Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature Selection
Feature selection is an important preprocessing step in pattern classification and machine learning, and mutual information is widely used to measure relevance between features and decision. However, it is difficult to directly calculate relevance between continuous or fuzzy features using mutual in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2011-08-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://www.atlantis-press.com/article/2353.pdf |
| _version_ | 1818543408133701632 |
|---|---|
| author | Daren Yu Shuang An Qinghua Hu |
| author_facet | Daren Yu Shuang An Qinghua Hu |
| author_sort | Daren Yu |
| collection | DOAJ |
| description | Feature selection is an important preprocessing step in pattern classification and machine learning, and mutual information is widely used to measure relevance between features and decision. However, it is difficult to directly calculate relevance between continuous or fuzzy features using mutual information. In this paper we introduce the fuzzy information entropy and fuzzy mutual information for computing relevance between numerical or fuzzy features and decision. The relationship between fuzzy information entropy and differential entropy is also discussed. Moreover, we combine fuzzy mutual information with "min-Redundancy-Max-Relevance", "Max-Dependency" and min-Redundancy-Max-Dependency" algorithms. The performance and stability of the proposed algorithms are tested on benchmark data sets. Experimental results show the proposed algorithms are effective and stable. |
| first_indexed | 2024-12-11T22:34:59Z |
| format | Article |
| id | doaj.art-c2ae99e8aef54eceb43c3b91787d6c59 |
| institution | Directory Open Access Journal |
| issn | 1875-6883 |
| language | English |
| last_indexed | 2024-12-11T22:34:59Z |
| publishDate | 2011-08-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj.art-c2ae99e8aef54eceb43c3b91787d6c592022-12-22T00:48:01ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832011-08-014410.2991/ijcis.2011.4.4.18Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature SelectionDaren YuShuang AnQinghua HuFeature selection is an important preprocessing step in pattern classification and machine learning, and mutual information is widely used to measure relevance between features and decision. However, it is difficult to directly calculate relevance between continuous or fuzzy features using mutual information. In this paper we introduce the fuzzy information entropy and fuzzy mutual information for computing relevance between numerical or fuzzy features and decision. The relationship between fuzzy information entropy and differential entropy is also discussed. Moreover, we combine fuzzy mutual information with "min-Redundancy-Max-Relevance", "Max-Dependency" and min-Redundancy-Max-Dependency" algorithms. The performance and stability of the proposed algorithms are tested on benchmark data sets. Experimental results show the proposed algorithms are effective and stable.https://www.atlantis-press.com/article/2353.pdfFeature selection; fuzzy mutual information; redundancy; relevance; stability |
| spellingShingle | Daren Yu Shuang An Qinghua Hu Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature Selection International Journal of Computational Intelligence Systems Feature selection; fuzzy mutual information; redundancy; relevance; stability |
| title | Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature Selection |
| title_full | Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature Selection |
| title_fullStr | Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature Selection |
| title_full_unstemmed | Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature Selection |
| title_short | Fuzzy Mutual Information Based min-Redundancy and Max-Relevance Heterogeneous Feature Selection |
| title_sort | fuzzy mutual information based min redundancy and max relevance heterogeneous feature selection |
| topic | Feature selection; fuzzy mutual information; redundancy; relevance; stability |
| url | https://www.atlantis-press.com/article/2353.pdf |
| work_keys_str_mv | AT darenyu fuzzymutualinformationbasedminredundancyandmaxrelevanceheterogeneousfeatureselection AT shuangan fuzzymutualinformationbasedminredundancyandmaxrelevanceheterogeneousfeatureselection AT qinghuahu fuzzymutualinformationbasedminredundancyandmaxrelevanceheterogeneousfeatureselection |