Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets
Multi-label learning is often applied to handle complex decision tasks, and feature selection is its essential part. The relation of labels is always ignored or not enough to consider for both multi-label learning and its feature selection. To deal with the problem, F-neighborhood rough sets are emp...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9007716/ |
id |
doaj-6e4b1ba376334f609a2fb47641eaa7e2 |
---|---|
record_format |
Article |
spelling |
doaj-6e4b1ba376334f609a2fb47641eaa7e22021-03-30T02:39:45ZengIEEEIEEE Access2169-35362020-01-018396783968810.1109/ACCESS.2020.29761629007716Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough SetsZhixuan Deng0https://orcid.org/0000-0002-3374-3666Zhonglong Zheng1https://orcid.org/0000-0002-5271-9215Dayong Deng2https://orcid.org/0000-0002-4558-5861Tianxiang Wang3https://orcid.org/0000-0003-2220-5501Yiran He4https://orcid.org/0000-0002-9445-3005Dawei Zhang5https://orcid.org/0000-0002-7593-1593College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua, ChinaCollege of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua, ChinaCollege of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua, ChinaCollege of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua, ChinaCollege of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua, ChinaCollege of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua, ChinaMulti-label learning is often applied to handle complex decision tasks, and feature selection is its essential part. The relation of labels is always ignored or not enough to consider for both multi-label learning and its feature selection. To deal with the problem, F-neighborhood rough sets are employed. Different from other methods, the original approximate space is not changed, but the relation of labels is sufficient to consider. To be specific, a multi-label decision system is discomposed into a family of single-label decision tables with the label set(first-order strategy) at first. Secondly, calculate attribute significance in the family of single-label decision tables. Third, construct an attribute significance matrix and improved attribute significance matrices to evaluate the quality of the features, then a parallel reduct is obtained with information fusion. These processes construct F-neighborhood parallel reduction algorithm for a multi-label decision system(FNPRMS). Compared with the state-of-the-arts, experimental results show that FNPRMS is effective and efficient on 9 publicly available data sets.https://ieeexplore.ieee.org/document/9007716/Rough setsfeature selectionmulti-label learningF-neighborhood rough setsattribute significance matrix |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhixuan Deng Zhonglong Zheng Dayong Deng Tianxiang Wang Yiran He Dawei Zhang |
spellingShingle |
Zhixuan Deng Zhonglong Zheng Dayong Deng Tianxiang Wang Yiran He Dawei Zhang Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets IEEE Access Rough sets feature selection multi-label learning F-neighborhood rough sets attribute significance matrix |
author_facet |
Zhixuan Deng Zhonglong Zheng Dayong Deng Tianxiang Wang Yiran He Dawei Zhang |
author_sort |
Zhixuan Deng |
title |
Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets |
title_short |
Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets |
title_full |
Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets |
title_fullStr |
Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets |
title_full_unstemmed |
Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets |
title_sort |
feature selection for multi-label learning based on f-neighborhood rough sets |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Multi-label learning is often applied to handle complex decision tasks, and feature selection is its essential part. The relation of labels is always ignored or not enough to consider for both multi-label learning and its feature selection. To deal with the problem, F-neighborhood rough sets are employed. Different from other methods, the original approximate space is not changed, but the relation of labels is sufficient to consider. To be specific, a multi-label decision system is discomposed into a family of single-label decision tables with the label set(first-order strategy) at first. Secondly, calculate attribute significance in the family of single-label decision tables. Third, construct an attribute significance matrix and improved attribute significance matrices to evaluate the quality of the features, then a parallel reduct is obtained with information fusion. These processes construct F-neighborhood parallel reduction algorithm for a multi-label decision system(FNPRMS). Compared with the state-of-the-arts, experimental results show that FNPRMS is effective and efficient on 9 publicly available data sets. |
topic |
Rough sets feature selection multi-label learning F-neighborhood rough sets attribute significance matrix |
url |
https://ieeexplore.ieee.org/document/9007716/ |
work_keys_str_mv |
AT zhixuandeng featureselectionformultilabellearningbasedonfneighborhoodroughsets AT zhonglongzheng featureselectionformultilabellearningbasedonfneighborhoodroughsets AT dayongdeng featureselectionformultilabellearningbasedonfneighborhoodroughsets AT tianxiangwang featureselectionformultilabellearningbasedonfneighborhoodroughsets AT yiranhe featureselectionformultilabellearningbasedonfneighborhoodroughsets AT daweizhang featureselectionformultilabellearningbasedonfneighborhoodroughsets |
_version_ |
1724184740830904320 |