查詢結果分析
來源資料
頁籤選單縮合
題 名 | 在動態資料庫中挖掘關聯法則之快速演算法=A Fast Algorithm for mining Association Rules in Dynamic Databases |
---|---|
作 者 | 蘇建源; 張晉赫; 邱宏彬; | 書刊名 | 資訊管理研究. 南華大學 |
卷 期 | 3 2003.07[民92.07] |
頁 次 | 頁17-29 |
分類號 | 312.13 |
關鍵詞 | 資料探勘; 關聯法則; 線上探勘; 漸進式探勘; 敏感性分析; Data mining; Association rules; Dynamic databases; Online mining; Incremental mining; Sensitive information; |
語 文 | 中文(Chinese) |
中文摘要 | 資料探勘(data mining)為近年來廣泛地應用在客戶資源管理、行銷、醫學及其他許多領域中的一門學科。如何有效率地從大量的資料中搜尋出隱含的資訊與有用的規則,一直是關聯法則探勘研究領域中十分重視的課題。在關聯法則的挖掘上,最具代表性的方法是Apriori演算法,其牽涉到多次資料庫掃描以取得大項目組,因此,對於現實生活中的動態新增資料庫而言,Apriori演算法面臨了三個主要的問題,其一為該演算法相當耗時,不適合線上探勘;二為無法有效解決動態新增資料庫中漸進式探勘的問題,第三為相對於整體資料庫,較新時間點的敏感性資料無法被有效的擷取。 本文提出一簡單的關聯法則之多層更新挖掘法(□ultilayer □pdate □iner, MUM),此方法不需要重複掃描原始資料庫,因此,可支援線上探勘及漸進式探勘的需求。利用MUM多層同步處理與更新的特性,搭配敏感度指數的定義,MUM可以被用來挖掘對決策者有用的即時性敏感資訊。同時,本文藉由許多實驗及相關的分析以檢驗MUM的執行效能並探討其優缺點與可行性。 |
英文摘要 | Data mining is the exploration and analysis of large quantities of data in order to discover meaningful patterns and rules. It is an important discipline, which has widely applied in fields ranging from customer relationship management to marketing, and medicine. The discovery of association rules is an important task in data mining. The Apriori algorithm is the most popularly and widely used technique for mining association rules. However, the Apriori algorithm must scan the database many times to discover the large itemsets so that it has three main disadvantages: (1) it is time-consuming; (2) it is not suitable for mining of incrementally growing databases due to the need of rescanning the original databases; and (3)as databases grow, the sensitive information in the new transactions can be not mined effectively. In this paper, we propose the Multilayer Update Miner (MUM) algorithm, which does not need to rescan the original database, to mine the association rules for the incrementally growing databases. Based on two our designed sensitivity indexes, the MUM can mine sensitive information from the newly inserted transaction. Many experiments and related analyses are conducted to validate our proposed approaches. |
本系統中英文摘要資訊取自各篇刊載內容。