Cyborg groups enhance face recognition in crowded environments.
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2019
2019
Historique:
received:
14
09
2018
accepted:
12
02
2019
entrez:
7
3
2019
pubmed:
7
3
2019
medline:
18
12
2019
Statut:
epublish
Résumé
Recognizing a person in a crowded environment is a challenging, yet critical, visual-search task for both humans and machine-vision algorithms. This paper explores the possibility of combining a residual neural network (ResNet), brain-computer interfaces (BCIs) and human participants to create "cyborgs" that improve decision making. Human participants and a ResNet undertook the same face-recognition experiment. BCIs were used to decode the decision confidence of humans from their EEG signals. Different types of cyborg groups were created, including either only humans (with or without the BCI) or groups of humans and the ResNet. Cyborg groups decisions were obtained weighing individual decisions by confidence estimates. Results show that groups of cyborgs are significantly more accurate (up to 35%) than the ResNet, the average participant, and equally-sized groups of humans not assisted by technology. These results suggest that melding humans, BCI, and machine-vision technology could significantly improve decision-making in realistic scenarios.
Identifiants
pubmed: 30840663
doi: 10.1371/journal.pone.0212935
pii: PONE-D-18-26924
pmc: PMC6402761
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0212935Commentaires et corrections
Type : ErratumIn
Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Proc Natl Acad Sci U S A. 2016 Aug 2;113(31):8777-82
pubmed: 27432950
Psychol Rev. 2013 Jul;120(3):697-719
pubmed: 23915088
Curr Biol. 2017 Sep 25;27(18):2827-2832.e3
pubmed: 28889976
PLoS One. 2016 Feb 26;11(2):e0150036
pubmed: 26918457
Nat Commun. 2014 Dec 08;5:5672
pubmed: 25482825
J Neurosci. 2015 Feb 25;35(8):3478-84
pubmed: 25716847
Neuron. 2014 Dec 17;84(6):1329-42
pubmed: 25521381
Clin Neurophysiol. 2012 Jun;123(6):1158-67
pubmed: 22119799
PLoS One. 2014 Jul 29;9(7):e102693
pubmed: 25072739
Sci Rep. 2017 Aug 10;7(1):7772
pubmed: 28798411
R Soc Open Sci. 2017 Aug 16;4(8):170193
pubmed: 28878973
J Exp Psychol Hum Percept Perform. 2002 Oct;28(5):1243-66
pubmed: 12421068
Annu Rev Psychol. 2004;55:623-55
pubmed: 14744229
Proc Natl Acad Sci U S A. 2018 Jun 12;115(24):6171-6176
pubmed: 29844174
Psychophysiology. 1994 May;31(3):291-308
pubmed: 8008793
Front Neuroinform. 2011 Nov 24;5:30
pubmed: 22131973
Proc Biol Sci. 2017 Feb 22;284(1849):
pubmed: 28202816
Sci Rep. 2016 Nov 30;6:37718
pubmed: 27901053
Nature. 1996 Jun 6;381(6582):520-2
pubmed: 8632824
IEEE Trans Biomed Eng. 2017 Jun;64(6):1238-1248
pubmed: 28541187
Proc Natl Acad Sci U S A. 2011 May 31;108(22):9020-5
pubmed: 21576485
Front Neurosci. 2010 Apr 21;4:30
pubmed: 20582271
J Pers Soc Psychol. 2018 Jan;114(1):10-28
pubmed: 29094960
Trends Ecol Evol. 2017 Sep;32(9):636-645
pubmed: 28739079
IEEE Trans Rehabil Eng. 2000 Dec;8(4):441-6
pubmed: 11204034
Nat Neurosci. 2016 Mar;19(3):366-74
pubmed: 26906503
Ergonomics. 2000 Jul;43(7):833-43
pubmed: 10929820
Neuroimage. 2012 Jan 2;59(1):94-108
pubmed: 21782959