mmFall: Fall Detection Using 4-D mmWave Radar and a Hybrid Variational RNN AutoEncoder

Elderly fall prevention and detection becomes extremely crucial with the fast aging population globally. In this article, we propose mmFall , a novel fall detection system, which comprises 1) the emerging millimeter-wave (mmWave) radar sensor to collect the human body's point cloud along with t...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on automation science and engineering Ročník 19; číslo 2; s. 1245 - 1257
Hlavní autori:	Jin, Feng, Sengupta, Arindam, Cao, Siyang
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.04.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Activities of daily living Anomalies Anomaly detection Cameras Centroids Conditional probability Data collection Doppler radar Fall detection False alarms Inference Labelling millimeter wave (mmWave) radar Millimeter waves Older people Privacy Radar Radar antennas Radar data Radar detection Radar measurements Randomness recurrent autoencoder (RAE) Recurrent neural networks semisupervised learning Senior citizens Sensors Three-dimensional displays variational autoencoder
ISSN:	1545-5955, 1558-3783
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Elderly fall prevention and detection becomes extremely crucial with the fast aging population globally. In this article, we propose mmFall , a novel fall detection system, which comprises 1) the emerging millimeter-wave (mmWave) radar sensor to collect the human body's point cloud along with the body centroid and 2) a hybrid variational recurrent neural network (RNN) autoencoder (HVRAE) to compute the anomaly level of the body motion based on the acquired point cloud. A fall is detected when the spike in anomaly level and the drop in centroid height occur simultaneously. The mmWave radar sensor offers privacy-compliance and high sensitivity to motion, over the traditional sensing modalities. However, 1) randomness in radar point cloud and 2) difficulties in fall collection/labeling in the traditional supervised fall detection approaches are the two major challenges. To overcome the randomness in radar data, the proposed HVRAE uses variational inference, a generative approach rather than a discriminative approach, to infer the posterior probability of the body's latent motion state every frame, followed by a RNN to summarize the temporal features over multiple frames. Moreover, to circumvent the difficulties in fall data collection/labeling, the HVRAE is built upon an autoencoder architecture in a semisupervised approach, which is only trained on the normal activities of daily living (ADL). In the inference stage, the HVRAE will generate a spike in the anomaly level once an abnormal motion, such as fall, occurs. During the experiment,<xref ref-type="fn" rid="fn1"> 1 we implemented the HVRAE along with two other baselines, and tested on the data set collected in an apartment. The receiver operating characteristic (ROC) curve indicates that our proposed model outperforms baselines and achieves 98% detection out of 50 falls at the expense of just 2 false alarms. Note to Practitioners -Traditional nonwearable fall detection approaches typically make use of a vision-based sensor, such as camera, to monitor and detect fall using a classifier that is trained in a supervised fashion on the collected fall and nonfall data. However, several problems render these methods impractical. First, camera-based monitoring may trigger privacy concerns. Second, fall data collection using human subjects is difficult and costly, not to mention the impossible ask of the elderly repeating simulated falls for data collection. In this article, we propose a new fall detection approach to overcome these problems 1) using a palm-size mmWave radar sensor to monitor the elderly, that is highly sensitive to motion while protecting privacy and 2) using a semisupervised anomaly detection approach to circumvent the fall data collection. Further hardware engineering and more training data from people with different body figures could make the proposed fall detection solution even more practical.
AbstractList	Elderly fall prevention and detection becomes extremely crucial with the fast aging population globally. In this article, we propose mmFall , a novel fall detection system, which comprises 1) the emerging millimeter-wave (mmWave) radar sensor to collect the human body's point cloud along with the body centroid and 2) a hybrid variational recurrent neural network (RNN) autoencoder (HVRAE) to compute the anomaly level of the body motion based on the acquired point cloud. A fall is detected when the spike in anomaly level and the drop in centroid height occur simultaneously. The mmWave radar sensor offers privacy-compliance and high sensitivity to motion, over the traditional sensing modalities. However, 1) randomness in radar point cloud and 2) difficulties in fall collection/labeling in the traditional supervised fall detection approaches are the two major challenges. To overcome the randomness in radar data, the proposed HVRAE uses variational inference, a generative approach rather than a discriminative approach, to infer the posterior probability of the body's latent motion state every frame, followed by a RNN to summarize the temporal features over multiple frames. Moreover, to circumvent the difficulties in fall data collection/labeling, the HVRAE is built upon an autoencoder architecture in a semisupervised approach, which is only trained on the normal activities of daily living (ADL). In the inference stage, the HVRAE will generate a spike in the anomaly level once an abnormal motion, such as fall, occurs. During the experiment,<xref ref-type="fn" rid="fn1"> 1 we implemented the HVRAE along with two other baselines, and tested on the data set collected in an apartment. The receiver operating characteristic (ROC) curve indicates that our proposed model outperforms baselines and achieves 98% detection out of 50 falls at the expense of just 2 false alarms. Note to Practitioners -Traditional nonwearable fall detection approaches typically make use of a vision-based sensor, such as camera, to monitor and detect fall using a classifier that is trained in a supervised fashion on the collected fall and nonfall data. However, several problems render these methods impractical. First, camera-based monitoring may trigger privacy concerns. Second, fall data collection using human subjects is difficult and costly, not to mention the impossible ask of the elderly repeating simulated falls for data collection. In this article, we propose a new fall detection approach to overcome these problems 1) using a palm-size mmWave radar sensor to monitor the elderly, that is highly sensitive to motion while protecting privacy and 2) using a semisupervised anomaly detection approach to circumvent the fall data collection. Further hardware engineering and more training data from people with different body figures could make the proposed fall detection solution even more practical. Elderly fall prevention and detection becomes extremely crucial with the fast aging population globally. In this article, we propose mmFall , a novel fall detection system, which comprises 1) the emerging millimeter-wave (mmWave) radar sensor to collect the human body’s point cloud along with the body centroid and 2) a hybrid variational recurrent neural network (RNN) autoencoder (HVRAE) to compute the anomaly level of the body motion based on the acquired point cloud. A fall is detected when the spike in anomaly level and the drop in centroid height occur simultaneously. The mmWave radar sensor offers privacy-compliance and high sensitivity to motion, over the traditional sensing modalities. However, 1) randomness in radar point cloud and 2) difficulties in fall collection/labeling in the traditional supervised fall detection approaches are the two major challenges. To overcome the randomness in radar data, the proposed HVRAE uses variational inference, a generative approach rather than a discriminative approach, to infer the posterior probability of the body’s latent motion state every frame, followed by a RNN to summarize the temporal features over multiple frames. Moreover, to circumvent the difficulties in fall data collection/labeling, the HVRAE is built upon an autoencoder architecture in a semisupervised approach, which is only trained on the normal activities of daily living (ADL). In the inference stage, the HVRAE will generate a spike in the anomaly level once an abnormal motion, such as fall, occurs. During the experiment, 1 we implemented the HVRAE along with two other baselines, and tested on the data set collected in an apartment. The receiver operating characteristic (ROC) curve indicates that our proposed model outperforms baselines and achieves 98% detection out of 50 falls at the expense of just 2 false alarms. Note to Practitioners —Traditional nonwearable fall detection approaches typically make use of a vision-based sensor, such as camera, to monitor and detect fall using a classifier that is trained in a supervised fashion on the collected fall and nonfall data. However, several problems render these methods impractical. First, camera-based monitoring may trigger privacy concerns. Second, fall data collection using human subjects is difficult and costly, not to mention the impossible ask of the elderly repeating simulated falls for data collection. In this article, we propose a new fall detection approach to overcome these problems 1) using a palm-size mmWave radar sensor to monitor the elderly, that is highly sensitive to motion while protecting privacy and 2) using a semisupervised anomaly detection approach to circumvent the fall data collection. Further hardware engineering and more training data from people with different body figures could make the proposed fall detection solution even more practical.
Author	Sengupta, Arindam Cao, Siyang Jin, Feng
Author_xml	– sequence: 1 givenname: Feng orcidid: 0000-0002-2985-3328 surname: Jin fullname: Jin, Feng email: fengjin@email.arizona.edu organization: Department of Electrical and Computer Engineering, The University of Arizona, Tucson, AZ, USA – sequence: 2 givenname: Arindam orcidid: 0000-0002-6563-9679 surname: Sengupta fullname: Sengupta, Arindam email: sengupta@email.arizona.edu organization: Department of Electrical and Computer Engineering, The University of Arizona, Tucson, AZ, USA – sequence: 3 givenname: Siyang orcidid: 0000-0001-9593-265X surname: Cao fullname: Cao, Siyang email: caos@email.arizona.edu organization: Department of Electrical and Computer Engineering, The University of Arizona, Tucson, AZ, USA
BookMark	eNp9kE1PAjEQhhuDiYj-AOOliefFfm_rjSCICdEEAY-b0m1NyX5gu5jw790V4sGDc5iZw_tM3nkvQa-qKwvADUZDjJG6X47eJkOCCBpSxAjm8gz0MecyoamkvW5nPOGK8wtwGeMWIcKkQn2wLsupLooH2HX4aBtrGl9XcBV99QFZ8gjL8l1_WbjQuQ5QVznUcHbYBJ_DtQ5ed2pdwMXLCxztm3pSmTq34QqcO11Ee32aA7CaTpbjWTJ_fXoej-aJIYo2CWNCcaMEpQaxDZJUyHwj8lw6QSXCSjmRktRx6wwRbaUul-0_zpKUpYoaOgB3x7u7UH_ubWyybb0PraGYEcFSRhiitFWlR5UJdYzBusz45sd5E7QvMoyyLsSsCzHrQsxOIbYk_kPugi91OPzL3B4Zb6391SuKuKKYfgNNDHvy
CODEN	ITASC7
CitedBy_id	crossref_primary_10_1109_JSEN_2024_3355421 crossref_primary_10_1109_JSEN_2024_3458068 crossref_primary_10_3390_s24020648 crossref_primary_10_1109_COMST_2022_3177305 crossref_primary_10_1109_JSAC_2024_3423629 crossref_primary_10_1109_JIOT_2023_3237494 crossref_primary_10_1109_JSEN_2023_3348199 crossref_primary_10_1109_JIOT_2022_3175894 crossref_primary_10_1016_j_bspc_2022_103741 crossref_primary_10_1109_JIOT_2024_3421336 crossref_primary_10_1109_ACCESS_2022_3211673 crossref_primary_10_1145_3749500 crossref_primary_10_1007_s42979_023_02480_y crossref_primary_10_3390_s23135810 crossref_primary_10_1145_3749471 crossref_primary_10_1109_JSEN_2024_3452110 crossref_primary_10_1109_TMC_2023_3344125 crossref_primary_10_1109_TMC_2025_3539985 crossref_primary_10_1007_s11042_024_19830_4 crossref_primary_10_1109_COMST_2024_3409556 crossref_primary_10_1088_1361_6501_ad7b60 crossref_primary_10_1007_s12530_024_09570_z crossref_primary_10_3390_s24186074 crossref_primary_10_1016_j_mlwa_2025_100655 crossref_primary_10_1109_ACCESS_2022_3190355 crossref_primary_10_1109_MRA_2024_3352851 crossref_primary_10_1016_j_engappai_2023_106939 crossref_primary_10_1109_JSEN_2021_3111187 crossref_primary_10_1109_TIM_2025_3550240 crossref_primary_10_1109_TNSRE_2024_3379453 crossref_primary_10_1109_JSEN_2025_3530007 crossref_primary_10_3390_s23115031 crossref_primary_10_3390_s24010268 crossref_primary_10_1109_LSENS_2025_3560919 crossref_primary_10_1109_COMST_2024_3398004 crossref_primary_10_1007_s11042_023_15952_3 crossref_primary_10_1109_JIOT_2023_3301887 crossref_primary_10_3103_S0146411624700597 crossref_primary_10_3390_s24165450 crossref_primary_10_1109_LGRS_2024_3413962 crossref_primary_10_1109_TIM_2024_3450071 crossref_primary_10_1109_JSEN_2024_3352425 crossref_primary_10_1109_JSEN_2024_3448622 crossref_primary_10_1109_JSEN_2024_3483835 crossref_primary_10_1109_JSEN_2024_3407962 crossref_primary_10_1109_TMC_2023_3291882 crossref_primary_10_1109_TMC_2025_3546757 crossref_primary_10_1145_3729465 crossref_primary_10_1109_JSEN_2022_3177173 crossref_primary_10_3390_rs15051254 crossref_primary_10_32604_cmc_2023_045008 crossref_primary_10_3390_bdcc7020099 crossref_primary_10_3390_app15158381 crossref_primary_10_1109_TBME_2025_3548092 crossref_primary_10_1109_JBHI_2022_3171554
Cites_doi	10.1007/978-3-319-55077-0_47 10.1016/j.jsr.2016.05.001 10.1117/1.2819119 10.1109/JSEN.2020.2991741 10.1007/s41666-019-00061-4 10.1109/LRA.2018.2801475 10.18356/13bf5476-en 10.1109/TAES.2019.2910980 10.1109/TNSRE.2014.2357806 10.1109/TBME.2019.2893528 10.1080/17483107.2019.1604831 10.1109/VCIP47243.2019.8965661 10.1080/01621459.2017.1285773 10.1145/3264947 10.1109/72.279181 10.1109/JBHI.2014.2319372 10.1109/ICMLA.2019.00279 10.1109/WiMOB.2015.7347965 10.1109/LSENS.2018.2889060 10.1145/1541880.1541882 10.1109/SMC.2019.8914303 10.3115/v1/d14-1179 10.1109/JSEN.2020.2967100 10.1109/MSP.2015.2502784 10.1109/JSEN.2016.2628099 10.24963/ijcai.2019/378 10.1145/2816795.2818072 10.1109/ACCESS.2019.2922708 10.1109/TBME.2012.2228262 10.1016/j.inffus.2017.12.007 10.3390/s19173720 10.1109/MSP.2019.2911722 10.1109/TBME.2014.2315784 10.1109/IEEE-IWS.2019.8804036 10.1007/978-3-319-33353-3_1 10.1561/9781680836233 10.1109/TAES.2017.2740098 10.1109/TBME.2014.2367038 10.1109/RADAR.2019.8835656 10.1109/MSP.2018.2890128 10.1109/TBME.2012.2186449 10.1109/TAES.2018.2799758 10.1007/s11042-015-2513-9 10.1162/neco.1997.9.8.1735 10.1109/MFI.2017.8170428 10.1109/ACCESS.2019.2907925
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D
DOI	10.1109/TASE.2020.3042158
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-3783
EndPage	1257
ExternalDocumentID	10_1109_TASE_2020_3042158 9305931
Genre	orig-research
GrantInformation_xml	– fundername: The University of Arizona. funderid: 10.13039/100007899
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c293t-44695c9633c04b08368db6dd8f6380199f6727f5efc266667fd8783fe274793c3
IEDL.DBID	RIE
ISICitedReferencesCount	70
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000778949400056&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1545-5955
IngestDate	Sun Jun 29 12:34:30 EDT 2025 Tue Nov 18 22:31:16 EST 2025 Sat Nov 29 04:12:47 EST 2025 Wed Aug 27 02:40:50 EDT 2025
IsPeerReviewed	false
IsScholarly	true
Issue	2
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c293t-44695c9633c04b08368db6dd8f6380199f6727f5efc266667fd8783fe274793c3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-9593-265X 0000-0002-2985-3328 0000-0002-6563-9679
PQID	2647424033
PQPubID	27623
PageCount	13
ParticipantIDs	proquest_journals_2647424033 ieee_primary_9305931 crossref_citationtrail_10_1109_TASE_2020_3042158 crossref_primary_10_1109_TASE_2020_3042158
PublicationCentury	2000
PublicationDate	2022-04-01
PublicationDateYYYYMMDD	2022-04-01
PublicationDate_xml	– month: 04 year: 2022 text: 2022-04-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on automation science and engineering
PublicationTitleAbbrev	TASE
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref57 ref12 ref56 ref15 ref59 ref14 ref53 ref11 ref55 ref10 Fabius (ref43) 2014 ref17 ref16 ref19 ref18 Blackman (ref49) 1986 (ref46) 2015 ref51 ref50 ref45 ref48 ref41 (ref62) 2020 ref8 ref7 Braei (ref34) 2020 ref9 Chung (ref44) 2015 (ref2) 2008 ref4 ref5 ref40 (ref61) 2020 ref37 ref36 ref31 ref30 ref33 ref32 ref1 ref39 ref38 Chalapathy (ref35) 2019 Haykin (ref52) 2011 Rezende (ref54) ref24 ref23 ref26 ref25 ref20 ref63 ref22 ref21 ref28 ref27 Dai (ref58) (ref6) 2017 ref29 (ref60) 2019 (ref3) 2018 Kingma (ref42) 2013 (ref47) 2018
References_xml	– start-page: 3079 volume-title: Proc. Adv. Neural Inf. Process. Syst. (NIPS) ident: ref58 article-title: Semi-supervised sequence learning – ident: ref40 doi: 10.1007/978-3-319-55077-0_47 – volume-title: Google LLC Request for Waiver Part 15 for Project Soli year: 2018 ident: ref47 – volume-title: Overview of Traffic Monitoring for 18xx or 68xx year: 2020 ident: ref61 – volume-title: Neural Networks and Learning Machines year: 2011 ident: ref52 – ident: ref4 doi: 10.1016/j.jsr.2016.05.001 – ident: ref50 doi: 10.1117/1.2819119 – ident: ref31 doi: 10.1109/JSEN.2020.2991741 – ident: ref36 doi: 10.1007/s41666-019-00061-4 – ident: ref45 doi: 10.1109/LRA.2018.2801475 – ident: ref1 doi: 10.18356/13bf5476-en – ident: ref27 doi: 10.1109/TAES.2019.2910980 – ident: ref7 doi: 10.1109/TNSRE.2014.2357806 – start-page: II–1278 volume-title: Proc. 31st Int. Conf. Mach. Learn. (ICML) ident: ref54 article-title: Stochastic backpropagation and approximate inference in deep generative models – ident: ref22 doi: 10.1109/TBME.2019.2893528 – ident: ref39 doi: 10.1080/17483107.2019.1604831 – ident: ref32 doi: 10.1109/VCIP47243.2019.8965661 – ident: ref51 doi: 10.1080/01621459.2017.1285773 – ident: ref28 doi: 10.1145/3264947 – ident: ref57 doi: 10.1109/72.279181 – ident: ref11 doi: 10.1109/JBHI.2014.2319372 – ident: ref23 doi: 10.1109/ICMLA.2019.00279 – ident: ref13 doi: 10.1109/WiMOB.2015.7347965 – ident: ref30 doi: 10.1109/LSENS.2018.2889060 – ident: ref33 doi: 10.1145/1541880.1541882 – ident: ref21 doi: 10.1109/SMC.2019.8914303 – ident: ref56 doi: 10.3115/v1/d14-1179 – ident: ref25 doi: 10.1109/JSEN.2020.2967100 – ident: ref16 doi: 10.1109/MSP.2015.2502784 – ident: ref5 doi: 10.1109/JSEN.2016.2628099 – ident: ref59 doi: 10.24963/ijcai.2019/378 – volume-title: arXiv:1901.03407 year: 2019 ident: ref35 article-title: Deep learning for anomaly detection: A survey – ident: ref63 doi: 10.1145/2816795.2818072 – ident: ref15 doi: 10.1109/ACCESS.2019.2922708 – ident: ref10 doi: 10.1109/TBME.2012.2228262 – ident: ref41 doi: 10.1016/j.inffus.2017.12.007 – volume-title: arXiv:2004.00433 year: 2020 ident: ref34 article-title: Anomaly detection in univariate time-series: A survey on the state-of-the-art – volume-title: Radar Library year: 1986 ident: ref49 article-title: Multiple-target tracking with radar applications – ident: ref38 doi: 10.3390/s19173720 – volume-title: arXiv:1412.6581 year: 2014 ident: ref43 article-title: Variational recurrent auto-encoders – ident: ref48 doi: 10.1109/MSP.2019.2911722 – volume-title: Operation Radar Services 76–81 GHz Band year: 2015 ident: ref46 – ident: ref8 doi: 10.1109/TBME.2014.2315784 – ident: ref26 doi: 10.1109/IEEE-IWS.2019.8804036 – volume-title: WHO Global Report on Falls Prevention in Older Age year: 2008 ident: ref2 – ident: ref9 doi: 10.1007/978-3-319-33353-3_1 – ident: ref53 doi: 10.1561/9781680836233 – ident: ref24 doi: 10.1109/TAES.2017.2740098 – ident: ref19 doi: 10.1109/TBME.2014.2367038 – volume-title: xWR1843 Evaluation Module (xWR1843BOOST) Single-Chip mmWave Sensing Solution year: 2019 ident: ref60 – volume-title: Programming Chirp Parameters in TI Radar Devices year: 2020 ident: ref62 – ident: ref29 doi: 10.1109/RADAR.2019.8835656 – ident: ref17 doi: 10.1109/MSP.2018.2890128 – ident: ref12 doi: 10.1109/TBME.2012.2186449 – ident: ref18 doi: 10.1109/TAES.2018.2799758 – ident: ref37 doi: 10.1007/s11042-015-2513-9 – ident: ref55 doi: 10.1162/neco.1997.9.8.1735 – volume-title: arXiv:1312.6114 year: 2013 ident: ref42 article-title: Auto-encoding variational Bayes – volume-title: Falls. World Health Orgnazation year: 2018 ident: ref3 – volume-title: arXiv:1506.02216 year: 2015 ident: ref44 article-title: A recurrent latent variable model for sequential data – volume-title: mmWave Radar Sensors in Robotics Applications year: 2017 ident: ref6 – ident: ref14 doi: 10.1109/MFI.2017.8170428 – ident: ref20 doi: 10.1109/ACCESS.2019.2907925
SSID	ssj0024890
Score	2.5815156
Snippet	Elderly fall prevention and detection becomes extremely crucial with the fast aging population globally. In this article, we propose mmFall , a novel fall...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1245
SubjectTerms	Activities of daily living Anomalies Anomaly detection Cameras Centroids Conditional probability Data collection Doppler radar Fall detection False alarms Inference Labelling millimeter wave (mmWave) radar Millimeter waves Older people Privacy Radar Radar antennas Radar data Radar detection Radar measurements Randomness recurrent autoencoder (RAE) Recurrent neural networks semisupervised learning Senior citizens Sensors Three-dimensional displays variational autoencoder
Title	mmFall: Fall Detection Using 4-D mmWave Radar and a Hybrid Variational RNN AutoEncoder
URI	https://ieeexplore.ieee.org/document/9305931 https://www.proquest.com/docview/2647424033
Volume	19
WOSCitedRecordID	wos000778949400056&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: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 1558-3783 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024890 issn: 1545-5955 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF5q8aAHX1WsVtmDJzE2yWaTrLdiW3qQILXW3kKyDxCaVNK04L93Z5vWgiJ4CTnsQpjZycw3O98MQjfSOA7lQOaeW55HpcW40JiHp46rGPOUbYjCT0EUhZMJe66huw0XRkppis_kPbyau3wx4wtIlbUZgQF0GuvsBEGw4mp999ULTT4FIgKLMkqrG0zHZu1R56WnkaCrAao-og5Md9_yQWaoyo8_sXEv_cP_fdgROqjCSNxZ6f0Y1WR-gva3mgs20DjL-sl0-oDhibuyNEVXOTZFAtizujjL3pKlxMNEJAVOcoETPPgEBhceawRdZQnxMIpwZ1HOejnQ34tT9NrvjR4HVjVFweLalZda_j6jXNsZ4baXQjPqUKS-EKHSpqcDPKbgMlZRqbh21r4fKBEGIVES8CojnJyhej7L5TnCVChHSapS5nLt_JI0IVRQn0jqpiyQbhPZa7nGvGoxDpMuprGBGjaLQRUxqCKuVNFEt5stH6v-Gn8tboDsNwsrsTdRa628uLLAeawDPY36PZuQi993XaI9F6gMpgqnheplsZBXaJcvy_d5cW0O1xczksjb
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB6kCurBVxWrVffgSYwm2Wya9Va0pWINovVxC8k-QGhTadOC_96dbayCIngJOexCmNnJzDc73wzAsbKOQ3uYuRdOEDDlcCEN5hGZ52vOA-1aonC3EcfRywu_W4DTORdGKWWLz9QZvtq7fDkUE0yVnXOKA-gM1llkQeB7M7bWV2e9yGZUMCZwGGesvMP0XH7eaz60DBb0DUQ1h9TD-e7fvJAdq_LjX2wdTHv9f5-2AWtlIEmaM81vwoLKt2D1W3vBKjwNBu20378g-CRXqrBlVzmxZQIkcK7IYPCcThW5T2U6ImkuSUo678jhIk8GQ5d5QnIfx6Q5KYatHAnwo214bLd6lx2nnKPgCOPMC6OBkDNhLI0KN8iwHXUks1DKSBvjMyEe13gdq5nSwrjrMGxoGTUiqhUiVk4F3YFKPszVLhAmtacV0xn3hXF_aZZSJllIFfMz3lB-DdxPuSaibDKOsy76iQUbLk9QFQmqIilVUYOT-Za3WYeNvxZXUfbzhaXYa1D_VF5S2uA4MaGewf2BS-ne77uOYLnTu-0m3ev4Zh9WfCQ22JqcOlSK0UQdwJKYFq_j0aE9aB_UF8wi
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=mmFall%3A+Fall+Detection+Using+4-D+mmWave+Radar+and+a+Hybrid+Variational+RNN+AutoEncoder&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Jin%2C+Feng&rft.au=Sengupta%2C+Arindam&rft.au=Cao%2C+Siyang&rft.date=2022-04-01&rft.issn=1545-5955&rft.eissn=1558-3783&rft.volume=19&rft.issue=2&rft.spage=1245&rft.epage=1257&rft_id=info:doi/10.1109%2FTASE.2020.3042158&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TASE_2020_3042158
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon