|
JAIST Repository >
科学技術開発戦略センター 2003～2008 >
z2-70. JAIST PRESS 発行誌等 >
IFSR 2005 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/3873
|
| タイトル: | Methodology of Data Mining - Utilization of Ruduct and Indentification of Decision Rule - |
| 著者: | Niwano, Kaede
Kijima, Kyoichi |
| キーワード: | Rough set theory
Knowledge
Data mining
Decision making |
| 発行日: | Nov-2005 |
| 出版者: | JAIST Press |
| 抄録: | This paper proposes a new data mining methodology of reasoning for sorting new cases by using past cases or data based on rough set theory. Rough set theory is a mathematical framework to treat uncertainty. Our methodology consists of two parts. At first we focus on finding reduct for reducing large amount of data. When we try to discover a useful knowledge from a large amount of data when performing data mining, there exists trade-off between computation capacity and precision degree of the results. If we want to get more precise knowledge, we more need to cut down the data. Reduct is such a subset of the set of data attributes that provides the same quality of reasoning as the original set. Therefore by finding out an appropriate reduct, we can cut the set of attributes. Then we introduce a new way to identify more appropriate decision by employing concept of approximation and similarity relation S. Generally, in reasoning using rough set theory, we have two types of rules, namely, deterministic rule and non-deterministic rule. The former determines only one decision class while the latter does not. To treat the latter cases, we propose a new approach to making more precise decisions by measuring the possibility of being in a decision class. |
| 記述: | The original publication is available at JAIST Press http://www.jaist.ac.jp/library/jaist-press/index.html
IFSR 2005 : Proceedings of the First World Congress of the International Federation for Systems Research : The New Roles of Systems Sciences For a Knowledge-based Society : Nov. 14-17, 2083, Kobe, Japan
Symposium 2, Session 5 : Creation of Agent-Based Social Systems Sciences Decision Systems |
| 言語: | ENG |
| URI: | http://hdl.handle.net/10119/3873 |
| ISBN: | 4-903092-02-X |
| 出現コレクション: | IFSR 2005
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| 20059.pdf | | 2612Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
