Incremental Perspective for Feature Selection Based on Fuzzy Rough Sets
- Submitting institution
-
The University of West London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11044
- Type
- D - Journal article
- DOI
-
10.1109/TFUZZ.2017.2718492
- Title of journal
- IEEE Transactions on Fuzzy Systems
- Article number
- -
- First page
- 1257
- Volume
- 26
- Issue
- 3
- ISSN
- 1063-6706
- Open access status
- Technical exception
- Month of publication
- -
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 35
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Feature selection based on fuzzy rough sets is an effective approach for feature selection. Most existing methods use the whole dataset as the basis of deleting or adding features, which is costly or even intractable for large datasets. This paper presents a method that deletes or adds features incrementally based on batches of data presented sequentially. The theory behind this method, discernibility relations, can guarantee that the features selected incrementally (i.e. the data is presented in batches) are equivalent in discernibility power to those selected if the data is presented in whole. This is also validated experimentally.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -