Noise free Attribute oriented induction

Noise free Attribute oriented induction

洪家育(Jia-Yu Hong)

指導教授 ： 陳彥良

國立中央大學/管理學院/資訊管理學系/碩士(2015年)

摘要

屬性導向歸納方法(簡稱AOI方法)主要是被發展來挖掘關連式資料庫的一般化知識，這種方法的輸入包括一個關連式資料表和一組與資料表屬性相關的概念階層 (或稱為概念樹) 。它是一種以歸納為基礎的資料分析技術，將關聯式表格 (Relational Dataset) 資料集合中的每一個屬性，檢查其資料分佈，以決定應歸納到哪個相關的抽象層級。但是因為屬性導向歸納方法很容易受到干擾值 (noise) 的影響，使得歸納出的結果的一般化特徵過於粗略。對於此問題，本論文提出一個以AOI方法為基礎的Noise-free AOI方法，此演算法能將資料中的干擾值(Noise data)過濾掉，讓屬性導向歸納法找出的一般化特徵更加明確。

關鍵字

屬性導向歸納法 ； 概念階層 ； 關連式資料 ； 資料挖礦 ； 干擾值

並列摘要

Attribute oriented induction ( AOI for short) was developed mainly to mine generalized knowledge of relational dataset, this approach include a relational dataset and a set of attributes associated with concept (or concept tree). It is a kind of generalize -based data analysis techniques, and the relational Dataset in each of the properties, checking its data distribution to determine which should be grouped into relevant levels of abstraction. But attribute oriented induction method is very susceptible to interference noise effects, so the results of the generalization features too sketchy. For this problem, this paper proposes a method based AOI, is Noise-free AOI methods. This algorithm can filter out the noise data, so that Noise free AOI can generalize more clearly.

並列關鍵字

attribute oriented induction ； concept tree ； relation dataset ； data mining ； noise data

參考文獻

[15] Liu, Q. H., Tang, C. J., Li, C., Liu, Q. W., Zeng, T., & Jiang, Y. G. (2007). Traditional Chinese Medicine prescription mining based on attribute-oriented relevancy induction. Jisuanji Yingyong/ Journal of Computer Applications,27(2), 449-452.

[1] Cai, Y. (1989). Attribute-oriented induction in relational databases (Doctoral dissertation, Simon Fraser University).

[2] Carter, C. L., & Hamilton, H. J. (1998). Efficient attribute-oriented generalization for knowledge discovery from large databases. Knowledge and Data Engineering, IEEE Transactions on, 10(2), 193-208.

[5] Hsu, C. C. (2004). Extending attribute-oriented induction algorithm for major values and numeric values. Expert Systems with Applications, 27(2), 187-202.

[6] Yager, R. R., & Petry, F. E. (2006). A multicriteria approach to data summarization using concept ontologies. Fuzzy Systems, IEEE Transactions on, 14(6), 767-780.