一种基于情节矩阵和频繁情节树的情节挖掘方法-控制与决策.PDF

第28 卷 第3 期 控 制 与 决 策 2013 年 3 月 Vol. 28 No. 3 Control and Decision Mar. 2013 文章编号: 1001-0920 (2013) 03-0339-06 一种基于情节矩阵和频繁情节树的情节挖掘方法 林树宽, 乔建忠 (东北大学信息科学与工程学院，沈阳110819) 摘 要: 针对现有的最小发生的频繁情节挖掘中存在的问题, 提出一种发现情节的不同最小发生并对其进行计数的 方法. 在此基础上, 提出基于情节矩阵和频繁情节树的最小发生频繁情节挖掘方法, 基于直接扩展思想, 只需扫描数 据一次, 不需生成候选情节, 提高了挖掘的时空效率. 提出了基于相同结点链和哈希链的优化方法, 通过省略相同结 点的扩展过程, 进一步提高了挖掘性能. 最后, 在不同类型的真实数据集上进行实验, 实验结果验证了所提出的频繁 情节挖掘方法的优势以及优化方法的有效性和高效性. 关键词: 频繁情节；情节矩阵；频繁情节树；相同结点链 中图分类号: TP391 文献标志码: A An episode mining method based on episode matrix and frequent episode tree LIN Shu-kuan, QIAO Jian-zhong (College of Information Science and Engineering，Northeastern University ，Shenyang 110819，China ． Correspondent ：LIN Shu-kuan ，E-mail ：linshukuan@) Abstract: For the problems existing in current frequent episode mining with minimal occurrences, the paper proposes a method of discovering distinct minimal occurrences and counting them. On this basis, an episode matrix and frequent episode tree based mining method is proposed, which only scans event sequences once based on the idea of direct extension without candidate generation and enhances space-time efficiency. Moreover, its optimization is presented based on same node chains and hash chains, which improves the mining performance further by omitting the extension process of same nodes. A series of experiments on different types of real data sets show the advantage of the proposed method, and validate the effectiveness and efficiency of the optimization method. Key words: frequent episode ；episode matrix ；frequent episode tree ；same node chain