在本研究中，提出了一個整合式模糊關聯法則挖掘架構，並分為二大部分：第一部分為從交易資料庫中挖掘出模糊關聯法則，這是一項重要的資料挖掘議題，並且能挖掘出許多未知且重要的決策資訊供決策制定。而在許多模糊關聯法則文獻中，對於模糊關聯法則挖掘演算法之效率更是一項重要的研究議題。本研究提出改良式模糊關聯法則挖掘演算法來解決模糊挖掘過程中之效率問題。第二部分為從模糊大項目組與網路瀏覽資料萃取出二項資訊間之模糊關聯法則。 本研究提出以群聚為基礎之模糊關聯法則挖掘演算法，並以模糊群聚表概念來改善以往模糊關聯法則挖掘演算法之效率不佳問題。實驗結果證明，以群聚為基礎之模糊關聯法則挖掘演算法確實有效改善模糊大項目組之處理效率。本研究架構所挖掘出之整合式模糊關聯法則資訊將有助於決策者進行決策制定。 In this paper, two important issues of mining association rules are investigated. The first problem is the discovery of generalized fuzzy association rules in the transaction database. It's an important data-mining task, because more general and qualitative knowledge can be uncovered for decision making. However, few algorithms have been proposed in the literature, moreover, the efficiency of these algorithms needs to be improved to handle real-world large datasets. The second problem is to discover association rules from the web usage data and the large itemsets identified in the transaction database. This kind of rules will be useful for marketing decision. A cluster-based mining architecture is proposed to address the two problems. At first, an efficient fuzzy association rule miner, based on cluster-based fuzzy-sets tables, is presented to identify all the large fuzzy itemsets. This method requires less contrast to generate large itemsets. Next, a fuzzy rule discovery method is used to compute the confidence values for discovering the relationships between transaction database and browsing information database. An illustrated example is given to demonstrate the effectiveness of the proposed methods and experimental results show that CBFAR outperforms a known Apriori-based fuzzy association rules mining algorithm.
