應用模糊關聯法則於遺漏值問題之研究

The Study of Fuzzy Association Rule into the Problem of Missing Value

徐嘉鈴(Chia-Ling Hsu)

指導教授 ： 龐金宗

元智大學/資訊學院/資訊管理學系/碩士(2008年)

摘要

隨著大型資料庫與資料倉儲的日益增加，在資料收集過程中仍有遺漏值的問題發生。資料相依之遺漏值問題，將嚴重影響到資料探勘的分析品質。所以如何妥善處理遺漏值問題，便成為一個重要的議題。已經有很多處理遺漏值的方法被提出，其中以關聯法則的概念最為常見。
在本篇論文中，以關聯法則為基礎，將模糊集合及階層類別之理論加入，再依據MVC技術做為填補遺漏值為方法。此研究結果顯示，支持度及信賴度門檻值對填補遺漏值之正確率有極大的影響；此外，填補之歸屬函數值的改變，對正確率之數據也跟著被影響。

關鍵字

關聯法則 ； 模糊集合 ； 遺漏值

並列摘要

Large-scale database and data warehousing increasing, in the data collection process have the missing value are large problems. The problem of the missing value, it will seriously affect the quality of the analysis of data mining. So how to properly handle the issue of the missing value, will become an important topic. There has been the method that a lot of processing the missing value being put forward, among them with the concept of the association rule most is familiar.
In this paper, the study take the association rule as the foundation, join the fuzzy set and taxonomy theories, and be used as to missing value completion as method according to the MVC technique. The study results show that minimum support and minimum confidence to the missing value completion of the correct value of a tremendous impact; In addition, to predict the fuzzy membership value of the change, the rate of correct data with the affected.

並列關鍵字

Association Rule ； Fuzzy Set ； Missing Value

參考文獻

[29] 王國河，「整合叢集與迴歸技術以處理大型資料庫遺失值問題之新方法」，碩士論文，國立成功大學資訊工程研究所，民國91年7月。[30] 李允中、王小璠、蘇木春，「模糊理論及其應用」，全華科技，民國92年1月。

[1] R. Agrawal, T. Imielinksi, and A. Swami, “Mining Association Rules between Sets of Items in Large Datatabase,” in The 1993 ACM SIGMOD Conf., Washington, D.C, USA, pp.207-216, 1993.

[3] W.H. Au and K.C.C. Chan,“An Effective Algorithm for Discovering Fuzzy Rules in Relational Databases,” Proc. of the 7th IEEE International Conf. on Fuzzy Systems, Vol.2, pp.1314-1319, 1998.

[8] J. Han, Y. Fu, “Discovery of Multiple-level Association Rules from Large Database,” in The Internat. Conf. on Very Large Databases, 1995.

[10] T.P. Hong, K.Y. Lin, Shyue-Liang Wang, “Fuzzy Data Mining for Interesting Generalized Association Rules,” Fuzzy Sets and Systems, Vol.138, No.2, pp.255-269, 2003.