Manifold Regularized Experimental Design for Active Learning
- Submitting institution
-
University of Northumbria at Newcastle
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 22062337
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2016.2635440
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 969
- Volume
- 26
- Issue
- 2
- ISSN
- 1057-7149
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2016
- 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)
-
D - Computer Vision and Natural Computing (CVNC)
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This novel idea on active learning allows effective training particularly in small-sized dataset. Its potential to tackle healthcare challenges, where data tends to be insufficient, was recognized by an invited presentation from Sunderland City Council in 2018 (invited by Dave Young, Deputy Strategic Change Manager, Sunderland City Council, Dave.Young@sunderland.gov.uk) in the half-day workshop Advanced Technology for Health and Care Services, for connecting academics with industrialists. It has also led to an invited academic seminar at Seoul National University, Korea in 2017 (invited by Prof. Jehee Lee, jehee@cse.snu.ac.kr) discussing the potential use of such a machine learning method in computer graphics.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -