On-Device Reliability Assessment and Prediction of Missing Photoplethysmographic Data Using Deep Neural Networks

Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and mu...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on biomedical circuits and systems Ročník 14; číslo 6; s. 1323 - 1332
Hlavní autori:	Singha Roy, Monalisa, Roy, Biplab, Gupta, Rajarshi, Das Sharma, Kaushik
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 01.12.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Annotations Artificial neural networks Convolutional neural network Convolutional neural networks Latency Long short term memory Loosening Missing data Model accuracy Multilayer perceptrons Network latency Network reliability Neural networks Noise reduction on-device measurement Photoplethsymography photoplethysmogram (PPG) Prediction models prediction of missing data Predictive models Quality assessment Quality control Random access memory Reliability Reliability analysis reliability assessment Root-mean-square errors Segments stack denoising autoencoder
ISSN:	1932-4545, 1940-9990, 1940-9990
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers' data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts' annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet.
AbstractList	Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers' data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts' annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet.Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers' data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts' annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet. Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers' data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts' annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet.
Author	Das Sharma, Kaushik Gupta, Rajarshi Singha Roy, Monalisa Roy, Biplab
Author_xml	– sequence: 1 givenname: Monalisa surname: Singha Roy fullname: Singha Roy, Monalisa email: monalisa_sr03@yahoo.co, in organization: Electrical Engineering Section, Department of Applied Physics, University of Calcutta, Kolkata, India – sequence: 2 givenname: Biplab surname: Roy fullname: Roy, Biplab email: biplab.roy@nitmas.edu.in organization: Electronics & Communication Engineering Department, NITMAS, West Bengal, India – sequence: 3 givenname: Rajarshi orcidid: 0000-0001-5964-7683 surname: Gupta fullname: Gupta, Rajarshi email: rgaphy@caluniv.ac.in organization: Electrical Engineering Section, Department of Applied Physics, University of Calcutta, Kolkata, India – sequence: 4 givenname: Kaushik orcidid: 0000-0002-0176-709X surname: Das Sharma fullname: Das Sharma, Kaushik email: kdsaphy@caluniv.ac.in organization: Electrical Engineering Section, Department of Applied Physics, University of Calcutta, Kolkata, India
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33026985$$D View this record in MEDLINE/PubMed
BookMark	eNp9kU1vEzEQhi1URD_gD4CELHHhssGf2fUxJBSQCq2gPVuOd7Zx2bUX20uVf4_TpBx64DIzkp9nZM17io588IDQa0pmlBL14frjcvFzxggjM05Yo7h8hk6oEqRSSpGj3cxZJaSQx-g0pTtC5Jwp9gId88LPVSNP0HjpqxX8cRbwD-idWbve5S1epAQpDeAzNr7FVxFaZ7MLHocOf3MpOX-LrzYhh7GHvNmmIdxGM26cxSuTDb55AFYAI_4OUzR9afk-xF_pJXremT7Bq0M_Qzfnn66XX6qLy89fl4uLynJJc8WBda2B2ghCJSir1oYCaRgnpjZGgDC8q6G8NZKLllMDa2ot7RpCrCiVn6H3-71jDL8nSFkPLlnoe-MhTEkzIRQTdU1lQd89Qe_CFH35XaGaWgjCSVOotwdqWg_Q6jG6wcStfrxlAZo9YGNIKUKnrctmd7Qcjes1JXoXm36ITe9i04fYisqeqI_b_yu92UsOAP4JitG5ZIr_BfhMo2g
CODEN	ITBCCW
CitedBy_id	crossref_primary_10_1109_TBCAS_2021_3134043 crossref_primary_10_1109_JBHI_2023_3289548 crossref_primary_10_1007_s00034_024_02658_6 crossref_primary_10_1007_s13534_022_00248_6 crossref_primary_10_3390_bioengineering11040365 crossref_primary_10_1109_TIM_2024_3450120 crossref_primary_10_1109_TBCAS_2021_3065824 crossref_primary_10_1109_TBCAS_2020_3036081 crossref_primary_10_1109_TCBB_2022_3205064 crossref_primary_10_1080_10255842_2024_2359041 crossref_primary_10_1088_1361_6501_ac2d5b crossref_primary_10_1016_j_ress_2023_109378 crossref_primary_10_3390_en18082019 crossref_primary_10_1155_2021_9925033 crossref_primary_10_1109_TIM_2021_3102737 crossref_primary_10_1109_TIM_2022_3197781 crossref_primary_10_1109_TIM_2022_3212750
Cites_doi	10.1186/1687-6180-2012-173 10.1088/0967-3334/33/10/1617 10.1088/0967-3334/32/6/004 10.1109/JBHI.2014.2361654 10.1109/TBCAS.2012.2200677 10.1016/j.bspc.2019.101676 10.1109/JSEN.2019.2917157 10.3390/bioengineering3040021 10.1109/TIM.2018.2829488 10.1109/TCYB.2016.2536638 10.1109/TBCAS.2018.2839184 10.1016/j.bspc.2019.101747 10.1109/JBHI.2014.2338351 10.1109/TBCAS.2019.2956948 10.1109/TIM.2020.2971132 10.1109/TCSII.2019.2891636 10.1109/TBCAS.2017.2649940 10.1088/0967-3334/33/9/1491 10.1109/TBCAS.2011.2164247 10.3390/e21030274 10.1109/TBCAS.2011.2157822 10.1016/j.jocn.2019.03.003 10.1161/STROKEAHA.113.003321 10.1109/TBCAS.2011.2167717 10.1088/1361-6579/ab5b84 10.1088/0967-3334/28/3/R01 10.1109/TBCAS.2015.2477437 10.1088/0967-3334/32/3/008 10.1088/0967-3334/35/12/2543 10.1016/j.engappai.2014.05.014 10.1109/TBCAS.2019.2945114 10.1080/08037051.2018.1436400 10.1109/TBME.2009.2018297 10.1109/TBME.2012.2204882
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID	97E RIA RIE AAYXX CITATION NPM 7QO 7SP 7TB 8FD FR3 L7M P64 7X8
DOI	10.1109/TBCAS.2020.3028935
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef PubMed Biotechnology Research Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database Advanced Technologies Database with Aerospace Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Biotechnology Research Abstracts Technology Research Database Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Biotechnology Research Abstracts PubMed
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: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1940-9990
EndPage	1332
ExternalDocumentID	33026985 10_1109_TBCAS_2020_3028935 9216529
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: University Grants Commission, India grantid: 029/17-18/1702
GroupedDBID	--- 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS AAYXX CITATION NPM RIG 7QO 7SP 7TB 8FD FR3 L7M P64 7X8
ID	FETCH-LOGICAL-c351t-3e2fdae7a4015e9c9ba1e08230a7aa4e4a3f7e0158534d31aeb1cc1f800c4f803
IEDL.DBID	RIE
ISICitedReferencesCount	19
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000616310900016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1932-4545 1940-9990
IngestDate	Sun Sep 28 08:34:39 EDT 2025 Mon Jun 30 08:37:34 EDT 2025 Thu Apr 03 07:08:31 EDT 2025 Sat Nov 29 05:32:53 EST 2025 Tue Nov 18 22:23:12 EST 2025 Wed Aug 27 05:45:33 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	6
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-c351t-3e2fdae7a4015e9c9ba1e08230a7aa4e4a3f7e0158534d31aeb1cc1f800c4f803
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-0176-709X 0000-0001-5964-7683
PMID	33026985
PQID	2487440308
PQPubID	85510
PageCount	10
ParticipantIDs	pubmed_primary_33026985 crossref_primary_10_1109_TBCAS_2020_3028935 proquest_journals_2487440308 crossref_citationtrail_10_1109_TBCAS_2020_3028935 proquest_miscellaneous_2449247715 ieee_primary_9216529
PublicationCentury	2000
PublicationDate	2020-12-01
PublicationDateYYYYMMDD	2020-12-01
PublicationDate_xml	– month: 12 year: 2020 text: 2020-12-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on biomedical circuits and systems
PublicationTitleAbbrev	TBCAS
PublicationTitleAlternate	IEEE Trans Biomed Circuits Syst
PublicationYear	2020
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	sullivan (ref33) 2010; 37 huang (ref40) 2018; 18 ref13 (ref43) 0 ref12 ref15 ref14 ref31 ref30 ref11 ref10 ref2 ref1 ref39 ref17 ref38 ref16 ref19 ref18 petrolis (ref32) 2010; 37 ref24 ref23 singha roy (ref34) 2019 ref26 ref25 ref20 weng (ref41) 2005 ref22 ref21 (ref36) 0 singha roy (ref37) 2018; 67 ref28 ref27 (ref35) 2010 ref29 ref8 ref7 ref9 ref4 (ref42) 1988 ref3 ref6 ref5
References_xml	– ident: ref30 doi: 10.1186/1687-6180-2012-173 – year: 0 ident: ref36 article-title: Easy Pulse PPG sensor – ident: ref14 doi: 10.1088/0967-3334/33/10/1617 – ident: ref29 doi: 10.1088/0967-3334/32/6/004 – ident: ref10 doi: 10.1109/JBHI.2014.2361654 – ident: ref3 doi: 10.1109/TBCAS.2012.2200677 – ident: ref38 doi: 10.1016/j.bspc.2019.101676 – ident: ref11 doi: 10.1109/JSEN.2019.2917157 – ident: ref15 doi: 10.3390/bioengineering3040021 – year: 2010 ident: ref35 article-title: Mind the Gap - The PhysioNet Computing in Cardiology Challenge 2010 – volume: 67 start-page: 2820 year: 2018 ident: ref37 article-title: Improving photoplethysmographic measurements under motion artifacts using artificial neural network for personal healthcare publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2018.2829488 – ident: ref39 doi: 10.1109/TCYB.2016.2536638 – ident: ref7 doi: 10.1109/TBCAS.2018.2839184 – year: 0 ident: ref43 article-title: Biopac Systems USA – ident: ref27 doi: 10.1016/j.bspc.2019.101747 – ident: ref16 doi: 10.1109/JBHI.2014.2338351 – ident: ref2 doi: 10.1109/TBCAS.2019.2956948 – ident: ref22 doi: 10.1109/TIM.2020.2971132 – ident: ref21 doi: 10.1109/TCSII.2019.2891636 – ident: ref8 doi: 10.1109/TBCAS.2017.2649940 – ident: ref18 doi: 10.1088/0967-3334/33/9/1491 – ident: ref5 doi: 10.1109/TBCAS.2011.2164247 – ident: ref31 doi: 10.3390/e21030274 – ident: ref13 doi: 10.1109/TBCAS.2011.2157822 – ident: ref24 doi: 10.1016/j.jocn.2019.03.003 – start-page: 236 year: 2019 ident: ref34 article-title: Reconstruction of corrupted and missing segments from photoplethysmographicdata using recurrent neural network publication-title: Proc IEEE TENSYMP – year: 1988 ident: ref42 publication-title: Optimum Signal Processing An Introduction – ident: ref23 doi: 10.1161/STROKEAHA.113.003321 – volume: 37 start-page: 317 year: 2010 ident: ref33 article-title: Reconstruction of missing physiological signals using artificial neural networks publication-title: Proc Comput Cardiol – ident: ref9 doi: 10.1109/TBCAS.2011.2167717 – ident: ref20 doi: 10.1088/1361-6579/ab5b84 – volume: 37 start-page: 437 year: 2010 ident: ref32 article-title: Principal component analysis based method for reconstruction of fragments of corrupted or lost signal in multilead data reflecting electrical heart activity and hemodynamics publication-title: Proc Comput Cardiol – ident: ref1 doi: 10.1088/0967-3334/28/3/R01 – ident: ref6 doi: 10.1109/TBCAS.2015.2477437 – ident: ref12 doi: 10.1088/0967-3334/32/3/008 – ident: ref19 doi: 10.1088/0967-3334/35/12/2543 – ident: ref28 doi: 10.1016/j.engappai.2014.05.014 – ident: ref4 doi: 10.1109/TBCAS.2019.2945114 – ident: ref25 doi: 10.1080/08037051.2018.1436400 – volume: 18 year: 2018 ident: ref40 article-title: A Deep CNN-LSTM model for particulate matter (Pm2.5) forecasting in smart cities publication-title: Sensors (Switzerland) – start-page: 41 year: 2005 ident: ref41 article-title: An improved pre-processing approach for photoplethysmographic signal publication-title: Proc IEEE Eng Med Biol 27th Annu Conf – ident: ref26 doi: 10.1109/TBME.2009.2018297 – ident: ref17 doi: 10.1109/TBME.2012.2204882
SSID	ssj0056292
Score	2.3649766
Snippet	Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1323
SubjectTerms	Annotations Artificial neural networks Convolutional neural network Convolutional neural networks Latency Long short term memory Loosening Missing data Model accuracy Multilayer perceptrons Network latency Network reliability Neural networks Noise reduction on-device measurement Photoplethsymography photoplethysmogram (PPG) Prediction models prediction of missing data Predictive models Quality assessment Quality control Random access memory Reliability Reliability analysis reliability assessment Root-mean-square errors Segments stack denoising autoencoder
Title	On-Device Reliability Assessment and Prediction of Missing Photoplethysmographic Data Using Deep Neural Networks
URI	https://ieeexplore.ieee.org/document/9216529 https://www.ncbi.nlm.nih.gov/pubmed/33026985 https://www.proquest.com/docview/2487440308 https://www.proquest.com/docview/2449247715
Volume	14
WOSCitedRecordID	wos000616310900016&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 Electronic Library (IEL) customDbUrl: eissn: 1940-9990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0056292 issn: 1932-4545 databaseCode: RIE dateStart: 20070101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9tAEB4F1EN7oEBacEujReJGXfzMsseUEPXQhkikVW7Wej0WSGBHiYPEv2dm_VAOpVIvlqV9eOVvdndmZ_YbgLMsSNPAU9odYqzZQMldrWTqStauU2lkbHm2__yU0-nlYqFmPfja3YVBRBt8ht_41frys9Js-KjsQgX-MA7UDuxIKeu7Wu2qS9u4TYDM-gjzeMftBRlPXcy_X41uyRQMyEJlx1rI6WrIjg-GilMob-1HNsHK67qm3XMm7_9vtPuw1-iWYlQLwwH0sDiEd1uMg31Y3hTuGHl1EByMXJN0P4tRx88pdJGJ2YrdNwyZKHPxi7ChxmJ2V1Ycbs7QPtZM1_dGjHWlhQ08EGPEpWC2DxrEtA4vX3-A35Pr-dUPt0m64Jow9is3xCDPNEpNhleMyqhU-2jdcVpqHWGkw1wildE-H2Whr2mxN8bPSfE0ET3Dj7BblAUeg0hJNeEjYW9ovEgaX0cmS_OUWjKtfB474Le_PjENIzknxnhIrGXiqcQilzBySYOcA-ddm2XNx_HP2n3GpavZQOLASYtw0kzZdRJEnAmA6XscOO2KabKxB0UXWG64TkT2qpQ-9XxUS0bXdytQn_7-zc_wlkdWR8KcwG612uAXeGOeqvv1akASvbgcWIl-AS-o8AI
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VggQ9lEeBbilgJG4QGjvOGh-XLlUR22UlFtRb5DgTUQmS1W4WiX_PjPNQD4DEJYrkR6x8Y3vGM_4G4GWh8lzF1kVjTB0bKGXkrMkjw9p1brxJA8_215mZz99eXtrFDrwe7sIgYgg-wzf8Gnz5Re23fFR2YpUcp8regJup1kq2t7X6dZc28pACmTUSZvJO-ysysT1ZvjudfCZjUJGNyq61hBPWkCWvxpaTKF_bkUKKlb9rm2HXObv7f-O9B_uddikmrTjchx2sHsDeNc7BA1h9qqIp8vogOBy5pen-JSYDQ6dwVSEWa3bgMGiiLsUFoUONxeJb3XDAOYP7o-W6vvJi6honQuiBmCKuBPN90CDmbYD55iF8OXu_PD2PurQLkU9S2UQJqrJwaByZXilab3MnMTjknHFOo3ZJaZDKaKfXRSIdLffey5JUT6_pmTyC3aqu8BBETsoJHwrHYx9r46XTvsjLnFoysXyZjkD2vz7zHSc5p8b4ngXbJLZZQC5j5LIOuRG8GtqsWkaOf9Y-YFyGmh0kIzjuEc66SbvJlOZcAEzgM4IXQzFNN_ahuArrLdfRZLEaI6nnx61kDH33AnX0528-h9vny4tZNvsw__gE7vAo27iYY9ht1lt8Crf8z-Zqs34W5Po3J0ryYQ
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=On-Device+Reliability+Assessment+and+Prediction+of+Missing+Photoplethysmographic+Data+Using+Deep+Neural+Networks&rft.jtitle=IEEE+transactions+on+biomedical+circuits+and+systems&rft.au=Singha+Roy%2C+Monalisa&rft.au=Roy%2C+Biplab&rft.au=Gupta%2C+Rajarshi&rft.au=Das+Sharma%2C+Kaushik&rft.date=2020-12-01&rft.eissn=1940-9990&rft.volume=14&rft.issue=6&rft.spage=1323&rft_id=info:doi/10.1109%2FTBCAS.2020.3028935&rft_id=info%3Apmid%2F33026985&rft.externalDocID=33026985
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4545&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4545&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4545&client=summon