Automated and precise heartbeat detection in ballistocardiography signals using bidirectional LSTM
Ballistocardiography (BCG) provides an unobtrusive, mechanical measurement of heartbeat for early detection and longitudinal monitoring of cardiovascular conditions, although it is plagued by poor signal to noise ratio. Despite tremendous efforts over the last decade in related advanced signal proce...
Saved in:
Published in | Franklin Open Vol. 1; pp. 30 - 38 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier
01.08.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Ballistocardiography (BCG) provides an unobtrusive, mechanical measurement of heartbeat for early detection and longitudinal monitoring of cardiovascular conditions, although it is plagued by poor signal to noise ratio. Despite tremendous efforts over the last decade in related advanced signal processing and deep learning research, automated and precise heartbeat detection in BCG remains a major technical challenge. In this work, we design and study a sequential deep neural network based approach that addresses three key issues in automated BCG learning and detection: auto-labeling of BCG samples in the raw training data; design of a recursive neural network that can learn the association between the continuous BCG waves and the label sequence in the form of sample-by-sample predictions; and finally, heartbeat detection from the output sequence. We evaluate the proposed method using our data set comprising 8 human subjects under varying cardiac output conditions: pre-exercise and post-exercise. Using multiple performance metrics, we report that the proposed method can achieve a heart rate accuracy of 98.68% and root-mean-square-error of 1.37 bpm with 98.85% coverage, which compare favorably to two state-of-the-art methods in the same test. |
---|---|
AbstractList | Ballistocardiography (BCG) provides an unobtrusive, mechanical measurement of heartbeat for early detection and longitudinal monitoring of cardiovascular conditions, although it is plagued by poor signal to noise ratio. Despite tremendous efforts over the last decade in related advanced signal processing and deep learning research, automated and precise heartbeat detection in BCG remains a major technical challenge. In this work, we design and study a sequential deep neural network based approach that addresses three key issues in automated BCG learning and detection: auto-labeling of BCG samples in the raw training data; design of a recursive neural network that can learn the association between the continuous BCG waves and the label sequence in the form of sample-by-sample predictions; and finally, heartbeat detection from the output sequence. We evaluate the proposed method using our data set comprising 8 human subjects under varying cardiac output conditions: pre-exercise and post-exercise. Using multiple performance metrics, we report that the proposed method can achieve a heart rate accuracy of 98.68% and root-mean-square-error of 1.37 bpm with 98.85% coverage, which compare favorably to two state-of-the-art methods in the same test. |
Author | Haihong Zhang Shiyu Zhang Zhiping Lin Soon Huat Ng |
Author_xml | – sequence: 1 fullname: Shiyu Zhang organization: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore – sequence: 2 fullname: Haihong Zhang organization: Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore – sequence: 3 fullname: Zhiping Lin organization: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore; Corresponding author – sequence: 4 fullname: Soon Huat Ng organization: Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore |
BookMark | eNotj8tqwzAURLVIoWmaP-hCP2BXki1ZWobQF6R00XRtrqQrR8GxjOws8vcNTVcDc5gD80AWQxqQkCfOSs64ej6WIUMasRRMiJLJkjG-IEvRNFXBtaruyXqaomW11sxoxZbEbs5zOsGMnsLg6ZjRxQnpASHPFmGmHmd0c0wDjQO10PdxmpOD7GPqMoyHC51iN0A_0fMUh47a6GO-LaCnu-_95yO5C1eO6_9ckZ_Xl_32vdh9vX1sN7vCCaZ5IblUTBhXWS1MCJ7XKASaxmhRawdCcm6caVTQwQVrlRNeOKiY9wbBSl2tyMfN6xMc2zHHE-RLmyC2f0XKXXs9FV2PrVHeAdNGocS6CdLWXhntJSrZOHSu-gX2UGji |
CitedBy_id | crossref_primary_10_3390_s23136200 crossref_primary_10_1016_j_fraope_2024_100073 |
ContentType | Journal Article |
DBID | DOA |
DOI | 10.1016/j.fraope.2022.05.001 |
DatabaseName | Directory of Open Access Journals |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
DeliveryMethod | fulltext_linktorsrc |
EndPage | 38 |
ExternalDocumentID | oai_doaj_org_article_96dca0896e5e47f5b4d698d5e657cecc |
GroupedDBID | 0SF AALRI AAXUO ADVLN AFJKZ AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ FDB GROUPED_DOAJ ROL |
ID | FETCH-LOGICAL-c2081-5156029c3b829ffd14e22e9798248ca25119c976f8fcfbb6c2d2ca30dd9eab583 |
IEDL.DBID | DOA |
ISSN | 2773-1863 |
IngestDate | Fri Oct 04 13:12:32 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c2081-5156029c3b829ffd14e22e9798248ca25119c976f8fcfbb6c2d2ca30dd9eab583 |
OpenAccessLink | https://doaj.org/article/96dca0896e5e47f5b4d698d5e657cecc |
PageCount | 9 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_96dca0896e5e47f5b4d698d5e657cecc |
PublicationCentury | 2000 |
PublicationDate | 2022-08-01 |
PublicationDateYYYYMMDD | 2022-08-01 |
PublicationDate_xml | – month: 08 year: 2022 text: 2022-08-01 day: 01 |
PublicationDecade | 2020 |
PublicationTitle | Franklin Open |
PublicationYear | 2022 |
Publisher | Elsevier |
Publisher_xml | – name: Elsevier |
SSID | ssib048809860 |
Score | 2.2342377 |
Snippet | Ballistocardiography (BCG) provides an unobtrusive, mechanical measurement of heartbeat for early detection and longitudinal monitoring of cardiovascular... |
SourceID | doaj |
SourceType | Open Website |
StartPage | 30 |
SubjectTerms | Ballistocardiography Heartbeat detection Recursive deep learning |
Title | Automated and precise heartbeat detection in ballistocardiography signals using bidirectional LSTM |
URI | https://doaj.org/article/96dca0896e5e47f5b4d698d5e657cecc |
Volume | 1 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrZ1LSwMxEMeD9ORFFBXf5OB1sZvXJsdWLEXUiy30tiSTRAplW-r2-5tJKvTmxesesksmmcfyn98Q8sis9jVIXkmjoBJeWUTehqrxJiIZwLmYaZ8fajoXrwu5OBj1hZqwggcuG_dklAc71EYFGUQTpUvrGe1lULKB9P7sfWt5UEylk4Sn0ujcIsyahle1Vvy3by6Lu-LWrjdIyWQsgztxJswBsz8Hl8kpOdlnhXRUvuaMHIXunLjRrl-nhDJ4msp9ukEOxXegOIK6d8mFUh_6LKTq6LKjzq5WiAmALDAtHGqK6ox0viiq27-oW5YAlv_-0bfP2fsFmU9eZs_Taj8SoQKWgnclsfGZGeBOMxOjr0VgLJjGaCY0WKwXDKQMI-oI0TkFzDOwfOi9CdZJzS_JoFt34YrQqINTPF1pMCCAa4eEWiasSSHbJz95Tca4Ie2mUC9a5FDnB8k67d467V_WufmPRW7JMRqqyO7uyKDf7sJ9SgV695Ct_gOGL7NW |
link.rule.ids | 315,786,790,870,2115,27957,27958 |
linkProvider | Directory of Open Access Journals |
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=Automated+and+precise+heartbeat+detection+in+ballistocardiography+signals+using+bidirectional+LSTM&rft.jtitle=Franklin+Open&rft.au=Shiyu+Zhang&rft.au=Haihong+Zhang&rft.au=Zhiping+Lin&rft.au=Soon+Huat+Ng&rft.date=2022-08-01&rft.pub=Elsevier&rft.issn=2773-1863&rft.volume=1&rft.spage=30&rft.epage=38&rft_id=info:doi/10.1016%2Fj.fraope.2022.05.001&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_96dca0896e5e47f5b4d698d5e657cecc |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2773-1863&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2773-1863&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2773-1863&client=summon |