Determining appropriate approaches for using data in feature selection
- Submitting institution
-
The University of East Anglia
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 182619652
- Type
- D - Journal article
- DOI
-
10.1007/s13042-015-0469-8
- Title of journal
- International Journal of Machine Learning and Cybernetics
- Article number
- -
- First page
- 915
- Volume
- 8
- Issue
- 3
- ISSN
- 1868-8071
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- 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
-
1
- Research group(s)
-
-
- Citation count
- 12
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Through a rigorous investigation we developed clear guidelines for deciding the appropriate method for feature selection. This formed a core component of Wang's ensemble methodology for winning the Rail Big Data Sandbox Competition in 2017 organised by the RSSB on behalf of the UK Government and grants for predicting train delays (RSSB-COF-INP-02), and additional grants including development of AI methods for improving seabed mapping (EIRA-RD031) and a KTP grant (KTP-12424) for transforming our AI ensemble methods to a TRL6+ product for seabed mapping.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -