Induction of classication rules by Gini-index based rule generation
- Submitting institution
-
University of Portsmouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10643613
- Type
- D - Journal article
- DOI
-
10.1016/j.ins.2018.01.025
- Title of journal
- Information Sciences
- Article number
- -
- First page
- 227
- Volume
- 436-437
- Issue
- -
- ISSN
- 0020-0255
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2018
- 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)
-
B - Computational Intelligence
- Citation count
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a new rule-based algorithm that leads to improved performance when compared with decision tree algorithms (which are very popular), as well as to a reduced number of rules. These improvements facilitate transparency and interpretability – essential issues regarding AI transparency and accountability, which are currently at the forefront of UK and EU agendas. The work has been applied for image segmentation (Liu at al., ICWAPR)’18, pp. 244-249) and used as a benchmark for rule-based methods (Meng&Shi, Knowledge-Based Systems, 2020, 105472).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -