JICCE (한국정보통신학회)
Current Result Document :
| 한글제목(Korean Title) |
Modified FAST: A New Optimal Feature Subset Selection Algorithm |
| 영문제목(English Title) |
Modified FAST: A New Optimal Feature Subset Selection Algorithm |
| 저자(Author) |
Arpita Nagpal
Deepti Gaur
|
| 원문수록처(Citation) |
VOL 13 NO. 02 PP. 0113 ~ 0122 (2015. 06) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Feature subset selection is as a pre-processing step in learning algorithms. In this paper, we propose an efficient algorithm, Modified FAST, for feature subset selection. This algorithm is suitable for text data sets, and uses the concept of information gain to remove irrelevant and redundant features. A new optimal value of the threshold for symmetric uncertainty, used to identify relevant features, is found. The thresholds used by previous feature selection algorithms such as FAST, Relief, and CFS were not optimal. It has been proven that the threshold value greatly affects the percentage of selected features and the classification accuracy. A new performance unified metric that combines accuracy and the number of features selected has been proposed and applied in the proposed algorithm. It was experimentally shown that the percentage of selected features obtained by the proposed algorithm was lower than that obtained using existing algorithms in most of the data sets. The effectiveness of our algorithm on the optimal threshold was statistically validated with other algorithms.
|
| 키워드(Keyword) |
Entropy
Feature selection
Filter model
Graph-based clustering
Mutual information
|
| 파일첨부 |
PDF 다운로드
|
