Novel Improvements on the Fuzzy-Rough QuickReduct Algorithm
Summary :
Feature Selection (FS) is widely used to resolve the problem of selecting a subset of information-rich features; Fuzzy-Rough QuickReduct (FRQR) is one of the most successful FS methods. This paper presents two variants of the FRQR algorithm in order to improve its performance: 1) Combining Fuzzy-Rough Dependency Degree with Correlation-based FS merit to deal with a dilemma situation in feature subset selection and 2) Hybridizing the newly proposed method with the threshold based FRQR. The effectiveness of the proposed approaches are proven over sixteen UCI datasets; smaller subsets of features and higher classification accuracies are achieved.
- Publication
- IEICE TRANSACTIONS on Information Vol.E98-D No.2 pp.453-456
- Publication Date
- 2015/02/01
- Publicized
- 2014/10/21
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2014EDL8099
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Javad Rahimipour ANARAKI
Sungkyunkwan University
Mahdi EFTEKHARI
Shahid Bahonar University of Kerman
Chang Wook AHN
Sungkyunkwan University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Javad Rahimipour ANARAKI, Mahdi EFTEKHARI, Chang Wook AHN, "Novel Improvements on the Fuzzy-Rough QuickReduct Algorithm" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 2, pp. 453-456, February 2015, doi: 10.1587/transinf.2014EDL8099.
Abstract: Feature Selection (FS) is widely used to resolve the problem of selecting a subset of information-rich features; Fuzzy-Rough QuickReduct (FRQR) is one of the most successful FS methods. This paper presents two variants of the FRQR algorithm in order to improve its performance: 1) Combining Fuzzy-Rough Dependency Degree with Correlation-based FS merit to deal with a dilemma situation in feature subset selection and 2) Hybridizing the newly proposed method with the threshold based FRQR. The effectiveness of the proposed approaches are proven over sixteen UCI datasets; smaller subsets of features and higher classification accuracies are achieved.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8099/_p
Copy
@ARTICLE{e98-d_2_453,
author={Javad Rahimipour ANARAKI, Mahdi EFTEKHARI, Chang Wook AHN, },
journal={IEICE TRANSACTIONS on Information},
title={Novel Improvements on the Fuzzy-Rough QuickReduct Algorithm},
year={2015},
volume={E98-D},
number={2},
pages={453-456},
abstract={Feature Selection (FS) is widely used to resolve the problem of selecting a subset of information-rich features; Fuzzy-Rough QuickReduct (FRQR) is one of the most successful FS methods. This paper presents two variants of the FRQR algorithm in order to improve its performance: 1) Combining Fuzzy-Rough Dependency Degree with Correlation-based FS merit to deal with a dilemma situation in feature subset selection and 2) Hybridizing the newly proposed method with the threshold based FRQR. The effectiveness of the proposed approaches are proven over sixteen UCI datasets; smaller subsets of features and higher classification accuracies are achieved.},
keywords={},
doi={10.1587/transinf.2014EDL8099},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Novel Improvements on the Fuzzy-Rough QuickReduct Algorithm
T2 - IEICE TRANSACTIONS on Information
SP - 453
EP - 456
AU - Javad Rahimipour ANARAKI
AU - Mahdi EFTEKHARI
AU - Chang Wook AHN
PY - 2015
DO - 10.1587/transinf.2014EDL8099
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2015
AB - Feature Selection (FS) is widely used to resolve the problem of selecting a subset of information-rich features; Fuzzy-Rough QuickReduct (FRQR) is one of the most successful FS methods. This paper presents two variants of the FRQR algorithm in order to improve its performance: 1) Combining Fuzzy-Rough Dependency Degree with Correlation-based FS merit to deal with a dilemma situation in feature subset selection and 2) Hybridizing the newly proposed method with the threshold based FRQR. The effectiveness of the proposed approaches are proven over sixteen UCI datasets; smaller subsets of features and higher classification accuracies are achieved.
ER -
English
