DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders.
Anomaly detection
Convolutional autoencoders
Fall detection
Spatio-temporal
Journal
Journal of healthcare informatics research
ISSN: 2509-4971
Titre abrégé: J Healthc Inform Res
Pays: Switzerland
ID NLM: 101707451
Informations de publication
Date de publication:
Mar 2020
Mar 2020
Historique:
received:
04
10
2018
revised:
12
07
2019
accepted:
25
10
2019
entrez:
13
4
2022
pubmed:
18
12
2019
medline:
18
12
2019
Statut:
epublish
Résumé
Human falls rarely occur; however, detecting falls is very important from the health and safety perspective. Due to the rarity of falls, it is difficult to employ supervised classification techniques to detect them. Moreover, in these highly skewed situations, it is also difficult to extract domain-specific features to identify falls. In this paper, we present a novel framework,
Identifiants
pubmed: 35415435
doi: 10.1007/s41666-019-00061-4
pii: 61
pmc: PMC8982799
doi:
Types de publication
Journal Article
Langues
eng
Pagination
50-70Informations de copyright
© Springer Nature Switzerland AG 2019.
Déclaration de conflit d'intérêts
Conflict of interestsThe authors declare that they have no conflict of interest.
Références
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:557-560
pubmed: 28268392
PLoS One. 2016 Apr 19;11(4):e0152173
pubmed: 27093601
Comput Methods Programs Biomed. 2014 Dec;117(3):489-501
pubmed: 25308505
IEEE Trans Pattern Anal Mach Intell. 2013 Jan;35(1):221-31
pubmed: 22392705
IEEE Trans Image Process. 2017 Feb 17;26(4):1992-2004
pubmed: 28221995
IEEE J Biomed Health Inform. 2014 Nov;18(6):1915-22
pubmed: 25375688
Int J Med Inform. 2016 Oct;94:112-6
pubmed: 27573318
Ann Intern Med. 1990 Aug 15;113(4):308-16
pubmed: 2115755