Subclass-based semi-random data partitioning for improving sample representativeness
- Submitting institution
-
University of Portsmouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14316666
- Type
- D - Journal article
- DOI
-
10.1016/j.ins.2018.11.002
- Title of journal
- Information Sciences
- Article number
- -
- First page
- 208
- Volume
- 478
- Issue
- -
- ISSN
- 0020-0255
- Open access status
- Compliant
- Month of publication
- November
- 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
-
2
- Research group(s)
-
B - Computational Intelligence
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper addresses the issue of sample representativeness in the context of data partitioning for classification. The proposed approach ensures that both the training and the test set contain samples representative of the categories to be learnt. The significance of this research is that improvements in classification performance can be obtained across a variety of classification problems by implementing this new way of data partitioning.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -