An efficient LS-SVM based method for fuzzy system construction
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 12 - Engineering
- Output identifier
- 96686887
- Type
- D - Journal article
- DOI
-
10.1109/TFUZZ.2014.2321594
- Title of journal
- IEEE Transactions on Fuzzy Systems
- Article number
- -
- First page
- 627
- Volume
- 23
- Issue
- 3
- ISSN
- 1063-6706
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2014
- URL
-
http://dx.doi.org/10.1109/TFUZZ.2014.2321594
- 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
-
2
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This research is significant as it provides new insights by innovatively deriving a solid mathematics-based two-phase learning method to extract sparse fuzzy rules for model construction. Experimental evaluations, including on melt pressure prediction and mammographic masses diagnosis, show that model sparseness and computational efficiency can be achieved with comparative model accuracy, as opposed to previous learning techniques. The research contributed and strengthened the collaboration between 10+ leading UK and Chinese research institutions and industrial partners in energy and construction sectors (e.g. EP/L001063/1 and EP/G042594/1).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -