English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62797/95867 (66%)
Visitors : 3732561      Online Users : 354
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/54540


    Title: 多階層遺傳模糊探勘技術之研究
    Other Titles: Multi-Level Genetic-Fuzzy Data-Mining Techniques
    Authors: 陳俊豪
    Contributors: 淡江大學資訊工程學系
    Keywords: 資料探勘;遺傳演算法;多階層模糊關聯規則;隸屬函數;遺傳模糊探勘;Data mining;Genetic algorithm;Multi-level fuzzy association rules;Membership functions;Genetic-fuzzy mining
    Date: 2010
    Issue Date: 2011-07-06 11:51:36 (UTC+8)
    Abstract: 遺傳模糊探勘的議題主要是結合遺傳演算法與模糊理論從交易資料中同時探勘隸屬函數與模糊關聯規則的技術。故架構上分為兩個步驟,分別為隸屬函數探勘與模糊關聯規則探勘步驟。在第一步驟首先使用演化式計算找出適合於探勘問題的隸屬函數,之後再使用最後的最佳隸屬函數去探勘模糊關聯規則。可惜的是,截至目前為止,上述遺傳模糊資料探勘研究成果僅針對一般的數值型交易資料,對於具概念階層的數值型交易資料庫,仍未見有研究進行探討。 本計畫的主要目的在發展多階層遺傳模糊探勘方法,同時探勘商品最小支持度、隸屬函數與多階層模糊關聯規則。根據遺傳模糊探勘技術應注重的因素,包括:隸屬函數型態、規則有效性、最小支持度合適性與語意項目個數合適性,本計畫提出一個兩年的研究,針對下列的研究議題進行探討: (1) 在單一最小支持度模糊關聯規則探勘(SMSFM)問題下,針對不同的多階層模糊關聯規則模式,包括:逐層探勘模式(Level-by-level mode)與跨層探勘模式(Generalized mode),設計發展單一最小支持度之多階層遺傳模糊探勘技術。 (2) 在多重最小支持度模糊關聯規則探勘(MMSFM)問題下,考量不同的最小支持度限制(Minimum Support Constraints)策略與多階層模糊關聯規則模式,設計發展多重最小支持度之多階層遺傳模糊探勘技術。
    Genetic-fuzzy data mining techniques are used to discover membership functions and useful fuzzy association rules by combining the genetic algorithms and the fuzzy concepts. The framework consists of two phases, including mining membership function and mining fuzzy association phases. In the first phase, the genetic algorithm is used to derive appropriate membership functions for items. In second phase, the final membership functions are then used to mine fuzzy association rules. Unfortunately, all of the literature on genetic-fuzzy data mining, to our best knowledge, is confined to the quantitative transaction database environment; no research work has been conducted on genetic-fuzzy data mining over quantitative transaction database with taxonomy. The aim of this project is to develop the multi-level genetic-fuzzy data mining methods for mining minimum supports, membership functions and multi-level fuzzy association rules from quantitative transaction database with taxonomy. According to the general issues in designing genetic-fuzzy data mining algorithms, such as types of membership functions, the effectiveness of the rules, suitability of minimum supports and appropriate number of linguistic terms, in this context, we will propose a two-year project, focusing on the following main issues: (1) For single-minimum-support fuzzy-mining problem, we attempt to design multi-level genetic-fuzzy data mining techniques for items with a single minimum support based on two types of multi-level rule mining modes, including level-by-level and generalized modes. (2) For multiple-minimum-support fuzzy-mining problem, we attempt to design multi-level genetic-fuzzy data mining techniques for items with multiple minimum supports based on two types of multi-level rule mining modes, and by considering two types of minimum support constraints.
    Appears in Collections:[資訊工程學系暨研究所] 研究報告

    Files in This Item:

    There are no files associated with this item.

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback