Stability comparison of feature selection algorithms using normalized rank transformation
電気・情報関連学会中国支部連合大会講演論文集 Volume 58
Page 327-328
published_at 2007-10
アクセス数 : 787 件
ダウンロード数 : 142 件
今月のアクセス数 : 0 件
今月のダウンロード数 : 0 件
この文献の参照には次のURLをご利用ください : https://ir.lib.hiroshima-u.ac.jp/00022847
| File | |
| Title ( eng ) |
Stability comparison of feature selection algorithms using normalized rank transformation
|
| Creator |
Djatna Taufik
|
| Source Title |
電気・情報関連学会中国支部連合大会講演論文集
|
| Volume | 58 |
| Start Page | 327 |
| End Page | 328 |
| Abstract |
There are needs for evaluating rank order-based similarity between different classifiers in feature selection. Feature selection maps from data set to give further understanding about the importance of ranking in decision making within feature selection algorithms. The results are ordered rankings of training and testing data. In order to compare stability within each classifier, we deploy normalized rank transformation approach to get the degree of similarity between training and testing data set. The accuracy of the selected features is then evaluated using various classifiers.
|
| Keywords |
feature selection
key performance indicators
|
| NDC |
Electrical engineering [ 540 ]
|
| Language |
eng
|
| Resource Type | conference paper |
| Publisher |
電気・情報関連学会中国支部
|
| Date of Issued | 2007-10 |
| Rights |
Copyright (c) 2007 by Authors
|
| Publish Type | Version of Record |
| Access Rights | open access |
| Source Identifier |
[NCID] AA11138730
|
