CAJ | 학술논문

提出一种基于强关联规则的可行动分簇算法（AC－SAR）。AC－SAR算法为每一个对象寻找关联性最强的对象，并通过反对称原则和可连接原则删除和合并相应规则，最终挖掘出涉及事务数据库中所有对象的多个连通子图（簇）。与传统算法相比，新算法无需设置阈值，没有冗余知识，算法的中间挖掘结果及最终生成的簇，能有效地解决诸多领域的实际问题。大量试验结果表明，该新算法具有较高的效率、准确性以及较强的可行动性。
제출일충기우강관련규칙적가행동분족산법（AC－SAR）。AC－SAR산법위매일개대상심조관련성최강적대상，병통과반대칭원칙화가련접원칙산제화합병상응규칙，최종알굴출섭급사무수거고중소유대상적다개련통자도（족）。여전통산법상비，신산법무수설치역치，몰유용여지식，산법적중간알굴결과급최종생성적족，능유효지해결제다영역적실제문제。대량시험결과표명，해신산법구유교고적효솔、준학성이급교강적가행동성。
An actionable clustering algorithm based on strong association rules (AC-SAR)was proposed.The AC-SAR algorithm looked for strong associated objects for each object,and then some relevant rules were deleted and merged by the anti-symmetric principle and the connectivity principle.The connected sub-graphs (clusters)related to all objects in transaction database were discovered finally.Compared with the traditional algorithms,the AC-SAR algo-rithm did not need to set the thresholds by user,and there were not redundant rules in the results.Moreover,the inter-mediate mined results and the final generated clusters could solve the problems in many fields effectively.A large number of experiments showed that the AC-SAR algorithm had higher efficiency,higher accuracy,and stronger action.