ModifiedFAST: A New Optimal Feature Subset Selection Algorithm

Arpita Nagpal, D. Gaur
{"title":"ModifiedFAST: A New Optimal Feature Subset Selection Algorithm","authors":"Arpita Nagpal, D. Gaur","doi":"10.6109/jicce.2015.13.2.113","DOIUrl":null,"url":null,"abstract":"Feature subset selection is as a pre-processing step in learning algorithms. In this paper, we propose an efficient algorithm, ModifiedFAST, for feature subset selection. This algorithm is suitable for text datasets, 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 datasets. The effectiveness of our algorithm on th optimal threshold was statistically validated with other algorithms.","PeriodicalId":272551,"journal":{"name":"J. Inform. and Commun. Convergence Engineering","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"J. Inform. and Commun. Convergence Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.6109/jicce.2015.13.2.113","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

Feature subset selection is as a pre-processing step in learning algorithms. In this paper, we propose an efficient algorithm, ModifiedFAST, for feature subset selection. This algorithm is suitable for text datasets, 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 datasets. The effectiveness of our algorithm on th optimal threshold was statistically validated with other algorithms.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
ModifiedFAST:一种新的最优特征子集选择算法
特征子集选择是学习算法中的预处理步骤。本文提出了一种高效的特征子集选择算法ModifiedFAST。该算法适用于文本数据集,并利用信息增益的概念去除不相关和冗余的特征。找到了对称不确定性阈值的一个新的最优值,用于识别相关特征。以前的特征选择算法(如FAST、Relief和CFS)使用的阈值不是最优的。事实证明,阈值对特征的选择百分比和分类精度有很大影响。提出了一种结合准确率和特征选择数量的性能统一度量,并将其应用于该算法中。实验表明,在大多数数据集上,本文算法获得的特征选择百分比低于现有算法。我们的算法在最优阈值上的有效性与其他算法进行了统计验证。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Low Power Time Synchronization for Wireless Sensor Networks Using Density-Driven Scheduling Smart Home System Using Internet of Things Odoo Data Mining Module Using Market Basket Analysis Seafarers Walking on an Unstable Platform: Comparisons of Time and Frequency Domain Analyses for Gait Event Detection Navigator Lookout Activity Classification Using Wearable Accelerometers
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1