Cyborg groups enhance face recognition in crowded environments
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1335
- Type
- D - Journal article
- DOI
-
10.1371/journal.pone.0212935
- Title of journal
- PLoS ONE
- Article number
- e0212935
- First page
- e0212935
- Volume
- 14
- Issue
- 3
- ISSN
- 1932-6203
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2019
- 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
-
1
- Research group(s)
-
B - Brain Computer Interfaces and Neural Engineering (BCI-NE)
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is the first to show that human and AI decision-makers can work seamlessly as peers improving group-performance. Human-machine collaboration is difficult yet critical for US/UK governments (https://brain.ieee.org/brain-storm/enhancing-human-agent-teaming/, https://www.gov.uk/government/publications/human-machine-teaming-jcn-118). We show that adding AI-based team members improves group performance very significantly over purely-human groups. The research sprung from a Defence-and-Security PhD(DOI:10.1101/357004) and was instrumental for the inaugural $5M, US-DOD/UK-MoD-funded Bilateral Academic Research Initiative project (with USC, UCB, Harvard, UMass, Oxford) on teams of brain-computer-interface-assisted humans and AIs for strategic decision-making. This 1200 views, rigorous paper tested 10 participants; classifiers used cross-validation, statistically-significant results. It underpins a 20-year military timescale.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -