SEG-SSC: a framework based on synthetic examples generation for self-labeled semi-supervised classification
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1324155
- Type
- D - Journal article
- DOI
-
10.1109/TCYB.2014.2332003
- Title of journal
- IEEE Transactions on Cybernetics
- Article number
- -
- First page
- 622
- Volume
- 45
- Issue
- 4
- ISSN
- 2168-2267
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2014
- 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)
-
-
- Citation count
- 41
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In data mining, the effective use of unannotated data is key to tackling many practical applications, including medical diagnoses and spam filtering, in which manual annotation is a very costly and slow process. The main significance of this work is on the novel generation of (optimised) artificial data for semi-supervised learning. The idea of using this kind of pre-processing technique for semi-supervised learning was novel and the paper empirically demonstrates that it greatly improves the performance of previously existing methods.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
