Simplex basis function based sparse least squares support vector regression
- Submitting institution
-
The University of Reading
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 80789
- Type
- D - Journal article
- DOI
-
10.1016/j.neucom.2018.11.025
- Title of journal
- Neurocomputing
- Article number
- -
- First page
- 394
- Volume
- 330
- Issue
- -
- ISSN
- 0925-2312
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2019
- 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
-
2
- Research group(s)
-
9 - DSAI
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Least square support vector machine regression (LS-SVR) is a highly important modelling paradigm in machine learning. The significance of this paper is that it provides a novel fast LS-SVR solution to achieve a linear time complexity and to remove a main disadvantage of support vector machines, i.e. lack of sparseness. The paper contributes both to theoretical and practical advances in support vector regression with a potentially significant impact in many applications. The experimental evaluation demonstrates its superior performance, particularly in achieving sparsity of support vector machines with benchmark modelling of engineering systems.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -