|
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/10119/3904
|
| タイトル: | Pattern Recognition in Metabonomics Using Self Organizing Maps |
| 著者: | Stefan, W. Roeder
Ulrike, Rolle-Kampczyk
Olf, Herbarth |
| キーワード: | stress patterns
pattern recognition
artificial neural networks
self organizing maps
metabonomics |
| 発行日: | Nov-2005 |
| 出版者: | JAIST Press |
| 抄録: | The contiguity between external exposure and internal stress burden in humans is linked by metabolic pathways. To gather deeper knowledge about these links it is necessary to look behind the scenes and to find out which variables affect each other as well as which groups of individuals can be described. The approach shown in this paper is based on the algorithm of self organizing maps (SOM), which have shown their capabilities for clustering tasks previously. They enable us to subdivide cases into classes without prior knowledge. Furthermore prediction of selected outcome variables is possible after training of the algorithm. New visualization techniques atop of the SOM algorithm allow a multidimensional view on the data and their immanent structures as well as on the classes found. Finally we checked several parameter combinations of the SOM for their applicability and performance with our data. |
| 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, 2114, Kobe, Japan
Symposium 5, Session 1 : Data/Text Mining from Large Databases Data Mining |
| 言語: | ENG |
| URI: | http://hdl.handle.net/10119/3904 |
| 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 |
|---|
| 20191.pdf | | 515Kb | 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。
|
