Personalization of Energy Expenditure Estimation in Free Living Using Topic Models

We introduce an approach to personalize energy expenditure (EE) estimates in free living. First, we use topic models to discover activity composites from recognized activity primitives and stay regions in daily living data. Subsequently, we determine activity composites that are relevant to contextu...

Full description

Saved in:
Bibliographic Details
Published inIEEE journal of biomedical and health informatics Vol. 19; no. 5; pp. 1577 - 1586
Main Authors Altini, Marco, Casale, Pierluigi, Penders, Julien F., Amft, Oliver
Format Journal Article
LanguageEnglish
Published United States IEEE 01.09.2015
Subjects
Online AccessGet full text

Cover

Loading…
Abstract We introduce an approach to personalize energy expenditure (EE) estimates in free living. First, we use topic models to discover activity composites from recognized activity primitives and stay regions in daily living data. Subsequently, we determine activity composites that are relevant to contextualize heart rate (HR). Activity composites were ranked and analyzed to optimize the correlation to HR normalization parameters. Finally, individual-specific HR normalization parameters were used to normalize HR. Normalized HR was then included in activity-specific regression models to estimate EE. Our HR normalization minimizes the effect of individual fitness differences from entering in EE regression models. By estimating HR normalization parameters in free living, our approach avoids dedicated individual calibration or laboratory tests. In a combined free-living and laboratory study dataset, including 34 healthy volunteers, we show that HR normalization in 14-day free-living data improves accuracy compared to no normalization and normalization based on activity primitives only (29.4% and 19.8 % error reduction against lab reference). Based on acceleration and HR, both recorded from a necklace, and GPS acquired from a smartphone, EE estimation error was reduced by 10.7% in a leave-one-participant-out analysis.
AbstractList We introduce an approach to personalize energy expenditure (EE) estimates in free living. First, we use topic models to discover activity composites from recognized activity primitives and stay regions in daily living data. Subsequently, we determine activity composites that are relevant to contextualize heart rate (HR). Activity composites were ranked and analyzed to optimize the correlation to HR normalization parameters. Finally, individual-specific HR normalization parameters were used to normalize HR. Normalized HR was then included in activity-specific regression models to estimate EE. Our HR normalization minimizes the effect of individual fitness differences from entering in EE regression models. By estimating HR normalization parameters in free living, our approach avoids dedicated individual calibration or laboratory tests. In a combined free-living and laboratory study dataset, including 34 healthy volunteers, we show that HR normalization in 14-day free-living data improves accuracy compared to no normalization and normalization based on activity primitives only (29.4% and 19.8 % error reduction against lab reference). Based on acceleration and HR, both recorded from a necklace, and GPS acquired from a smartphone, EE estimation error was reduced by 10.7% in a leave-one-participant-out analysis.
Author Amft, Oliver
Casale, Pierluigi
Altini, Marco
Penders, Julien F.
Author_xml – sequence: 1
  givenname: Marco
  surname: Altini
  fullname: Altini, Marco
  email: altini.marco@gmail.com
  organization: Bloom Technol., Diepenbeek, Belgium
– sequence: 2
  givenname: Pierluigi
  surname: Casale
  fullname: Casale, Pierluigi
  email: piecurus@gmail.com
  organization: IMEC-NL, Eindhoven, Netherlands
– sequence: 3
  givenname: Julien F.
  surname: Penders
  fullname: Penders, Julien F.
  email: Julien.Penders@imec-nl.nl
  organization: IMEC-NL, Eindhoven, Netherlands
– sequence: 4
  givenname: Oliver
  surname: Amft
  fullname: Amft, Oliver
  email: amft@fim.uni-passau.de
  organization: Univ. of Passau, Passau, Germany
BackLink https://www.ncbi.nlm.nih.gov/pubmed/25838531$$D View this record in MEDLINE/PubMed
BookMark eNo9kF9PwjAUxRuDEUQ-gDExe_Rl2D9b1z0qGYLBaAw8L2O7IzWjne1mxE9vlwF9uG16f_fcnHONBkorQOiW4CkhOH58fV4spxSTcEoDImjIL9CIEi58SrEYnN4kDoZoYu0Xdke4r5hfoSENBRMhIyP0-QHGapVV8i9rpFaeLr1EgdkdvOS3BlXIpjXgJbaR-x6QypsbAG8lf6TaeRvb1bWuZe696QIqe4Muy6yyMDneY7SZJ-vZwl-9vyxnTys_Z5Q0vluP44hFJMszHnIWFcK5cFaKQGyDMiy3rIhpEQWc4BCXOceYZYRRXOIYeB6yMXrodWujv1uwTbqXNoeqyhTo1qYkcvo4CkTkUNKjudHWGijT2jg_5pASnHZppl2aaZdmekzTzdwf5dvtHorzxCk7B9z1gASAc9ttZDwQ7B-7hXic
CODEN IJBHA9
CitedBy_id crossref_primary_10_1145_3404482
crossref_primary_10_1109_TBME_2022_3163429
crossref_primary_10_3389_fpubh_2019_00167
crossref_primary_10_1109_JSEN_2021_3075109
crossref_primary_10_1152_japplphysiol_00714_2018
crossref_primary_10_1016_j_artmed_2016_02_002
Cites_doi 10.1109/TBME.2007.896591
10.1038/oby.2005.103
10.1088/0967-3334/35/9/1797
10.1109/JBHI.2014.2313039
10.1152/japplphysiol.00128.2003
10.1161/01.RES.24.5.711
10.1145/1526709.1526816
10.1113/jphysiol.1949.sp004363
10.1123/jpah.2013-0190
10.1152/jappl.1954.7.2.218
10.1109/TBME.2011.2159840
10.1177/1089313X0400800301
10.1152/japplphysiol.00703.2003
10.1145/2534088.2534092
10.1055/s-2008-1025839
10.1249/MSS.0b013e3181c37458
10.4108/icst.pervasivehealth.2013.252069
10.1145/1409635.1409638
10.1079/BJN19890107
10.1152/japplphysiol.00150.2009
10.1109/TBME.2013.2284069
10.1016/j.pmcj.2014.05.007
10.1002/j.1550-8528.1995.tb00007.x
ContentType Journal Article
DBID 97E
RIA
RIE
CGR
CUY
CVF
ECM
EIF
NPM
AAYXX
CITATION
7X8
DOI 10.1109/JBHI.2015.2418256
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library Online
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
CrossRef
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
CrossRef
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2168-2208
EndPage 1586
ExternalDocumentID 10_1109_JBHI_2015_2418256
25838531
7073648
Genre orig-research
Journal Article
GroupedDBID 0R~
4.4
6IF
6IH
6IK
6IL
97E
AAJGR
AASAJ
ABQJQ
ABVLG
ACIWK
ACPRK
ADZIZ
AENEX
AFRAH
AKJIK
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CHZPO
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
RIA
RIE
RIG
RNS
CGR
CUY
CVF
ECM
EIF
NPM
AAYXX
AGSQL
CITATION
7X8
ID FETCH-LOGICAL-c321t-531097371aca65637d8825418d48b4f5fb3d92d7461050fc6003a1320f09e6c53
IEDL.DBID RIE
ISSN 2168-2194
IngestDate Tue Dec 03 23:32:12 EST 2024
Fri Dec 06 04:18:20 EST 2024
Sat Sep 28 07:56:02 EDT 2024
Wed Jun 26 19:22:05 EDT 2024
IsPeerReviewed true
IsScholarly true
Issue 5
Keywords Context
topic models
heart rate
energy expenditure
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c321t-531097371aca65637d8825418d48b4f5fb3d92d7461050fc6003a1320f09e6c53
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 25838531
PQID 1709707487
PQPubID 23479
PageCount 10
ParticipantIDs proquest_miscellaneous_1709707487
ieee_primary_7073648
crossref_primary_10_1109_JBHI_2015_2418256
pubmed_primary_25838531
PublicationCentury 2000
PublicationDate 2015-Sept.
2015-Sep
2015-9-00
20150901
PublicationDateYYYYMMDD 2015-09-01
PublicationDate_xml – month: 09
  year: 2015
  text: 2015-Sept.
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle IEEE journal of biomedical and health informatics
PublicationTitleAbbrev JBHI
PublicationTitleAlternate IEEE J Biomed Health Inform
PublicationYear 2015
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
ref15
ref10
altini (ref19) 0
ref2
ref1
blei (ref14) 2003; 3
ref17
ref16
ref18
redding (ref23) 2004; 8
ref24
åstrand (ref11) 1954; 7
ref26
ref25
ref20
ref22
ref21
ref8
ref7
ref9
ref4
tapia (ref6) 2008
ref3
ref5
References_xml – volume: 3
  start-page: 993
  year: 2003
  ident: ref14
  article-title: Latent Dirichlet allocation
  publication-title: J Mach Learn Res
  contributor:
    fullname: blei
– ident: ref1
  doi: 10.1109/TBME.2007.896591
– ident: ref20
  doi: 10.1038/oby.2005.103
– ident: ref12
  doi: 10.1088/0967-3334/35/9/1797
– start-page: 1:1
  year: 0
  ident: ref19
  publication-title: Proc of Conference on Wireless Health
  contributor:
    fullname: altini
– ident: ref7
  doi: 10.1109/JBHI.2014.2313039
– ident: ref21
  doi: 10.1152/japplphysiol.00128.2003
– ident: ref10
  doi: 10.1161/01.RES.24.5.711
– ident: ref22
  doi: 10.1145/1526709.1526816
– ident: ref16
  doi: 10.1113/jphysiol.1949.sp004363
– ident: ref25
  doi: 10.1123/jpah.2013-0190
– volume: 7
  start-page: 218
  year: 1954
  ident: ref11
  article-title: A nomogram for calculation of aerobic capacity (physical fitness) from pulse rate during submaximal work
  publication-title: J Appl Physiol
  doi: 10.1152/jappl.1954.7.2.218
  contributor:
    fullname: åstrand
– ident: ref2
  doi: 10.1109/TBME.2011.2159840
– volume: 8
  start-page: 69
  year: 2004
  ident: ref23
  article-title: Validity of using heart rate as a predictor of oxygen consumption in dance
  publication-title: J Dance Med Sci
  doi: 10.1177/1089313X0400800301
  contributor:
    fullname: redding
– ident: ref9
  doi: 10.1152/japplphysiol.00703.2003
– ident: ref26
  doi: 10.1145/2534088.2534092
– ident: ref17
  doi: 10.1055/s-2008-1025839
– ident: ref4
  doi: 10.1249/MSS.0b013e3181c37458
– year: 2008
  ident: ref6
  article-title: Using machine learning for real-time activity recognition and estimation of energy expenditure
  contributor:
    fullname: tapia
– ident: ref8
  doi: 10.4108/icst.pervasivehealth.2013.252069
– ident: ref13
  doi: 10.1145/1409635.1409638
– ident: ref3
  doi: 10.1079/BJN19890107
– ident: ref5
  doi: 10.1152/japplphysiol.00150.2009
– ident: ref24
  doi: 10.1109/TBME.2013.2284069
– ident: ref15
  doi: 10.1016/j.pmcj.2014.05.007
– ident: ref18
  doi: 10.1002/j.1550-8528.1995.tb00007.x
SSID ssj0000816896
Score 2.225262
Snippet We introduce an approach to personalize energy expenditure (EE) estimates in free living. First, we use topic models to discover activity composites from...
SourceID proquest
crossref
pubmed
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 1577
SubjectTerms Accelerometers
Accelerometry
Adult
Algorithms
Context
Databases, Factual
Energy Expenditure
Energy Metabolism - physiology
Estimation
Female
Heart rate
Heart Rate - physiology
Hidden Markov models
Humans
Laboratories
Legged locomotion
Male
Models, Biological
Monitoring, Ambulatory - methods
Protocols
Signal Processing, Computer-Assisted
Topic Models
Young Adult
Title Personalization of Energy Expenditure Estimation in Free Living Using Topic Models
URI https://ieeexplore.ieee.org/document/7073648
https://www.ncbi.nlm.nih.gov/pubmed/25838531
https://search.proquest.com/docview/1709707487
Volume 19
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Li9swEB6yOSy9tPvoI-1uUaGnUjuRZVnWcVsS0qUppSSQm5FtCcIWOyTxZX99Z-QHtLTQi9HBL83Ink_z-gDeG66dLhMXuCjPg1iZMjCKR3hIiSdJlLkj18DqW7LcxPdbuR3Bx6EWxlrrk89sSEMfyy_roiFX2VThekzi9AzOlE7aWq3Bn-IJJDwdV4SDAD_EuAti8pme3n9afqE8LhmixcJNETEXRRQxlIL_ZpE8xcq_0aa3OotnsOrft002eQibUx4Wj3-0cvzfCV3A0w5-srt2vVzCyFZXcL7qAuzX8ON7D87b8kxWOzb35YGMmiJTfLs5WDbHH0Nb88h2FVscrGVfd-SaYD4Fga3r_a5gxLP28_gcNov5-vMy6GgXgkJE_BRIahaqhOKmMIj2hCpT2kbytIzTPHbS5aLUUamoU7ucuQIhkzBUie1m2iaFFC9gXNWVfQUM0ZoVKVq8yKC1lLGJZJHwVKPgDXeaT-BDL_ps33bXyPyuZKYzUllGKss6lU3gmiQ4nNgJbwLvemVl-GlQvMNUtm6OGVc4D4RIqZrAy1aLw8W98l___aZv4Ak9uk0mu4Hx6dDYW0Qfp_ytX3a_AFUf0QY
link.rule.ids 314,780,784,796,27924,27925,54758
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PT9swFH5iIDEubNAB3RgYaaeJtHUcx8lxQ60KtAihVuIWOYktVaCkKs2Fv573nKTS0CbtEvmQRM57dt7n9-sD-KF5bOM8tJ7109QLlM49rbiPl4h4kkSeWnINTO_C8Ty4eZSPW3C5qYUxxrjkM9OjoYvl52VWkausr3A9hkH0AXZkgDi3rtbaeFQchYQj5PJx4OFWDJowJh_E_Zvf42vK5JI9tFl4LCLuIp9ihlLwP2ySI1n5N950dmf0CabtjOt0k6detU572eu7Zo7_-0mfYb8BoOxXvWIOYMsUh7A7bULsHXi4b-F5XaDJSsuGrkCQUVtkinBXK8OG-Guoqx7ZomCjlTFssiDnBHNJCGxWLhcZI6a155cvMB8NZ1djryFe8DLh87UnqV2oEorrTCPeEyqP6CDJozyI0sBKm4o89nNFvdrlwGYImoSmWmw7iE2YSXEE20VZmBNgiNeMiNDm-RrtpQy0L7OQRzEKXnMb8y78bEWfLOv-Gok7lwzihFSWkMqSRmVd6JAENzc2wuvCRausBDcHRTx0YcrqJeEKvwNBUqS6cFxrcfNwq_yvf3_pOXwcz6aTZHJ9d_sN9mgadWrZKWyvV5X5jlhknZ65JfgGh5LUWQ
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=Personalization+of+Energy+Expenditure+Estimation+in+Free+Living+Using+Topic+Models&rft.jtitle=IEEE+journal+of+biomedical+and+health+informatics&rft.au=Altini%2C+Marco&rft.au=Casale%2C+Pierluigi&rft.au=Penders%2C+Julien+F.&rft.au=Amft%2C+Oliver&rft.date=2015-09-01&rft.pub=IEEE&rft.issn=2168-2194&rft.eissn=2168-2208&rft.volume=19&rft.issue=5&rft.spage=1577&rft.epage=1586&rft_id=info:doi/10.1109%2FJBHI.2015.2418256&rft_id=info%3Apmid%2F25838531&rft.externalDocID=7073648
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2194&client=summon