Self-supervised autoencoder network for robust heart rate extraction from noisy photoplethysmogram: Applying blind source separation to biosignal analysis

Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photople...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine Vol. 199; p. 111319
Main Authors: Webster, Matthew B., Lee, Dongheon, Lee, Joonnyong
Format: Journal Article
Language:English
Published: United States Elsevier Ltd 01.12.2025
Subjects:
ISSN:0010-4825, 1879-0534, 1879-0534
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photoplethysmogram (PPG), enhancing heart rate (HR) detection in noisy PPG data. The MEAE is trained on PPG signals from a large open polysomnography database without any pre-processing or data selection. The trained network is then applied to a noisy PPG dataset collected during the daily activities of nine subjects and a surgical dataset comprising 4,681 patients. The extracted heartbeat-related source signal significantly improves HR detection as compared to the original PPG. The absence of pre-processing and the self-supervised nature of the proposed method, combined with its strong performance, highlight the potential of MEAE for BSS in biosignal analysis. •Biosignals are often difficult to analyze due to presence of unknown noises including motion artifacts.•Blind source separation via self-supervised autoencoder allows to separate out information from biosignals.•Blind source separation applied to noisy photoplethysmogram successfully isolated heartbeat related source.•Blind source separation without any directives (supervision in deep learning) can result in extraction of information present in the training data.•Analyses of large biosignal databases can benefit from self-supervised blind source separation due to the lack of pre-processing or data selection.
AbstractList Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photoplethysmogram (PPG), enhancing heart rate (HR) detection in noisy PPG data. The MEAE is trained on PPG signals from a large open polysomnography database without any pre-processing or data selection. The trained network is then applied to a noisy PPG dataset collected during the daily activities of nine subjects and a surgical dataset comprising 4,681 patients. The extracted heartbeat-related source signal significantly improves HR detection as compared to the original PPG. The absence of pre-processing and the self-supervised nature of the proposed method, combined with its strong performance, highlight the potential of MEAE for BSS in biosignal analysis.Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photoplethysmogram (PPG), enhancing heart rate (HR) detection in noisy PPG data. The MEAE is trained on PPG signals from a large open polysomnography database without any pre-processing or data selection. The trained network is then applied to a noisy PPG dataset collected during the daily activities of nine subjects and a surgical dataset comprising 4,681 patients. The extracted heartbeat-related source signal significantly improves HR detection as compared to the original PPG. The absence of pre-processing and the self-supervised nature of the proposed method, combined with its strong performance, highlight the potential of MEAE for BSS in biosignal analysis.
Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photoplethysmogram (PPG), enhancing heart rate (HR) detection in noisy PPG data. The MEAE is trained on PPG signals from a large open polysomnography database without any pre-processing or data selection. The trained network is then applied to a noisy PPG dataset collected during the daily activities of nine subjects and a surgical dataset comprising 4,681 patients. The extracted heartbeat-related source signal significantly improves HR detection as compared to the original PPG. The absence of pre-processing and the self-supervised nature of the proposed method, combined with its strong performance, highlight the potential of MEAE for BSS in biosignal analysis. •Biosignals are often difficult to analyze due to presence of unknown noises including motion artifacts.•Blind source separation via self-supervised autoencoder allows to separate out information from biosignals.•Blind source separation applied to noisy photoplethysmogram successfully isolated heartbeat related source.•Blind source separation without any directives (supervision in deep learning) can result in extraction of information present in the training data.•Analyses of large biosignal databases can benefit from self-supervised blind source separation due to the lack of pre-processing or data selection.
Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photoplethysmogram (PPG), enhancing heart rate (HR) detection in noisy PPG data. The MEAE is trained on PPG signals from a large open polysomnography database without any pre-processing or data selection. The trained network is then applied to a noisy PPG dataset collected during the daily activities of nine subjects and a surgical dataset comprising 4,681 patients. The extracted heartbeat-related source signal significantly improves HR detection as compared to the original PPG. The absence of pre-processing and the self-supervised nature of the proposed method, combined with its strong performance, highlight the potential of MEAE for BSS in biosignal analysis.
ArticleNumber 111319
Author Lee, Dongheon
Webster, Matthew B.
Lee, Joonnyong
Author_xml – sequence: 1
  givenname: Matthew B.
  surname: Webster
  fullname: Webster, Matthew B.
  organization: Mellowing Factory Co. Ltd., Seoul, Republic of Korea
– sequence: 2
  givenname: Dongheon
  orcidid: 0000-0002-3121-7099
  surname: Lee
  fullname: Lee, Dongheon
  organization: Chungnam National University Hospital, Daejeon, Republic of Korea
– sequence: 3
  givenname: Joonnyong
  orcidid: 0000-0002-3642-9891
  surname: Lee
  fullname: Lee, Joonnyong
  email: joonnyonglee@melab.snu.ac.kr
  organization: Mellowing Factory Co. Ltd., Seoul, Republic of Korea
BackLink https://www.ncbi.nlm.nih.gov/pubmed/41274114$$D View this record in MEDLINE/PubMed
BookMark eNqNkc1u1DAUhS1URKeFV0BesslgJ84fK0rFn1SJBbC2bOdmxlPHN9hOS16Fp8WjKSCx6ubezTlHOue7IGcePRBCOdtyxpvXh63BadYWJxi2JSvrLee84v0TsuFd2xesrsQZ2TDGWSG6sj4nFzEeGGOCVewZORe8bAXnYkN-fQU3FnGZIdzZCANVS0LwBgcI1EO6x3BLRww0oF5iontQIdGgElD4mYIyyaKnY8CJerRxpfMeE84O0n6NE-6Cmt7Qq3l2q_U7qp31A424BAM0wqxy0NGfkOYy0e68clTls0Ybn5Ono3IRXjz8S_L9w_tv15-Kmy8fP19f3RSmLLkodGta3mjBVTnk7rmXYnxsa6VACTCtalinWaMH3Qz9WI9atMBZr3ira2b6qrokr065c8AfC8QkJxsNOKc84BJllbequ6Yrmyx9-SBddJ5ezsFOKqzyz55Z0J0EJmCMAca_Es7kEZ08yH_o5BGdPKHL1ncnK-SudxaCjMZmEjDYACbJAe1jQt7-F2Ly5NYodwvr4yJ-A14OwUA
Cites_doi 10.1016/j.neucom.2014.08.092
10.1001/jamacardio.2018.0136
10.1007/BF02348427
10.1007/BF02345755
10.1109/TBME.2012.2208112
10.1038/s41597-022-01411-5
10.1109/JBHI.2018.2885139
10.1038/44565
10.1093/jamia/ocy064
10.1109/TIM.2011.2175832
10.1109/TIM.2018.2829488
10.1109/MEMB.2003.1213624
10.1109/TBME.2009.2039568
10.1016/j.artmed.2011.05.001
10.2174/157340312801215782
10.3390/s20113238
10.3390/electronics3020282
10.1088/0967-3334/28/3/R01
10.1186/s12938-018-0510-8
10.1109/TBME.2014.2359372
10.1378/chest.95.4.713
10.1016/S0893-6080(98)00140-3
10.3390/jpm7020003
10.1109/LSP.2015.2486681
10.1109/TIM.2008.2009136
10.1016/j.bspc.2006.01.001
10.1109/LSP.2015.2476667
10.1016/j.neucom.2025.131008
10.1109/TBME.2012.2186448
ContentType Journal Article
Copyright 2025 Elsevier Ltd
2025
Copyright © 2025. Published by Elsevier Ltd.
Copyright_xml – notice: 2025 Elsevier Ltd
– notice: 2025
– notice: Copyright © 2025. Published by Elsevier Ltd.
DBID AAYXX
CITATION
NPM
7X8
DOI 10.1016/j.compbiomed.2025.111319
DatabaseName CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic


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: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1879-0534
ExternalDocumentID 41274114
10_1016_j_compbiomed_2025_111319
S0010482525016737
Genre Journal Article
GroupedDBID ---
--K
--M
--Z
-~X
.1-
.55
.DC
.FO
.GJ
.~1
0R~
1B1
1P~
1RT
1~.
1~5
29F
4.4
457
4G.
53G
5GY
5VS
7-5
71M
77I
7RV
7X7
88E
8AO
8FE
8FG
8FH
8FI
8FJ
8G5
8P~
9DU
9JN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABFNM
ABJNI
ABMAC
ABMZM
ABOCM
ABUWG
ABWVN
ABXDB
ACDAQ
ACGFS
ACIEU
ACIUM
ACIWK
ACLOT
ACNNM
ACPRK
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADJOM
ADMUD
ADNMO
AEBSH
AEIPS
AEKER
AENEX
AEUPX
AEVXI
AFFHD
AFJKZ
AFKRA
AFPUW
AFRAH
AFRHN
AFTJW
AFXIZ
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHMBA
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJRQY
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ANZVX
AOUOD
APXCP
ARAPS
ASPBG
AVWKF
AXJTR
AZFZN
AZQEC
BBNVY
BENPR
BGLVJ
BHPHI
BKEYQ
BKOJK
BLXMC
BNPGV
BPHCQ
BVXVI
CCPQU
CS3
DU5
DWQXO
EBS
EFJIC
EFKBS
EFLBG
EJD
EMOBN
EO8
EO9
EP2
EP3
EX3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
FYUFA
G-2
G-Q
GBLVA
GBOLZ
GNUQQ
GUQSH
HCIFZ
HLZ
HMCUK
HMK
HMO
HVGLF
HZ~
IHE
J1W
K6V
K7-
KOM
LK8
LX9
M1P
M29
M2O
M41
M7P
MO0
N9A
NAPCQ
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
P62
PC.
PHGZM
PHGZT
PJZUB
PPXIY
PQGLB
PQQKQ
PROAC
PSQYO
Q38
R2-
ROL
RPZ
RXW
SAE
SBC
SCC
SDF
SDG
SDP
SEL
SES
SEW
SPC
SPCBC
SSH
SSV
SSZ
SV3
T5K
TAE
UAP
UKHRP
WOW
WUQ
X7M
XPP
Z5R
ZGI
~G-
~HD
AAYXX
CITATION
NPM
7X8
ID FETCH-LOGICAL-c2214-b7c716b41a2d879741a01f75aaea4ec7a608b06bdb6d9f5fb47e109a17b50c933
ISSN 0010-4825
1879-0534
IngestDate Mon Nov 24 00:27:30 EST 2025
Mon Nov 24 02:18:52 EST 2025
Thu Nov 27 01:06:00 EST 2025
Sat Nov 29 17:08:09 EST 2025
Sat Nov 29 06:57:07 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Biosignal processing
Heart rate detection
Blind source separation
Self-supervised learning
Photoplethysmogram
Denoising
Language English
License Copyright © 2025. Published by Elsevier Ltd.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c2214-b7c716b41a2d879741a01f75aaea4ec7a608b06bdb6d9f5fb47e109a17b50c933
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-3121-7099
0000-0002-3642-9891
PMID 41274114
PQID 3274586826
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3274586826
pubmed_primary_41274114
crossref_primary_10_1016_j_compbiomed_2025_111319
elsevier_sciencedirect_doi_10_1016_j_compbiomed_2025_111319
elsevier_clinicalkey_doi_10_1016_j_compbiomed_2025_111319
PublicationCentury 2000
PublicationDate December 2025
PublicationDateYYYYMMDD 2025-12-01
PublicationDate_xml – month: 12
  year: 2025
  text: December 2025
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Computers in biology and medicine
PublicationTitleAlternate Comput Biol Med
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Tison, Sanchez, Ballinger, Singh, Olgin, Pletcher, Vittinghoff, Lee, Fan, Gladstone, Mikell, Sohoni, Hsieh, Marcus (b8) 2018; 3
Wang, Zhou, Xing, Zhou (b17) 2018; 2018
Lee, Park, Yoon, Yang, Park, Jung (b41) 2022; 9
Kurylyak, Barbé, Lamonaca, Grimaldi, Van Moer (b30) 2013
Raghuram, Venu Madhav, Hari Krishna, Ashoka Reddy (b27) 2010
Lee, Reyes, McManus, Maitas, Chon (b12) 2013; 60
Lee, Sohn, Park, Yang, Lee, Kim (b14) 2018; 17
Brakel, Bengio (b38) 2017
Monte-Moreno (b15) 2011; 53
Elgendi (b18) 2012; 8
Terry (b31) 2005
Hyvärinen, Oja (b35) 1996; Vol. 9
Lee, Sun, Yang, Sohn, Park, Lee, Kim (b5) 2019; 23
Lee, Seung (b34) 1999; 401
Tremper (b9) 1989; 95
Shcherbina, Mattsson, Waggott, Salisbury, Christle, Hastie, Wheeler, Ashley (b19) 2017; 7
Chen, Kobayashi, Ichikawa, Takeuchi, Togawa (b13) 2000; 38
Zhang, Cui, Mueller, Tao, Kim, Rueschman, Mariani, Mobley, Redline (b40) 2018; 25
Zhang, Pi, Liu (b22) 2015; 62
Hyvärinen, Pajunen (b33) 1999; 12
Chen, Wang, Zee, Lutsey, Javaheri, Alcántara, Jackson, Williams, Redline (b39) 2015; 38
Singha Roy, Gupta, Chandra, Das Sharma, Talukdar (b4) 2018; 67
Krishnan, Natarajan, Warren (b20) 2010; 57
Lei, Ling, Feng, Chen (b37) 2020; 20
Webster, Lee (b6) 2025
Asada, Shaltis, Reisner, Rhee, Hutchinson (b43) 2003; 22
del Testa, Rossi (b3) 2015; 22
Johansson (b29) 2003; 41
Allen (b10) 2007; 28
Teng, Zhang (b16) 2003; 4
Ram, Madhav, Krishna, Komalla, Reddy (b24) 2012; 61
Widjaja, Varon, Dorado, Suykens, Van Huffel (b36) 2012; 59
Lee, Zhang (b26) 2003
Foo (b28) 2006; 1
Lakshminarasimha Murthy, Madhusudana, Suresha, Periyasamy, Ghosh (b23) 2015; 22
Luo, Li, Wang, Cuschieri (b2) 2017; 2017
Chan, Wong, Poh, Pun, Leung, Wong, Wong, Poh, Chu, Siu (b11) 2016; 5
Joseph, Joseph, Titus, Thomas, Jose (b25) 2014
Tamura, Maeda, Sekine, Yoshida (b44) 2014; 3
Reddy, George, Kumar (b21) 2009; 58
Howell, Porr (b42) 2019
Comon, Jutten (b32) 2010
Phan, Siong, Pathirana, Seneviratne (b7) 2015
Li, Struzik, Zhang, Cichocki (b1) 2015; 165
Johansson (10.1016/j.compbiomed.2025.111319_b29) 2003; 41
del Testa (10.1016/j.compbiomed.2025.111319_b3) 2015; 22
Tison (10.1016/j.compbiomed.2025.111319_b8) 2018; 3
Hyvärinen (10.1016/j.compbiomed.2025.111319_b35) 1996; Vol. 9
Teng (10.1016/j.compbiomed.2025.111319_b16) 2003; 4
Reddy (10.1016/j.compbiomed.2025.111319_b21) 2009; 58
Joseph (10.1016/j.compbiomed.2025.111319_b25) 2014
Lee (10.1016/j.compbiomed.2025.111319_b34) 1999; 401
Krishnan (10.1016/j.compbiomed.2025.111319_b20) 2010; 57
Lee (10.1016/j.compbiomed.2025.111319_b12) 2013; 60
Kurylyak (10.1016/j.compbiomed.2025.111319_b30) 2013
Luo (10.1016/j.compbiomed.2025.111319_b2) 2017; 2017
Lee (10.1016/j.compbiomed.2025.111319_b41) 2022; 9
Foo (10.1016/j.compbiomed.2025.111319_b28) 2006; 1
Tamura (10.1016/j.compbiomed.2025.111319_b44) 2014; 3
Hyvärinen (10.1016/j.compbiomed.2025.111319_b33) 1999; 12
Li (10.1016/j.compbiomed.2025.111319_b1) 2015; 165
Chen (10.1016/j.compbiomed.2025.111319_b13) 2000; 38
Lei (10.1016/j.compbiomed.2025.111319_b37) 2020; 20
Wang (10.1016/j.compbiomed.2025.111319_b17) 2018; 2018
Elgendi (10.1016/j.compbiomed.2025.111319_b18) 2012; 8
Phan (10.1016/j.compbiomed.2025.111319_b7) 2015
Zhang (10.1016/j.compbiomed.2025.111319_b22) 2015; 62
Ram (10.1016/j.compbiomed.2025.111319_b24) 2012; 61
Widjaja (10.1016/j.compbiomed.2025.111319_b36) 2012; 59
Lee (10.1016/j.compbiomed.2025.111319_b14) 2018; 17
Chan (10.1016/j.compbiomed.2025.111319_b11) 2016; 5
Shcherbina (10.1016/j.compbiomed.2025.111319_b19) 2017; 7
Lee (10.1016/j.compbiomed.2025.111319_b5) 2019; 23
Tremper (10.1016/j.compbiomed.2025.111319_b9) 1989; 95
Terry (10.1016/j.compbiomed.2025.111319_b31) 2005
Allen (10.1016/j.compbiomed.2025.111319_b10) 2007; 28
Comon (10.1016/j.compbiomed.2025.111319_b32) 2010
Brakel (10.1016/j.compbiomed.2025.111319_b38) 2017
Monte-Moreno (10.1016/j.compbiomed.2025.111319_b15) 2011; 53
Asada (10.1016/j.compbiomed.2025.111319_b43) 2003; 22
Raghuram (10.1016/j.compbiomed.2025.111319_b27) 2010
Singha Roy (10.1016/j.compbiomed.2025.111319_b4) 2018; 67
Webster (10.1016/j.compbiomed.2025.111319_b6) 2025
Lee (10.1016/j.compbiomed.2025.111319_b26) 2003
Chen (10.1016/j.compbiomed.2025.111319_b39) 2015; 38
Lakshminarasimha Murthy (10.1016/j.compbiomed.2025.111319_b23) 2015; 22
Howell (10.1016/j.compbiomed.2025.111319_b42) 2019
Zhang (10.1016/j.compbiomed.2025.111319_b40) 2018; 25
References_xml – volume: 17
  start-page: 81
  year: 2018
  ident: b14
  article-title: Novel blood pressure and pulse pressure estimation based on pulse transit time and stroke volume approximation
  publication-title: BioMedical Eng. OnLine
– volume: 62
  start-page: 522
  year: 2015
  end-page: 531
  ident: b22
  article-title: TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise
  publication-title: IEEE Trans. Biomed. Eng.
– volume: 1
  start-page: 93
  year: 2006
  end-page: 98
  ident: b28
  article-title: Comparison of wavelet transformation and adaptive filtering in restoring artefact-induced time-related measurement
  publication-title: Biomed. Signal Process. Control.
– year: 2017
  ident: b38
  article-title: Learning independent features with adversarial nets for non-linear ICA
– start-page: 170
  year: 2013
  end-page: 174
  ident: b30
  article-title: Photoplethysmogram-based blood pressure evaluation using Kalman filtering and neural networks
  publication-title: 2013 IEEE International Symposium on Medical Measurements and Applications (MeMeA)
– volume: 38
  start-page: 877
  year: 2015
  end-page: 888
  ident: b39
  article-title: Racial/ethnic differences in sleep disturbances: The multi-ethnic study of atherosclerosis (MESA)
  publication-title: Sleep
– volume: 9
  start-page: 279
  year: 2022
  ident: b41
  article-title: VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients
  publication-title: Sci. Data
– volume: 2018
  year: 2018
  ident: b17
  article-title: A novel neural network model for blood pressure estimation using photoplethesmography without electrocardiogram
  publication-title: J. Heal. Eng.
– volume: 58
  start-page: 1706
  year: 2009
  end-page: 1711
  ident: b21
  article-title: Use of Fourier series analysis for motion artifact reduction and data compression of photoplethysmographic signals
  publication-title: IEEE Trans. Instrum. Meas.
– year: 2005
  ident: b31
  article-title: Multi-domain motion estimation and plethysmographic recognition using fuzzy neural-nets
– volume: 12
  start-page: 429
  year: 1999
  end-page: 439
  ident: b33
  article-title: Nonlinear independent component analysis: Existence and uniqueness results
  publication-title: Neural Netw.
– volume: 4
  start-page: 3153
  year: 2003
  end-page: 3156 Vol.4
  ident: b16
  article-title: Continuous and noninvasive estimation of arterial blood pressure using a photoplethysmographic approach
  publication-title: Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439)
– volume: 57
  start-page: 1867
  year: 2010
  end-page: 1876
  ident: b20
  article-title: Two-stage approach for detection and reduction of motion artifacts in photoplethysmographic data
  publication-title: IEEE Trans. Biomed. Eng.
– volume: 59
  start-page: 1169
  year: 2012
  end-page: 1176
  ident: b36
  article-title: Application of kernel principal component analysis for single-lead-ECG-derived respiration
  publication-title: IEEE Trans. Biomed. Eng.
– year: 2025
  ident: b6
  article-title: Blind source separation of single-channel mixtures via multi-encoder autoencoders
  publication-title: Neurocomputing
– start-page: 460
  year: 2010
  end-page: 463
  ident: b27
  article-title: Evaluation of wavelets for reduction of motion artifacts in photoplethysmographic signals
  publication-title: 10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010)
– volume: 41
  start-page: 242
  year: 2003
  end-page: 248
  ident: b29
  article-title: Neural network for photoplethysmographic respiratory rate monitoring
  publication-title: Med. Biol. Eng. Comput.
– volume: 2017
  year: 2017
  ident: b2
  article-title: Patient-specific deep architectural model for ECG classification
  publication-title: J. Heal. Eng.
– volume: 22
  start-page: 2304
  year: 2015
  end-page: 2308
  ident: b3
  article-title: Lightweight lossy compression of biometric patterns via denoising autoencoders
  publication-title: IEEE Signal Process. Lett.
– volume: 38
  start-page: 569
  year: 2000
  end-page: 574
  ident: b13
  article-title: Continuous estimation of systolic blood pressure using the pulse arrival time and intermittent calibration
  publication-title: Med. Biol. Eng. Comput.
– volume: 165
  start-page: 23
  year: 2015
  end-page: 31
  ident: b1
  article-title: Feature learning from incomplete EEG with denoising autoencoder
  publication-title: Neurocomputing
– volume: 3
  start-page: 282
  year: 2014
  end-page: 302
  ident: b44
  article-title: Wearable photoplethysmographic sensors—Past and present
  publication-title: Electronics
– volume: 67
  start-page: 2820
  year: 2018
  end-page: 2829
  ident: b4
  article-title: Improving photoplethysmographic measurements under motion artifacts using artificial neural network for personal healthcare
  publication-title: IEEE Trans. Instrum. Meas.
– start-page: 194
  year: 2003
  end-page: 195
  ident: b26
  article-title: Reduction of motion artifacts from photoplethysmographic recordings using a wavelet denoising approach
  publication-title: IEEE EMBS Asian-Pacific Conference on Biomedical Engineering, 2003.
– volume: 22
  start-page: 2391
  year: 2015
  end-page: 2395
  ident: b23
  article-title: Multiple spectral peak tracking for heart rate monitoring from photoplethysmography signal during intensive physical exercise
  publication-title: IEEE Signal Process. Lett.
– volume: 20
  year: 2020
  ident: b37
  article-title: Estimation of heart rate and respiratory rate from PPG signal using complementary ensemble empirical mode decomposition with both independent component analysis and non-negative matrix factorization
  publication-title: Sensors
– volume: 23
  start-page: 2375
  year: 2019
  end-page: 2385
  ident: b5
  article-title: Bidirectional recurrent auto-encoder for photoplethysmogram denoising
  publication-title: IEEE J. Biomed. Health Informatics
– volume: 61
  start-page: 1445
  year: 2012
  end-page: 1457
  ident: b24
  article-title: A novel approach for motion artifact reduction in PPG signals based on AS-LMS adaptive filter
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 22
  start-page: 28
  year: 2003
  end-page: 40
  ident: b43
  article-title: Mobile monitoring with wearable photoplethysmographic biosensors
  publication-title: IEEE Eng. Med. Biol. Mag.
– volume: 53
  start-page: 127
  year: 2011
  end-page: 138
  ident: b15
  article-title: Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques
  publication-title: Artif. Intell. Med.
– volume: 25
  start-page: 1351
  year: 2018
  end-page: 1358
  ident: b40
  article-title: The national sleep research resource: towards a sleep data commons
  publication-title: J. Am. Med. Inform. Assoc. (JAMIA)
– volume: Vol. 9
  year: 1996
  ident: b35
  article-title: One-unit learning rules for independent component analysis
  publication-title: Advances in Neural Information Processing Systems
– year: 2010
  ident: b32
  article-title: Handbook of Blind Source Separation, Independent Component Analysis and Applications
– volume: 401
  start-page: 788
  year: 1999
  end-page: 791
  ident: b34
  article-title: Learning the parts of objects by non-negative matrix factorization
  publication-title: Nature
– volume: 3
  start-page: 409
  year: 2018
  end-page: 416
  ident: b8
  article-title: Passive detection of atrial fibrillation using a commercially available smartwatch
  publication-title: JAMA Cardiol.
– volume: 95
  start-page: 713
  year: 1989
  end-page: 715
  ident: b9
  article-title: Pulse oximetry
  publication-title: Chest
– start-page: 1
  year: 2014
  end-page: 5
  ident: b25
  article-title: Photoplethysmogram (PPG) signal analysis and wavelet de-noising
  publication-title: 2014 Annual International Conference on Emerging Research Areas: Magnetics, Machines and Drives (AICERA/ICMMD)
– volume: 7
  year: 2017
  ident: b19
  article-title: Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort
  publication-title: J. Pers. Med.
– year: 2019
  ident: b42
  article-title: ECG detectors
– start-page: 144
  year: 2015
  end-page: 147
  ident: b7
  article-title: Smartwatch: Performance evaluation for long-term heart rate monitoring
  publication-title: 2015 International Symposium on Bioelectronics and Bioinformatics
– volume: 5
  year: 2016
  ident: b11
  article-title: Diagnostic performance of a smartphone-based photoplethysmographic application for atrial fibrillation screening in a primary care setting
  publication-title: J. Am. Hear. Assoc.
– volume: 60
  start-page: 203
  year: 2013
  end-page: 206
  ident: b12
  article-title: Atrial fibrillation detection using an iPhone 4S
  publication-title: IEEE Trans. Biomed. Eng.
– volume: 8
  start-page: 14
  year: 2012
  end-page: 25
  ident: b18
  article-title: On the analysis of fingertip photoplethysmogram signals
  publication-title: Curr. Cardiol. Rev.
– volume: 28
  start-page: R1
  year: 2007
  end-page: 39
  ident: b10
  article-title: Photoplethysmography and its application in clinical physiological measurement
  publication-title: Physiol. Meas.
– volume: 165
  start-page: 23
  issn: 0925-2312
  issue: C
  year: 2015
  ident: 10.1016/j.compbiomed.2025.111319_b1
  article-title: Feature learning from incomplete EEG with denoising autoencoder
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2014.08.092
– volume: 2018
  issue: 1
  year: 2018
  ident: 10.1016/j.compbiomed.2025.111319_b17
  article-title: A novel neural network model for blood pressure estimation using photoplethesmography without electrocardiogram
  publication-title: J. Heal. Eng.
– volume: 3
  start-page: 409
  issue: 5
  year: 2018
  ident: 10.1016/j.compbiomed.2025.111319_b8
  article-title: Passive detection of atrial fibrillation using a commercially available smartwatch
  publication-title: JAMA Cardiol.
  doi: 10.1001/jamacardio.2018.0136
– volume: 41
  start-page: 242
  issue: 3
  year: 2003
  ident: 10.1016/j.compbiomed.2025.111319_b29
  article-title: Neural network for photoplethysmographic respiratory rate monitoring
  publication-title: Med. Biol. Eng. Comput.
  doi: 10.1007/BF02348427
– volume: 38
  start-page: 569
  issn: 1741-0444
  issue: 5
  year: 2000
  ident: 10.1016/j.compbiomed.2025.111319_b13
  article-title: Continuous estimation of systolic blood pressure using the pulse arrival time and intermittent calibration
  publication-title: Med. Biol. Eng. Comput.
  doi: 10.1007/BF02345755
– volume: 60
  start-page: 203
  issue: 1
  year: 2013
  ident: 10.1016/j.compbiomed.2025.111319_b12
  article-title: Atrial fibrillation detection using an iPhone 4S
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2012.2208112
– volume: 9
  start-page: 279
  issue: 1
  year: 2022
  ident: 10.1016/j.compbiomed.2025.111319_b41
  article-title: VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients
  publication-title: Sci. Data
  doi: 10.1038/s41597-022-01411-5
– start-page: 194
  year: 2003
  ident: 10.1016/j.compbiomed.2025.111319_b26
  article-title: Reduction of motion artifacts from photoplethysmographic recordings using a wavelet denoising approach
– year: 2005
  ident: 10.1016/j.compbiomed.2025.111319_b31
– volume: 2017
  issue: 1
  year: 2017
  ident: 10.1016/j.compbiomed.2025.111319_b2
  article-title: Patient-specific deep architectural model for ECG classification
  publication-title: J. Heal. Eng.
– volume: 23
  start-page: 2375
  issue: 6
  year: 2019
  ident: 10.1016/j.compbiomed.2025.111319_b5
  article-title: Bidirectional recurrent auto-encoder for photoplethysmogram denoising
  publication-title: IEEE J. Biomed. Health Informatics
  doi: 10.1109/JBHI.2018.2885139
– volume: 5
  issue: 7
  year: 2016
  ident: 10.1016/j.compbiomed.2025.111319_b11
  article-title: Diagnostic performance of a smartphone-based photoplethysmographic application for atrial fibrillation screening in a primary care setting
  publication-title: J. Am. Hear. Assoc.
– volume: 401
  start-page: 788
  issn: 1476-4687
  issue: 6755
  year: 1999
  ident: 10.1016/j.compbiomed.2025.111319_b34
  article-title: Learning the parts of objects by non-negative matrix factorization
  publication-title: Nature
  doi: 10.1038/44565
– volume: 25
  start-page: 1351
  year: 2018
  ident: 10.1016/j.compbiomed.2025.111319_b40
  article-title: The national sleep research resource: towards a sleep data commons
  publication-title: J. Am. Med. Inform. Assoc. (JAMIA)
  doi: 10.1093/jamia/ocy064
– volume: 4
  start-page: 3153
  year: 2003
  ident: 10.1016/j.compbiomed.2025.111319_b16
  article-title: Continuous and noninvasive estimation of arterial blood pressure using a photoplethysmographic approach
– volume: 61
  start-page: 1445
  issue: 5
  year: 2012
  ident: 10.1016/j.compbiomed.2025.111319_b24
  article-title: A novel approach for motion artifact reduction in PPG signals based on AS-LMS adaptive filter
  publication-title: IEEE Trans. Instrum. Meas.
  doi: 10.1109/TIM.2011.2175832
– start-page: 1
  year: 2014
  ident: 10.1016/j.compbiomed.2025.111319_b25
  article-title: Photoplethysmogram (PPG) signal analysis and wavelet de-noising
– volume: 67
  start-page: 2820
  issue: 12
  year: 2018
  ident: 10.1016/j.compbiomed.2025.111319_b4
  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
– volume: 22
  start-page: 28
  issue: 3
  year: 2003
  ident: 10.1016/j.compbiomed.2025.111319_b43
  article-title: Mobile monitoring with wearable photoplethysmographic biosensors
  publication-title: IEEE Eng. Med. Biol. Mag.
  doi: 10.1109/MEMB.2003.1213624
– volume: 57
  start-page: 1867
  issue: 8
  year: 2010
  ident: 10.1016/j.compbiomed.2025.111319_b20
  article-title: Two-stage approach for detection and reduction of motion artifacts in photoplethysmographic data
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2009.2039568
– volume: 38
  start-page: 877
  issue: 6
  year: 2015
  ident: 10.1016/j.compbiomed.2025.111319_b39
  article-title: Racial/ethnic differences in sleep disturbances: The multi-ethnic study of atherosclerosis (MESA)
  publication-title: Sleep
– year: 2017
  ident: 10.1016/j.compbiomed.2025.111319_b38
– start-page: 170
  year: 2013
  ident: 10.1016/j.compbiomed.2025.111319_b30
  article-title: Photoplethysmogram-based blood pressure evaluation using Kalman filtering and neural networks
– volume: 53
  start-page: 127
  issn: 0933-3657
  issue: 2
  year: 2011
  ident: 10.1016/j.compbiomed.2025.111319_b15
  article-title: Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques
  publication-title: Artif. Intell. Med.
  doi: 10.1016/j.artmed.2011.05.001
– volume: 8
  start-page: 14
  issue: 1
  year: 2012
  ident: 10.1016/j.compbiomed.2025.111319_b18
  article-title: On the analysis of fingertip photoplethysmogram signals
  publication-title: Curr. Cardiol. Rev.
  doi: 10.2174/157340312801215782
– volume: 20
  issn: 1424-8220
  issue: 11
  year: 2020
  ident: 10.1016/j.compbiomed.2025.111319_b37
  article-title: Estimation of heart rate and respiratory rate from PPG signal using complementary ensemble empirical mode decomposition with both independent component analysis and non-negative matrix factorization
  publication-title: Sensors
  doi: 10.3390/s20113238
– volume: Vol. 9
  year: 1996
  ident: 10.1016/j.compbiomed.2025.111319_b35
  article-title: One-unit learning rules for independent component analysis
– volume: 3
  start-page: 282
  issn: 2079-9292
  issue: 2
  year: 2014
  ident: 10.1016/j.compbiomed.2025.111319_b44
  article-title: Wearable photoplethysmographic sensors—Past and present
  publication-title: Electronics
  doi: 10.3390/electronics3020282
– volume: 28
  start-page: R1
  issue: 3
  year: 2007
  ident: 10.1016/j.compbiomed.2025.111319_b10
  article-title: Photoplethysmography and its application in clinical physiological measurement
  publication-title: Physiol. Meas.
  doi: 10.1088/0967-3334/28/3/R01
– start-page: 144
  year: 2015
  ident: 10.1016/j.compbiomed.2025.111319_b7
  article-title: Smartwatch: Performance evaluation for long-term heart rate monitoring
– volume: 17
  start-page: 81
  issue: 1
  year: 2018
  ident: 10.1016/j.compbiomed.2025.111319_b14
  article-title: Novel blood pressure and pulse pressure estimation based on pulse transit time and stroke volume approximation
  publication-title: BioMedical Eng. OnLine
  doi: 10.1186/s12938-018-0510-8
– volume: 62
  start-page: 522
  issue: 2
  year: 2015
  ident: 10.1016/j.compbiomed.2025.111319_b22
  article-title: TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2014.2359372
– year: 2010
  ident: 10.1016/j.compbiomed.2025.111319_b32
– volume: 95
  start-page: 713
  issn: 0012-3692
  issue: 4
  year: 1989
  ident: 10.1016/j.compbiomed.2025.111319_b9
  article-title: Pulse oximetry
  publication-title: Chest
  doi: 10.1378/chest.95.4.713
– volume: 12
  start-page: 429
  issn: 0893-6080
  issue: 3
  year: 1999
  ident: 10.1016/j.compbiomed.2025.111319_b33
  article-title: Nonlinear independent component analysis: Existence and uniqueness results
  publication-title: Neural Netw.
  doi: 10.1016/S0893-6080(98)00140-3
– start-page: 460
  year: 2010
  ident: 10.1016/j.compbiomed.2025.111319_b27
  article-title: Evaluation of wavelets for reduction of motion artifacts in photoplethysmographic signals
– volume: 7
  issn: 2075-4426
  issue: 2
  year: 2017
  ident: 10.1016/j.compbiomed.2025.111319_b19
  article-title: Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort
  publication-title: J. Pers. Med.
  doi: 10.3390/jpm7020003
– volume: 22
  start-page: 2391
  issue: 12
  year: 2015
  ident: 10.1016/j.compbiomed.2025.111319_b23
  article-title: Multiple spectral peak tracking for heart rate monitoring from photoplethysmography signal during intensive physical exercise
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2015.2486681
– volume: 58
  start-page: 1706
  issue: 5
  year: 2009
  ident: 10.1016/j.compbiomed.2025.111319_b21
  article-title: Use of Fourier series analysis for motion artifact reduction and data compression of photoplethysmographic signals
  publication-title: IEEE Trans. Instrum. Meas.
  doi: 10.1109/TIM.2008.2009136
– volume: 1
  start-page: 93
  issn: 1746-8094
  issue: 1
  year: 2006
  ident: 10.1016/j.compbiomed.2025.111319_b28
  article-title: Comparison of wavelet transformation and adaptive filtering in restoring artefact-induced time-related measurement
  publication-title: Biomed. Signal Process. Control.
  doi: 10.1016/j.bspc.2006.01.001
– volume: 22
  start-page: 2304
  year: 2015
  ident: 10.1016/j.compbiomed.2025.111319_b3
  article-title: Lightweight lossy compression of biometric patterns via denoising autoencoders
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2015.2476667
– issn: 0925-2312
  year: 2025
  ident: 10.1016/j.compbiomed.2025.111319_b6
  article-title: Blind source separation of single-channel mixtures via multi-encoder autoencoders
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2025.131008
– volume: 59
  start-page: 1169
  issue: 4
  year: 2012
  ident: 10.1016/j.compbiomed.2025.111319_b36
  article-title: Application of kernel principal component analysis for single-lead-ECG-derived respiration
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2012.2186448
– year: 2019
  ident: 10.1016/j.compbiomed.2025.111319_b42
SSID ssj0004030
Score 2.4271903
Snippet Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Publisher
StartPage 111319
SubjectTerms Biosignal processing
Blind source separation
Denoising
Heart rate detection
Photoplethysmogram
Self-supervised learning
Title Self-supervised autoencoder network for robust heart rate extraction from noisy photoplethysmogram: Applying blind source separation to biosignal analysis
URI https://www.clinicalkey.com/#!/content/1-s2.0-S0010482525016737
https://dx.doi.org/10.1016/j.compbiomed.2025.111319
https://www.ncbi.nlm.nih.gov/pubmed/41274114
https://www.proquest.com/docview/3274586826
Volume 199
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1879-0534
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004030
  issn: 0010-4825
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3bjtMwELW6uwjxgrgu5bIyEuKlCso9NjytoCtAS0GiK_oW2YkDXS1xadLV8it8AN_JjO20ZS9SeeAlqiy5aXJOx-PxmRlCngGsVZoI5vlVyb24ihNPJEx6ZjXmPGFclabZRDYascmEf-r1fne5MKcnWV2zszM--69QwxiAjamz_wD38kthAD4D6HAF2OG6EfCf1UnlNYsZGoEG3EmxaDVWq8SiEbUVfRtt4VzLRdOipzhvB1gwYgB2eu5ah5usk1pPG4x96BZV5ojodyPmMsFE8F5NhpQEPxVD73gGMGiULSWOJxB6IKca5SGmGoEtfbLuCnf9JIwgd70W1Pnj_i9Kdu1DXHfytVbRVkf0Rtdfvyl9QV6kdV3_1G5xdrGNMFnTiVhzzDLugZmwIQd1yVhnw22XpQvrgQ1NHCOcM1vP4AXeBxeKyJnqv0pwjz7mB0eHh_l4OBk_n_3wsDsZnuK7Vi1bZCfMEg7Wc2f_3XDyfpWB65uuNsvf5jRjVkl4-c2vcoSu2ugYh2d8i9x0OxW6bxl2m_RUfYdc_-DAuUt-nSMaXSMadUSjQDRqiUYN0SgSja6IRpFo1BCNXiTaS9rRjBqaUUszuqIZbTVd0ox2NLtHjg6G49dvPdfpwyvCMIg9mRWwb5dxIMISXiF4ucIPqiwRQolYFZlIfSb9VJYyLXmVVDLOVOBzEWQy8QseRffJdq1r9YBQFckwgD16wFQVMynAHw_9QpV-VAah4KJPgu615zNb0CXvlI7H-QqqHKHKLVR9wjt88i5hGZbYHFi2wdxXy7nOqbXO6oazn3Z0yMHu42GeqJVeNHkUZnHCUhamfbJrebJ8njjAolRB_HCD2Y_IjdU_7zHZbucL9YRcK07baTPfI1vZhO05tv8B48HlWA
linkProvider Elsevier
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=Self-supervised+autoencoder+network+for+robust+heart+rate+extraction+from+noisy+photoplethysmogram%3A+Applying+blind+source+separation+to+biosignal+analysis&rft.jtitle=Computers+in+biology+and+medicine&rft.au=Webster%2C+Matthew+B&rft.au=Lee%2C+Dongheon&rft.au=Lee%2C+Joonnyong&rft.date=2025-12-01&rft.issn=1879-0534&rft.eissn=1879-0534&rft.volume=199&rft_id=info:doi/10.1016%2Fj.compbiomed.2025.111319&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0010-4825&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0010-4825&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0010-4825&client=summon