Integrating expert knowledge with data in Bayesian networks: Preserving data-driven expectations when the expert variables remain unobserved
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 438
- Type
- D - Journal article
- DOI
-
10.1016/j.eswa.2016.02.050
- Title of journal
- Expert Systems with Applications
- Article number
- -
- First page
- 197
- Volume
- 56
- Issue
- -
- ISSN
- 1873-6793
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- 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)
-
-
- Citation count
- 32
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "A method for information fusion between data and knowledge in Bayesian networks with latent variables. It ensures the expected values of the observed variables are preserved under all known conditions, under the assumption the statistical outcomes are already influenced by the causes an expert might identify as variables missing from the dataset. This work contributed to the EPSRC 3-year Fellowship award (Constantinou) ""Bayesian-AI"" in 2018 (https://gow.epsrc.ukri.org/NGBOViewGrant.aspx?GrantRef=EP/S001646/1), helped secure funding for project CAUSAL-DYNAMICS (http://www.eecs.qmul.ac.uk/~norman/projects/leverhulme/causal_dynamics.html), and led to the collaboration with Mr Kiattikun Chobtham who joined our lab with funding from Royal Thai Government to specifically work on this project (http://bayesian-ai.eecs.qmul.ac.uk/people/)
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
