Bayesian heatmaps: probabilistic classification with multiple unreliable information sources
- Submitting institution
-
University of Oxford
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9502
- Type
- E - Conference contribution
- DOI
-
10.1007/978-3-319-71246-8_7
- Title of conference / published proceedings
- ECML PKDD 2017: Machine Learning and Knowledge Discovery in Databases
- First page
- 109
- Volume
- 10535
- Issue
- -
- ISSN
- 0302-9743
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2017
- 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
- Yes
- Number of additional authors
-
2
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Our heatmap products were used in 2017/2019 by Rescue Global, the UN, 60 NGOs, CDEMA and 24-Commando Royal Engineers to help plan their disaster response for Hurricanes Irma, Maria and Dorian. It was utilised by Satellite Applications Catapult into an imagery labelling tool (InnovateUK ref:900060), WorkFusion for matching curriculum vitaes to job adverts (patent: US15588530), and integrated into disaster response tools by BMT Defence Systems Ltd (MoD:CDE42106) (CEO, Rescue Global; Senior Earth Observation Specialist, Catapult; Data Science Department Lead, WorkFusion; Head of Information Systems, BMT Defence Systems available to corroborate). Subsequent funding: Alan Turing Fellowship; FTSC (ST/S00307X/1); EPSRC (EP/S515735/1).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -