유용성、간길성화신기성등방면종합도량관련규칙,대관련규칙Apriori산법진행우화,해결전통적관련규칙알굴산법산생대량규칙집적문제. 실험결과표명,개진산법재발현유효규칙적정준솔방면구유일정우세,병차능구감소규칙수량.
This paper puts forward an improved algorithm of association rules based on genetic algorithm. Multiple metrics including support,confidence,comprehensibility and interestingness are used to optimize the Apriori algorithm based on the measure association rules consisting of certainty, usefulness, simplicity and novelty .The algorithm solved the problem that the traditional association rule mining algorithms always generate a lot of rules.The experiment results show that the improved algorithm has certain advantage in finding the precision of effective rules and can reduce the number of rules.
