DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders

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-...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of healthcare informatics research Jg. 4; H. 1; S. 50 - 70
Hauptverfasser: Nogas, Jacob, Khan, Shehroz S., Mihailidis, Alex
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 01.03.2020
Schlagworte:
ISSN:2509-4971, 2509-498X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract 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, DeepFall , which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.
AbstractList 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, DeepFall , which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.
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, , which formulates the fall detection problem as an anomaly detection problem. The framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.
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, DeepFall, which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.
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, DeepFall, which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.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, DeepFall, which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.
Author Khan, Shehroz S.
Nogas, Jacob
Mihailidis, Alex
Author_xml – sequence: 1
  givenname: Jacob
  orcidid: 0000-0002-6120-431X
  surname: Nogas
  fullname: Nogas, Jacob
  email: jacob.nogas@mail.utoronto.ca
  organization: University of Toronto
– sequence: 2
  givenname: Shehroz S.
  surname: Khan
  fullname: Khan, Shehroz S.
  organization: University of Toronto
– sequence: 3
  givenname: Alex
  surname: Mihailidis
  fullname: Mihailidis, Alex
  organization: Toronto Rehabilitation Institute, University Health Network
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35415435$$D View this record in MEDLINE/PubMed
BookMark eNp9kUFP3DAQha0KVCjlD_RQ5cjFxXacxO6hElqgRUJwgEpVL5bjHYNR1g52soh_j8MuK9rDnmyPv_dmNO8T2vHBA0JfKPlGCWmOE6d1XWNCJSaE1BTzD2ifVURiLsWfnc29oXvoMKWHDFHBKyaaj2ivrDiteFnto7-nAP257rrvxVXw-MIvdXJLKKZScQoDmMEFXzy54b6Y0OKm17mCb2HRh6i7Yhb8MnTjROXXyTgE8CbMIabPaNfqLsHh-jxAv8_Pbme_8OX1z4vZySU2nNcDFo0wNdOiNdY0LZub0lTU1lxYIFyX2rbUVq0lVDNqhQEJuTqnFFijTRaVB-jHyrcf2wXMDfghD6b66BY6Pqugnfr3x7t7dReWSkjBGimzwdHaIIbHEdKgFi4Z6DrtIYxJsZpLKSsqy4x-fd9r0-RtoRlgK8DEkFIEu0EoUVNwahWcysGp1-AUzyLxn8i4YVrzNK_rtkvLlTTlPv4OonoIY8xRpG2qF_Xvr3c
CitedBy_id crossref_primary_10_1007_s11042_023_16476_6
crossref_primary_10_1371_journal_pone_0325253
crossref_primary_10_1049_ipr2_12532
crossref_primary_10_1109_ACCESS_2025_3539449
crossref_primary_10_1109_ACCESS_2021_3083064
crossref_primary_10_1109_ACCESS_2023_3307138
crossref_primary_10_3390_s25113313
crossref_primary_10_1016_j_engappai_2025_111819
crossref_primary_10_3390_app13126916
crossref_primary_10_3390_diagnostics12123060
crossref_primary_10_1111_exsy_12564
crossref_primary_10_1186_s12984_021_00918_z
crossref_primary_10_3390_s22114194
crossref_primary_10_1016_j_compbiomed_2022_105626
crossref_primary_10_22630_MGV_2025_34_1_3
crossref_primary_10_1016_j_knosys_2025_113038
crossref_primary_10_1007_s10586_022_03818_6
crossref_primary_10_1007_s42979_023_02480_y
crossref_primary_10_1109_ACCESS_2020_3022366
crossref_primary_10_1109_TETCI_2024_3358103
crossref_primary_10_1007_s12559_020_09749_x
crossref_primary_10_1109_ACCESS_2024_3360691
crossref_primary_10_1111_jonm_13787
crossref_primary_10_3390_s25134128
crossref_primary_10_1016_j_jestch_2025_102185
crossref_primary_10_1007_s41666_022_00121_2
crossref_primary_10_1109_JSYST_2022_3140546
crossref_primary_10_1109_TCSVT_2024_3417810
crossref_primary_10_1109_ACCESS_2022_3143990
crossref_primary_10_1109_ACCESS_2022_3211939
crossref_primary_10_1007_s11042_022_12018_8
crossref_primary_10_1109_ACCESS_2023_3321192
crossref_primary_10_1016_j_eswa_2021_116076
crossref_primary_10_1109_TASE_2020_3042158
crossref_primary_10_1038_s41598_025_11325_y
crossref_primary_10_1109_JSEN_2024_3446673
crossref_primary_10_1007_s11760_022_02174_7
crossref_primary_10_1016_j_knosys_2023_110992
crossref_primary_10_1007_s00603_025_04620_7
crossref_primary_10_1109_JSEN_2020_3032728
crossref_primary_10_1007_s10489_024_05645_1
crossref_primary_10_1016_j_procs_2024_08_028
crossref_primary_10_3390_technologies10020047
crossref_primary_10_1007_s10044_020_00901_9
crossref_primary_10_1016_j_jestch_2022_101227
crossref_primary_10_1109_TCSVT_2023_3303258
crossref_primary_10_1186_s12938_023_01065_3
crossref_primary_10_3390_jimaging7070109
Cites_doi 10.1016/j.patrec.2017.07.016
10.1007/978-3-319-20227-3_19
10.1109/CVPR.2001.990497
10.1016/j.cmpb.2014.09.005
10.1109/JBHI.2014.2304357
10.1109/TPAMI.2012.59
10.1109/ICCV.2015.510
10.1007/978-3-642-33715-4_54
10.1109/WACV.2017.118
10.1109/ICOSP.2014.7015185
10.1016/j.eswa.2017.06.011
10.21528/CBIC2017-49
10.1016/j.cviu.2016.10.010
10.1109/TIP.2017.2670780
10.1109/TKDE.2018.2806975
10.1371/journal.pone.0152173
10.1016/j.ijmedinf.2016.07.004
10.1016/j.asoc.2017.01.034
10.1007/978-3-319-71249-9_3
10.7326/0003-4819-113-4-308
10.1109/CVPR.2016.86
10.1007/978-3-642-21735-7_7
10.1017/S026988891300043X
10.5244/C.31.139
10.29007/xt7r
10.1145/1541880.1541882
10.1109/EMBC.2016.7590763
10.1145/3123266.3123451
10.5244/C.26.124
ContentType Journal Article
Copyright Springer Nature Switzerland AG 2019
Springer Nature Switzerland AG 2019.
Copyright_xml – notice: Springer Nature Switzerland AG 2019
– notice: Springer Nature Switzerland AG 2019.
DBID AAYXX
CITATION
NPM
7X8
5PM
DOI 10.1007/s41666-019-00061-4
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
PubMed

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Computer Science
EISSN 2509-498X
EndPage 70
ExternalDocumentID PMC8982799
35415435
10_1007_s41666_019_00061_4
Genre Journal Article
GroupedDBID -EM
0R~
406
AACDK
AAHNG
AAIAL
AAJBT
AANZL
AARHV
AASML
AATNV
AATVU
AAUYE
AAYUE
ABAKF
ABDZT
ABECU
ABFTV
ABJNI
ABJOX
ABKCH
ABMQK
ABQBU
ABTEG
ABTKH
ABTMW
ABXPI
ACAOD
ACDTI
ACGFS
ACHSB
ACMLO
ACOKC
ACPIV
ACZOJ
ADHHG
ADKNI
ADKPE
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFQL
AEJRE
AEMSY
AEOHA
AESKC
AEVLU
AEXYK
AFBBN
AFQWF
AGDGC
AGMZJ
AGQEE
AGRTI
AHKAY
AHSBF
AIAKS
AIGIU
AILAN
AITGF
AJRNO
AJZVZ
ALFXC
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMXSW
AMYLF
AMYQR
AXYYD
BGNMA
CSCUP
DNIVK
DPUIP
EBLON
EBS
EIOEI
EJD
FERAY
FIGPU
FINBP
FNLPD
FSGXE
GGCAI
H13
HG6
IKXTQ
IWAJR
J-C
JZLTJ
KOV
LLZTM
M4Y
NPVJJ
NQJWS
NU0
O9J
PT4
RLLFE
ROL
RPM
RSV
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
TSG
UOJIU
UTJUX
UZXMN
VFIZW
Z83
ZMTXR
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
AEZWR
AFDZB
AFHIU
AFOHR
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
NPM
7X8
5PM
ID FETCH-LOGICAL-c446t-878c62a8bcfc7b2dc3c51f648fe04a3afb1f5bf01a21f8ce9e4a3d11e27acbcf3
IEDL.DBID RSV
ISICitedReferencesCount 61
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000705500800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2509-4971
IngestDate Tue Sep 30 17:00:03 EDT 2025
Fri Jul 11 11:34:17 EDT 2025
Thu Jan 02 22:54:57 EST 2025
Sat Nov 29 02:53:39 EST 2025
Tue Nov 18 22:17:49 EST 2025
Fri Feb 21 02:35:26 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 1
Keywords Spatio-temporal
Convolutional autoencoders
Fall detection
Anomaly detection
Language English
License Springer Nature Switzerland AG 2019.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c446t-878c62a8bcfc7b2dc3c51f648fe04a3afb1f5bf01a21f8ce9e4a3d11e27acbcf3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-6120-431X
OpenAccessLink https://www.ncbi.nlm.nih.gov/pmc/articles/8982799
PMID 35415435
PQID 2649995193
PQPubID 23479
PageCount 21
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_8982799
proquest_miscellaneous_2649995193
pubmed_primary_35415435
crossref_primary_10_1007_s41666_019_00061_4
crossref_citationtrail_10_1007_s41666_019_00061_4
springer_journals_10_1007_s41666_019_00061_4
PublicationCentury 2000
PublicationDate 2020-03-01
PublicationDateYYYYMMDD 2020-03-01
PublicationDate_xml – month: 03
  year: 2020
  text: 2020-03-01
  day: 01
PublicationDecade 2020
PublicationPlace Cham
PublicationPlace_xml – name: Cham
– name: Switzerland
PublicationTitle Journal of healthcare informatics research
PublicationTitleAbbrev J Healthc Inform Res
PublicationTitleAlternate J Healthc Inform Res
PublicationYear 2020
Publisher Springer International Publishing
Publisher_xml – name: Springer International Publishing
References Munawar A, Vinayavekhin P, De Magistris G (2017) Spatio-temporal anomaly detection for industrial robots through prediction in unsupervised feature space. In: 2017 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp 1017–1025
Nogas J, Khan SS, Mihailidis A (2018) Fall detection from thermal camera using convolutional lstm autoencoder. In: Proceedings of the 2nd workshop on aging, rehabilitation and independent assisted living. IJCAI Workshop
Tran HT, Hogg D (2017) Anomaly detection using a convolutional winner-take-all autoencoder. In: Proceedings of the British machine vision conference 2017. Leeds
YusifSSoarJHafeez-BaigAOlder people, assistive technologies, and the barriers to adoption: a systematic reviewInt J Med Inform20169411211610.1016/j.ijmedinf.2016.07.004
KhanSSMaddenMGOne-class classification: taxonomy of study and review of techniquesKnowl Eng Rev201429334537410.1017/S026988891300043X
Hasan M, Choi J, Neumann J, Roy-Chowdhury AK, Davis LS (2016) Learning temporal regularity in video sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 733–742
Gutoski M, Aquino NMR, Ribeiro M, Lazzaretti AE, Lopes HS (2017) Detection of video anomalies using convolutional autoencoders and one-class support vector machines. In: Proc. XIII Brazilian congress on computational intelligence
Viacheslav V, Alexander F, Vladimir M, Svetlana T, Oksana L (2014) Kinect depth map restoration using modified exemplar-based inpainting. In: 2014 12th International conference on signal processing (ICSP). IEEE, pp 1175–1179
PenttiläJA method for anomaly detection in hyperspectral images, using deep convolutional autoencoders. Master’s thesis2017FinlandUniversity of Jyväskylä
Masci J, Meier U, Cireşan D, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In: International conference on artificial neural networks. Springer, pp 52–59
SabokrouMFayyazMFathyMKletteRDeep-cascade: cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenesIEEE Trans Image Process201726419922004363624610.1109/TIP.2017.2670780
Baccouche M, Mamalet F, Wolf C, Garcia C, Baskurt A (2012) Spatio-temporal convolutional sparse autoencoder for sequence classification. In: BMVC. Citeseer
Skubic M, Harris BH, Stone E, Ho K, Su BY, Rantz M (2016) Testing non-wearable fall detection methods in the homes of older adults. In: 2016 IEEE 38th annual international conference of the engineering in medicine and biology society (EMBC). IEEE, pp 557–560
Nathan Silberman Derek Hoiem PK, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: ECCV
CDC (2017) Enter of disease control and prevention – important facts about falls. https://www.cdc.gov/homeandrecreationalsafety/falls/adultfalls.html. [Online accessed 22-December-2017]
RubensteinLZRobbinsASJosephsonKRSchulmanBLOsterweilDThe value of assessing falls in an elderly population: a randomized clinical trialAnn Intern Med1990113430831610.7326/0003-4819-113-4-308
Bertalmio M, Bertozzi AL, Sapiro G (2001) Navier-stokes, fluid dynamics, and image and video inpainting. In: Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, vol 1, pp I–355–I–362, DOI https://doi.org/10.1109/CVPR.2001.990497
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680
JiSXuWYangMYuK3d convolutional neural networks for human action recognitionIEEE Trans Pattern Anal Mach Intell201335122123110.1109/TPAMI.2012.59
Zhao Y, Deng B, Shen C, Liu Y, Lu H, Hua XS (2017) Spatio-temporal autoencoder for video anomaly detection. In: Proceedings of the 2017 ACM on multimedia conference, MM ’17. ACM, New York
Chong YS, Tay YH (2017) Abnormal event detection in videos using spatiotemporal autoencoder. In: International symposium on neural networks. Springer, pp 189–196
Itseez (2015) Open source computer vision library. https://github.com/itseez/opencv
KhanSSKargMEKulićDHoeyJDetecting falls with x-factor hidden Markov modelsAppl Soft Comput20175516817710.1016/j.asoc.2017.01.034
Khan SS, Taati B (2017) Detecting unseen falls from wearable devices using channel-wise ensemble of autoencoders. Expert Systems with Applications
Vadivelu S, Ganesan S, Murthy OR, Dhall A (2016) Thermal imaging based elderly fall detection. In: ACCV workshop. Springer, pp 541–553
XuDYanYRicciESebeNDetecting anomalous events in videos by learning deep representations of appearance and motionComput Vis Image Underst201715611712710.1016/j.cviu.2016.10.010
Du Tran Lubomir Bourdev RFLTMP (2015) Learning spatiotemporal features with 3d convolutional networks. In: IEEE International conference on computer vision (ICCV). IEEE, DOI https://doi.org/10.1109/ICCV.2015.510
Chollet F., et al. (2015) Keras: the python deep learning library https://github.com/fchollet/keras. Online accessed 20-January-2018
Mercuri M, Garripoli C, Karsmakers P, Soh PJ, Vandenbosch GA, Pace C, Leroux P, Schreurs D (2016) Healthcare system for non-invasive fall detection in indoor environment. In: Applications in electronics pervading industry, environment and society. Springer, pp 145–152
Samek W, Wiegand T, Müller KR (2017) Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. arXiv:https://arxiv.org/abs/1708.08296
Bogdan KwolekMKHuman fall detection on embedded platform using depth maps and wireless accelerometerComput Methods Programs Biomed201411748950110.1016/j.cmpb.2014.09.005
MaXWangHXueBZhouMJiBLiYDepth-based human fall detection via shape features and improved extreme learning machineIEEE J Biomed Health Inform20141861915192210.1109/JBHI.2014.2304357
GoldsteinMUchidaSA comparative evaluation of unsupervised anomaly detection algorithms for multivariate dataPloS one 1120164e015217310.1371/journal.pone.0152173
Chalapathy R, Menon AK, Chawla S (2017) Robust, deep and inductive anomaly detection. In: European conference on machine learning. Skopje
ChandolaVBanerjeeAKumarVAnomaly detection: a surveyACM Comput Surv200941315:115:5810.1145/1541880.1541882
Ribeiro M, Lazzaretti AE, Lopes HS (2017) A study of deep convolutional auto-encoders for anomaly detection in videos. Pattern Recognition Letters
KhanSSAhmadARelationship between variants of one-class nearest neighbors and creating their accurate ensemblesIEEE Trans Knowl Data Eng20183091796180910.1109/TKDE.2018.2806975
M Goldstein (61_CR10) 2016; 4
SS Khan (61_CR17) 2017; 55
LZ Rubenstein (61_CR28) 1990; 113
V Chandola (61_CR6) 2009; 41
X Ma (61_CR20) 2014; 18
MK Bogdan Kwolek (61_CR3) 2014; 117
61_CR19
S Yusif (61_CR36) 2016; 94
61_CR30
61_CR31
61_CR1
61_CR32
61_CR2
61_CR11
61_CR33
61_CR12
61_CR34
61_CR13
61_CR14
61_CR37
61_CR7
61_CR8
61_CR9
J Penttilä (61_CR26) 2017
D Xu (61_CR35) 2017; 156
61_CR4
S Ji (61_CR15) 2013; 35
61_CR5
SS Khan (61_CR18) 2014; 29
61_CR27
SS Khan (61_CR16) 2018; 30
M Sabokrou (61_CR29) 2017; 26
61_CR21
61_CR22
61_CR23
61_CR24
61_CR25
References_xml – reference: CDC (2017) Enter of disease control and prevention – important facts about falls. https://www.cdc.gov/homeandrecreationalsafety/falls/adultfalls.html. [Online accessed 22-December-2017]
– reference: Gutoski M, Aquino NMR, Ribeiro M, Lazzaretti AE, Lopes HS (2017) Detection of video anomalies using convolutional autoencoders and one-class support vector machines. In: Proc. XIII Brazilian congress on computational intelligence
– reference: GoldsteinMUchidaSA comparative evaluation of unsupervised anomaly detection algorithms for multivariate dataPloS one 1120164e015217310.1371/journal.pone.0152173
– reference: Chalapathy R, Menon AK, Chawla S (2017) Robust, deep and inductive anomaly detection. In: European conference on machine learning. Skopje
– reference: Munawar A, Vinayavekhin P, De Magistris G (2017) Spatio-temporal anomaly detection for industrial robots through prediction in unsupervised feature space. In: 2017 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp 1017–1025
– reference: Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680
– reference: KhanSSKargMEKulićDHoeyJDetecting falls with x-factor hidden Markov modelsAppl Soft Comput20175516817710.1016/j.asoc.2017.01.034
– reference: SabokrouMFayyazMFathyMKletteRDeep-cascade: cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenesIEEE Trans Image Process201726419922004363624610.1109/TIP.2017.2670780
– reference: Bertalmio M, Bertozzi AL, Sapiro G (2001) Navier-stokes, fluid dynamics, and image and video inpainting. In: Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, vol 1, pp I–355–I–362, DOI https://doi.org/10.1109/CVPR.2001.990497
– reference: Hasan M, Choi J, Neumann J, Roy-Chowdhury AK, Davis LS (2016) Learning temporal regularity in video sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 733–742
– reference: XuDYanYRicciESebeNDetecting anomalous events in videos by learning deep representations of appearance and motionComput Vis Image Underst201715611712710.1016/j.cviu.2016.10.010
– reference: RubensteinLZRobbinsASJosephsonKRSchulmanBLOsterweilDThe value of assessing falls in an elderly population: a randomized clinical trialAnn Intern Med1990113430831610.7326/0003-4819-113-4-308
– reference: JiSXuWYangMYuK3d convolutional neural networks for human action recognitionIEEE Trans Pattern Anal Mach Intell201335122123110.1109/TPAMI.2012.59
– reference: KhanSSAhmadARelationship between variants of one-class nearest neighbors and creating their accurate ensemblesIEEE Trans Knowl Data Eng20183091796180910.1109/TKDE.2018.2806975
– reference: Baccouche M, Mamalet F, Wolf C, Garcia C, Baskurt A (2012) Spatio-temporal convolutional sparse autoencoder for sequence classification. In: BMVC. Citeseer
– reference: Vadivelu S, Ganesan S, Murthy OR, Dhall A (2016) Thermal imaging based elderly fall detection. In: ACCV workshop. Springer, pp 541–553
– reference: Chong YS, Tay YH (2017) Abnormal event detection in videos using spatiotemporal autoencoder. In: International symposium on neural networks. Springer, pp 189–196
– reference: MaXWangHXueBZhouMJiBLiYDepth-based human fall detection via shape features and improved extreme learning machineIEEE J Biomed Health Inform20141861915192210.1109/JBHI.2014.2304357
– reference: Masci J, Meier U, Cireşan D, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In: International conference on artificial neural networks. Springer, pp 52–59
– reference: Nathan Silberman Derek Hoiem PK, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: ECCV
– reference: Mercuri M, Garripoli C, Karsmakers P, Soh PJ, Vandenbosch GA, Pace C, Leroux P, Schreurs D (2016) Healthcare system for non-invasive fall detection in indoor environment. In: Applications in electronics pervading industry, environment and society. Springer, pp 145–152
– reference: Itseez (2015) Open source computer vision library. https://github.com/itseez/opencv
– reference: Samek W, Wiegand T, Müller KR (2017) Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. arXiv:https://arxiv.org/abs/1708.08296
– reference: KhanSSMaddenMGOne-class classification: taxonomy of study and review of techniquesKnowl Eng Rev201429334537410.1017/S026988891300043X
– reference: Ribeiro M, Lazzaretti AE, Lopes HS (2017) A study of deep convolutional auto-encoders for anomaly detection in videos. Pattern Recognition Letters
– reference: YusifSSoarJHafeez-BaigAOlder people, assistive technologies, and the barriers to adoption: a systematic reviewInt J Med Inform20169411211610.1016/j.ijmedinf.2016.07.004
– reference: Skubic M, Harris BH, Stone E, Ho K, Su BY, Rantz M (2016) Testing non-wearable fall detection methods in the homes of older adults. In: 2016 IEEE 38th annual international conference of the engineering in medicine and biology society (EMBC). IEEE, pp 557–560
– reference: Bogdan KwolekMKHuman fall detection on embedded platform using depth maps and wireless accelerometerComput Methods Programs Biomed201411748950110.1016/j.cmpb.2014.09.005
– reference: Chollet F., et al. (2015) Keras: the python deep learning library https://github.com/fchollet/keras. Online accessed 20-January-2018
– reference: Nogas J, Khan SS, Mihailidis A (2018) Fall detection from thermal camera using convolutional lstm autoencoder. In: Proceedings of the 2nd workshop on aging, rehabilitation and independent assisted living. IJCAI Workshop
– reference: Tran HT, Hogg D (2017) Anomaly detection using a convolutional winner-take-all autoencoder. In: Proceedings of the British machine vision conference 2017. Leeds
– reference: Du Tran Lubomir Bourdev RFLTMP (2015) Learning spatiotemporal features with 3d convolutional networks. In: IEEE International conference on computer vision (ICCV). IEEE, DOI https://doi.org/10.1109/ICCV.2015.510
– reference: Viacheslav V, Alexander F, Vladimir M, Svetlana T, Oksana L (2014) Kinect depth map restoration using modified exemplar-based inpainting. In: 2014 12th International conference on signal processing (ICSP). IEEE, pp 1175–1179
– reference: PenttiläJA method for anomaly detection in hyperspectral images, using deep convolutional autoencoders. Master’s thesis2017FinlandUniversity of Jyväskylä
– reference: ChandolaVBanerjeeAKumarVAnomaly detection: a surveyACM Comput Surv200941315:115:5810.1145/1541880.1541882
– reference: Zhao Y, Deng B, Shen C, Liu Y, Lu H, Hua XS (2017) Spatio-temporal autoencoder for video anomaly detection. In: Proceedings of the 2017 ACM on multimedia conference, MM ’17. ACM, New York
– reference: Khan SS, Taati B (2017) Detecting unseen falls from wearable devices using channel-wise ensemble of autoencoders. Expert Systems with Applications
– ident: 61_CR27
  doi: 10.1016/j.patrec.2017.07.016
– ident: 61_CR22
  doi: 10.1007/978-3-319-20227-3_19
– ident: 61_CR30
– ident: 61_CR2
  doi: 10.1109/CVPR.2001.990497
– ident: 61_CR11
– volume: 117
  start-page: 489
  year: 2014
  ident: 61_CR3
  publication-title: Comput Methods Programs Biomed
  doi: 10.1016/j.cmpb.2014.09.005
– volume: 18
  start-page: 1915
  issue: 6
  year: 2014
  ident: 61_CR20
  publication-title: IEEE J Biomed Health Inform
  doi: 10.1109/JBHI.2014.2304357
– volume: 35
  start-page: 221
  issue: 1
  year: 2013
  ident: 61_CR15
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2012.59
– ident: 61_CR9
  doi: 10.1109/ICCV.2015.510
– ident: 61_CR8
– ident: 61_CR24
  doi: 10.1007/978-3-642-33715-4_54
– ident: 61_CR4
– ident: 61_CR23
  doi: 10.1109/WACV.2017.118
– ident: 61_CR34
  doi: 10.1109/ICOSP.2014.7015185
– ident: 61_CR19
  doi: 10.1016/j.eswa.2017.06.011
– ident: 61_CR12
  doi: 10.21528/CBIC2017-49
– volume: 156
  start-page: 117
  year: 2017
  ident: 61_CR35
  publication-title: Comput Vis Image Underst
  doi: 10.1016/j.cviu.2016.10.010
– volume: 26
  start-page: 1992
  issue: 4
  year: 2017
  ident: 61_CR29
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2017.2670780
– volume: 30
  start-page: 1796
  issue: 9
  year: 2018
  ident: 61_CR16
  publication-title: IEEE Trans Knowl Data Eng
  doi: 10.1109/TKDE.2018.2806975
– volume: 4
  start-page: e0152173
  year: 2016
  ident: 61_CR10
  publication-title: PloS one 11
  doi: 10.1371/journal.pone.0152173
– volume: 94
  start-page: 112
  year: 2016
  ident: 61_CR36
  publication-title: Int J Med Inform
  doi: 10.1016/j.ijmedinf.2016.07.004
– ident: 61_CR14
– volume: 55
  start-page: 168
  year: 2017
  ident: 61_CR17
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2017.01.034
– ident: 61_CR5
  doi: 10.1007/978-3-319-71249-9_3
– volume: 113
  start-page: 308
  issue: 4
  year: 1990
  ident: 61_CR28
  publication-title: Ann Intern Med
  doi: 10.7326/0003-4819-113-4-308
– ident: 61_CR33
– ident: 61_CR13
  doi: 10.1109/CVPR.2016.86
– ident: 61_CR21
  doi: 10.1007/978-3-642-21735-7_7
– volume: 29
  start-page: 345
  issue: 3
  year: 2014
  ident: 61_CR18
  publication-title: Knowl Eng Rev
  doi: 10.1017/S026988891300043X
– ident: 61_CR7
– ident: 61_CR32
  doi: 10.5244/C.31.139
– ident: 61_CR25
  doi: 10.29007/xt7r
– volume: 41
  start-page: 15:1
  issue: 3
  year: 2009
  ident: 61_CR6
  publication-title: ACM Comput Surv
  doi: 10.1145/1541880.1541882
– ident: 61_CR31
  doi: 10.1109/EMBC.2016.7590763
– ident: 61_CR37
  doi: 10.1145/3123266.3123451
– ident: 61_CR1
  doi: 10.5244/C.26.124
– volume-title: A method for anomaly detection in hyperspectral images, using deep convolutional autoencoders. Master’s thesis
  year: 2017
  ident: 61_CR26
SSID ssj0001845287
Score 2.4205885
Snippet 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...
SourceID pubmedcentral
proquest
pubmed
crossref
springer
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 50
SubjectTerms Biomedical Engineering and Bioengineering
Computational Biology/Bioinformatics
Computational Intelligence
Computer Science
Data Mining and Knowledge Discovery
Health Informatics
Research Article
Title DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders
URI https://link.springer.com/article/10.1007/s41666-019-00061-4
https://www.ncbi.nlm.nih.gov/pubmed/35415435
https://www.proquest.com/docview/2649995193
https://pubmed.ncbi.nlm.nih.gov/PMC8982799
Volume 4
WOSCitedRecordID wos000705500800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 2509-498X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001845287
  issn: 2509-4971
  databaseCode: RSV
  dateStart: 20170601
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwED-xgRAvDMZXYExG4g0s1YmzOLxN2yp4WDWxgSpeorNra5MqZ1rT_v2cXSeoG5oEL3lwzo7jO_t-9p3vAD6iqFBiYTgS9uCyLiTHQiBXcma0xRpLrWOyiWoyUdNpfZYuhS16b_feJBlX6uGymwwWLtr61jwqXi634CGpOxUSNnw___nnZEXJMo-Z8Ui9xxRqIt2W-XszmxrpDsy86y15y2QaNdF45__-4Rk8TciTHa5F5Tk8sH4XdvqsDixN8l14fJrM7S_g17G112Ocz7-wSev5N7_C4O3OQhE7tl104_IsnOWyQMrOo382v1jHu5qzo9avkmyHTy-7NsTNDL7TL-HH-OTi6CtPyRi4oR1jR6umMgc5Km2cqXQ-M4UphTuQytkRMRudFq7UbiQwF04ZW1sqnQlh8woNVSpewbZvvX0DTJPWdMYQMpVOEgLEQqqRcgWODG2ZtctA9AxpTIpUHhJmzJshxnIcx4bGsYnj2MgMPg11rtdxOu6l_tDzuaHpFGwk6G27XDSEDwkyB1ibwes134f2ipLQDsHLDKoNiRgIQqjuzTf-6jKG7Fa1yqu6zuBzLxdNWisW93Tz7b-Rv4MneTgNiB5ye7Dd3Szte3hkVt3V4mYftqqpoufk7HQ_TpjfNDIPBw
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fTxQxEJ4oGvVFBFHXX5TEN2xy3e2yXd8MeIEIFyKHIbw0ba-NJJcu4fbu73fa6y45MST62m27u51p52tn-g3AJ8UqxVVhqELsQXldcKoKpqjgE6OtqlWpdUw2UY1G4uKiPk2XwmZdtHvnkowrdX_ZjQcPF259axoNL-UP4RFHixUY83-c_bw9WRG8zGNmPDTvMYUaS7dl_t7NqkW6AzPvRkv-4TKNlmi4_n__8AKeJ-RJvi5VZQMeWL8J611WB5Im-SY8OUnu9pdweWDt9VBNp1_IqPH0yC9UiHYnoYgc2DaGcXkSznJJqErOYnw2HS_5rqZkv_GLpNvh1fO2CbyZIXZ6C86H38b7hzQlY6AGd4wtrprC7OVKaONMpfOJKUzJ3B4Xzg5Q2Mpp5krtBkzlzAlja4ulE8ZsXimDjYpXsOYbb98A0Wg1nTGITLnjiABVwcVAuEINDG6ZtcuAdQKRJjGVh4QZU9lzLMdxlDiOMo6j5Bns9m2ulzwd99be6eQscToFH4nytpnPJOJDhMwB1mbwein3vr-iRLSD8DKDakUj-gqBqnv1ib_6FSm7RS3yqq4z-NzphUxrxeyez3z7b9W34enh-ORYHh-Nvr-DZ3k4GYjRcu9hrb2Z2w_w2Czaq9nNxzhhfgMwrQ_3
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED-NDU28bDAYhE8j8Tas1omzOLyhdRUTUE3amCZeLNu1xaTKqda0f__OzgeUTZMQr87ZSeyz73e-L4APihWKq8xQhdiD8jLjVGVMUcGnRltVqlzrWGyimEzE5WV5-kcUf_R270ySTUxDyNLk68F86gZ94BsP1i5Ug0sahTDlD2CLB0f6oK-fXfy-ZRE8T2OVPBT1sZwaayNn7h5mXTrdgpy3PSf_Mp9GqTTe_f__eQw7LSIlnxsWegIb1u_BblftgbSbfw-2v7dm-Kfwc2TtfKxms09kUnl64lcqeMGT0ERGto7uXZ6EO14SSMlZ9Num500erBk5qvyq5fnw6mVdhXyawaf6GfwYH58ffaFtkQZqUJOs8TQV5jBVQhtnCp1OTWZy5g65cHaITKCcZi7XbshUypwwtrTYOmXMpoUy2Cnbh01fefsCiEZp6oxBxModR2SoMi6GwmVqaFCV1i4B1i2ONG0G81BIYyb73MtxHiXOo4zzKHkCB32feZO_417q992aS9xmwXaivK2WC4m4EaF0gLsJPG94oB8vyxEFIexMoFjjjp4gpPBef-KvfsVU3qIUaVGWCXzseES2Z8jins98-W_k72D7dDSW304mX1_BozRcGEQnutewWV8v7Rt4aFb11eL6bdw7N1p7GNs
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DeepFall%3A+Non-Invasive+Fall+Detection+with+Deep+Spatio-Temporal+Convolutional+Autoencoders&rft.jtitle=Journal+of+healthcare+informatics+research&rft.au=Nogas%2C+Jacob&rft.au=Khan%2C+Shehroz+S.&rft.au=Mihailidis%2C+Alex&rft.date=2020-03-01&rft.pub=Springer+International+Publishing&rft.issn=2509-4971&rft.eissn=2509-498X&rft.volume=4&rft.issue=1&rft.spage=50&rft.epage=70&rft_id=info:doi/10.1007%2Fs41666-019-00061-4&rft_id=info%3Apmid%2F35415435&rft.externalDocID=PMC8982799
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2509-4971&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2509-4971&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2509-4971&client=summon