ParaLabel: Autonomous Parameter Learning for Cross-Domain Step Counting in Wearable Sensors

Wearable step counters, also referred to as activity trackers, have been developed for health and activity monitoring, as well as for step tracking. These trackers, however, produce unreliable measurements during slow walking and when walking with assistive devices (i.e., aided walking). To address...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE sensors journal Jg. 20; H. 23; S. 13867 - 13879
Hauptverfasser:	Alinia, Parastoo, Fallahzadeh, Ramin, Connolly, Christopher P., Ghasemzadeh, Hassan
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.12.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Accelerometers Accuracy Algorithms cross-subject transfer learning Domains Feature extraction frequency components K-nearest neighbor Learning Legged locomotion low-pass filter Low-pass filters Machine learning algorithms Nearest neighbor methods Parameters peak detection Sensors Step counting time-domain features Tracking devices Treadmills wearable sensors Wearable technology Wrist
ISSN:	1530-437X, 1558-1748
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Wearable step counters, also referred to as activity trackers, have been developed for health and activity monitoring, as well as for step tracking. These trackers, however, produce unreliable measurements during slow walking and when walking with assistive devices (i.e., aided walking). To address this challenge, in this article, we introduce, ParaLabel , a filter-based step counting algorithm that is reliable against various walking velocities and intensities. ParaLabel addresses this problem by learning a filter cut-off frequency autonomously in a new domain without the need for collecting sensor data and manually tuning the algorithm parameter for a different velocity and/or pattern of walking. We formulate this problem as a transfer learning problem in which the new filter cut-off frequency is transferred from a bank containing previously fine-tuned parameters from different domain(s). Our extensive analysis using real data collected from 15 participants while wearing an accelerometer sensor on their chest, wrist, or left pocket demonstrates the superiority of ParaLabel to two commercially available trackers worn on the same body location, and state-of-the-art techniques. ParaLabel achieves 96.3% − 99.9% accuracy during walking on a treadmill at three different velocities, 98.2% − 99.9% accuracy during walking with a shopping cart, and 89.3% − 97.3% accuracy while walking with the aid of a walker.
AbstractList	Wearable step counters, also referred to as activity trackers, have been developed for health and activity monitoring, as well as for step tracking. These trackers, however, produce unreliable measurements during slow walking and when walking with assistive devices (i.e., aided walking). To address this challenge, in this article, we introduce, ParaLabel , a filter-based step counting algorithm that is reliable against various walking velocities and intensities. ParaLabel addresses this problem by learning a filter cut-off frequency autonomously in a new domain without the need for collecting sensor data and manually tuning the algorithm parameter for a different velocity and/or pattern of walking. We formulate this problem as a transfer learning problem in which the new filter cut-off frequency is transferred from a bank containing previously fine-tuned parameters from different domain(s). Our extensive analysis using real data collected from 15 participants while wearing an accelerometer sensor on their chest, wrist, or left pocket demonstrates the superiority of ParaLabel to two commercially available trackers worn on the same body location, and state-of-the-art techniques. ParaLabel achieves 96.3% − 99.9% accuracy during walking on a treadmill at three different velocities, 98.2% − 99.9% accuracy during walking with a shopping cart, and 89.3% − 97.3% accuracy while walking with the aid of a walker.
Author	Fallahzadeh, Ramin Connolly, Christopher P. Ghasemzadeh, Hassan Alinia, Parastoo
Author_xml	– sequence: 1 givenname: Parastoo orcidid: 0000-0001-8201-3005 surname: Alinia fullname: Alinia, Parastoo email: parastoo.alinia@wsu.edu organization: School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA – sequence: 2 givenname: Ramin surname: Fallahzadeh fullname: Fallahzadeh, Ramin organization: School of Medicine, Stanford University, Stanford, CA, USA – sequence: 3 givenname: Christopher P. surname: Connolly fullname: Connolly, Christopher P. organization: Department of Kinesiology and Educational Psychology, Pullman, Washington State University, WA, USA – sequence: 4 givenname: Hassan orcidid: 0000-0002-1844-1416 surname: Ghasemzadeh fullname: Ghasemzadeh, Hassan organization: School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA
BookMark	eNp9UEtLxDAQDqLg7uoPEC8Bz12TJmkbb0tdXxQVVlHwENJ2Kl26yZqkB_-9Lbt48CBzmOF7zDDfFB0aawChM0rmlBJ5-bBaPs5jEpM5I0TGjB6gCRUii2jKs8NxZiTiLH0_RlPv14RQmYp0gj6etdOFLqG7wos-WGM3tvd4RDcQwOECtDOt-cSNdTh31vvo2m50a_AqwBbntjdhpAfgbZDqsgO8AuOt8yfoqNGdh9N9n6HXm-VLfhcVT7f3-aKIqliyEFVVzVnFMxaDLrWGSjRZIpisslrKBkpexyIhdVoznpYMMhCCNgkVpchKVnPNZuhit3fr7FcPPqi17Z0ZTqqYJ4SKobJBle5U1fiEg0ZVbdChtSY43XaKEjUmqcYk1Zik2ic5OOkf59a1G-2-__Wc7zwtAPzqJWVSDuwPOQaBXg
CODEN	ISJEAZ
CitedBy_id	crossref_primary_10_1109_JSEN_2021_3099860 crossref_primary_10_1007_s43926_025_00186_6 crossref_primary_10_3390_s22113989 crossref_primary_10_1109_JSEN_2021_3058127 crossref_primary_10_1109_JSEN_2021_3059636 crossref_primary_10_1016_j_mtcomm_2023_106250 crossref_primary_10_1109_ACCESS_2024_3422256
Cites_doi	10.1145/2638728.2641313 10.1109/THMS.2013.2296875 10.1109/ICCCN.2009.5235366 10.1589/jpts.29.613 10.3390/s18072034 10.1109/APCCAS.2012.6419104 10.1109/IEMBS.2011.6091084 10.12968/ijtr.2012.19.7.387 10.1097/JCN.0b013e318283ba14 10.1186/1756-0500-7-952 10.1007/978-3-540-70994-7_14 10.3390/s151027230 10.1145/2493432.2493449 10.1145/3266157.3266212 10.1016/j.gaitpost.2013.10.009 10.3390/s16091423 10.1109/ICSEngT.2012.6339316 10.1109/JSEN.2016.2603163 10.1109/TPAMI.2002.1017616 10.1145/2971648.2971742 10.1186/s12984-016-0145-6 10.1109/CCDC.2015.7161816 10.1123/jab.15.3.318 10.3390/s18010297 10.1145/3299876 10.3390/s151229858 10.5120/17195-7390 10.1123/japa.2014-0033 10.1529/biophysj.107.110601 10.2196/mhealth.6321 10.1186/s13102-015-0018-5 10.1109/JSTSP.2016.2569472 10.1109/JIOT.2016.2553100 10.5081/jgps.3.1.273 10.1109/IEMBS.2006.260770 10.1007/s12553-012-0035-2 10.1109/IPIN.2011.6071935
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 7SP 7U5 8FD L7M
DOI	10.1109/JSEN.2020.3009231
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Engineering
EISSN	1558-1748
EndPage	13879
ExternalDocumentID	10_1109_JSEN_2020_3009231 9139931
Genre	orig-research
GrantInformation_xml	– fundername: National Science Foundation grantid: CNS-1750679 funderid: 10.13039/100000001
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c293t-ccd43c4832eabaaec5f86539c8d99feb4d2560d7d347b3e8e551f615b58b3d4a3
IEDL.DBID	RIE
ISICitedReferencesCount	6
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000589257300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1530-437X
IngestDate	Mon Jun 30 10:14:13 EDT 2025 Tue Nov 18 20:44:37 EST 2025 Sat Nov 29 05:43:03 EST 2025 Wed Aug 27 06:02:06 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	23
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-ccd43c4832eabaaec5f86539c8d99feb4d2560d7d347b3e8e551f615b58b3d4a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-8201-3005 0000-0002-1844-1416
PQID	2460151518
PQPubID	75733
PageCount	13
ParticipantIDs	proquest_journals_2460151518 ieee_primary_9139931 crossref_primary_10_1109_JSEN_2020_3009231 crossref_citationtrail_10_1109_JSEN_2020_3009231
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	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE sensors journal
PublicationTitleAbbrev	JSEN
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	ref35 ref13 jayalath (ref9) 2013; 28 ref12 ref37 ref15 ref36 ref14 ref31 ref30 ref33 ref11 ref32 ref10 chen (ref26) 2015; 23 ref2 ref39 ref17 ref38 ref16 ref19 ref18 mammen (ref4) 2012; 5 lee (ref5) 2013 dontje (ref1) 2014; 29 ref24 ref45 ref25 ref42 ref22 ref44 ref21 ref43 ref28 ref27 ref29 ref8 ref7 alinia (ref34) 2020 ref3 dirican (ref23) 2017; 8 ref6 arcidiacono (ref20) 2017; 53 ref40 zhongshen (ref41) 2003; 3
References_xml	– ident: ref36 doi: 10.1145/2638728.2641313 – ident: ref27 doi: 10.1109/THMS.2013.2296875 – ident: ref32 doi: 10.1109/ICCCN.2009.5235366 – ident: ref2 doi: 10.1589/jpts.29.613 – ident: ref16 doi: 10.3390/s18072034 – ident: ref29 doi: 10.1109/APCCAS.2012.6419104 – volume: 5 start-page: 9 year: 2012 ident: ref4 article-title: Is this bit fit? Measuring the quality of the fitbit step-counter publication-title: Health Fit J Can – year: 2013 ident: ref5 article-title: Validity of consumer-based physical activity monitors and calibration of smartphone for prediction of physical activity energy expenditure – ident: ref31 doi: 10.1109/IEMBS.2011.6091084 – ident: ref13 doi: 10.12968/ijtr.2012.19.7.387 – volume: 29 start-page: 218 year: 2014 ident: ref1 article-title: Daily physical activity in stable heart failure patients publication-title: European Journal of Cardiovascular Nursing doi: 10.1097/JCN.0b013e318283ba14 – ident: ref3 doi: 10.1186/1756-0500-7-952 – ident: ref10 doi: 10.1007/978-3-540-70994-7_14 – ident: ref45 doi: 10.3390/s151027230 – ident: ref6 doi: 10.1145/2493432.2493449 – volume: 23 start-page: 315 year: 2015 ident: ref26 article-title: Pedometer method based on adaptive peak detection algorithm publication-title: J Chin Inert Technol – ident: ref15 doi: 10.1145/3266157.3266212 – ident: ref17 doi: 10.1016/j.gaitpost.2013.10.009 – ident: ref30 doi: 10.3390/s16091423 – ident: ref40 doi: 10.1109/ICSEngT.2012.6339316 – ident: ref18 doi: 10.1109/JSEN.2016.2603163 – ident: ref37 doi: 10.1109/TPAMI.2002.1017616 – ident: ref25 doi: 10.1145/2971648.2971742 – ident: ref11 doi: 10.1186/s12984-016-0145-6 – ident: ref14 doi: 10.1109/CCDC.2015.7161816 – year: 2020 ident: ref34 article-title: ActiLabel: A combinatorial transfer learning framework for activity recognition publication-title: arXiv 2003 07415 – volume: 53 start-page: 109 year: 2017 ident: ref20 article-title: A threshold-based algorithm for the development of inertial sensor-based systems to perform real-time cow step counting in free-stall barns publication-title: Syst Eng – ident: ref42 doi: 10.1123/jab.15.3.318 – ident: ref19 doi: 10.3390/s18010297 – ident: ref38 doi: 10.1145/3299876 – volume: 8 start-page: 175 year: 2017 ident: ref23 article-title: Step counting using smartphone accelerometer and fast Fourier transform publication-title: Sigma J Eng Nat Sci – ident: ref35 doi: 10.3390/s151229858 – ident: ref43 doi: 10.5120/17195-7390 – ident: ref12 doi: 10.1123/japa.2014-0033 – volume: 3 start-page: 17 year: 2003 ident: ref41 article-title: The design of Butterworth lowpass filter based on MATLAB publication-title: Heilongjiang Electronic Technique – ident: ref7 doi: 10.1529/biophysj.107.110601 – ident: ref39 doi: 10.2196/mhealth.6321 – volume: 28 start-page: 31 year: 2013 ident: ref9 article-title: A gyroscope based accurate pedometer algorithm publication-title: Proc Int Conf Indoor Positioning Indoor Navigat – ident: ref44 doi: 10.1186/s13102-015-0018-5 – ident: ref33 doi: 10.1109/JSTSP.2016.2569472 – ident: ref24 doi: 10.1109/JIOT.2016.2553100 – ident: ref22 doi: 10.5081/jgps.3.1.273 – ident: ref28 doi: 10.1109/IEMBS.2006.260770 – ident: ref8 doi: 10.1007/s12553-012-0035-2 – ident: ref21 doi: 10.1109/IPIN.2011.6071935
SSID	ssj0019757
Score	2.340042
Snippet	Wearable step counters, also referred to as activity trackers, have been developed for health and activity monitoring, as well as for step tracking. These...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	13867
SubjectTerms	Accelerometers Accuracy Algorithms cross-subject transfer learning Domains Feature extraction frequency components K-nearest neighbor Learning Legged locomotion low-pass filter Low-pass filters Machine learning algorithms Nearest neighbor methods Parameters peak detection Sensors Step counting time-domain features Tracking devices Treadmills wearable sensors Wearable technology Wrist
Title	ParaLabel: Autonomous Parameter Learning for Cross-Domain Step Counting in Wearable Sensors
URI	https://ieeexplore.ieee.org/document/9139931 https://www.proquest.com/docview/2460151518
Volume	20
WOSCitedRecordID	wos000589257300001&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: 1558-1748 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019757 issn: 1530-437X databaseCode: RIE dateStart: 20010101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5UBPXgW6xWycGTuLptsm7irVRFRIqgYsHDkqcWtJU-BP-9M9tYFEXwtoQkLPvtbL7ZmfkGYC-EVAWqbtdZCIlAa0qQhWSJ5Me8nhtnjXVls4m81ZLttrqegoNJLYz3vkw-84d0WcbyXc-O6FfZEUlYKiqans7z43Gt1iRioPJS1RMNOE0Ez9sxgllL1dHlzVkLPcE6OqgkMcRr386gsqnKjy9xebycL_3vxpZhMdJI1hjjvgJTvrsKC1_EBVdhLvY3f3pfg4dr3ddX2vjnE9YYDamQAT1-RqMvlA_DoszqI0MOy5p018lp70V3uozSwFgzdpRgOHCPU6neit2gB9zrD9bh7vzstnmRxLYKicWzfZhY6wS3Ak3Za6O1t1mQJFBrpVMqeCMc0SCXOy5yw730SKoCEh-TScOd0HwDZrq9rt8EJkig3tm69JoCgN7IgJsrm4mQaa6zCqSfD7qwUXOcWl88F6XvkaqCsCkImyJiU4H9yZLXseDGX5PXCIzJxIhDBaqfaBbRJAdFXaDvieytJrd-X7UN87T3OFelCjPD_sjvwKx9G3YG_d3ybfsAeLLSPw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fSxtBEB4kFawPVWOLaWO7D30Sr7nc7vV2fQsxojUNgpYG-nDszyqYRPJD8L_vzGUTWloKvh3L7t1x383tNzcz3wB8DCFVgarbdR5CItCaEmQheSL5Z54VxlljXdVsohgM5HCorjbgeF0L472vks_8JzqsYvluYhf0q6xFEpaKiqZf5EJk6bJaax0zUEWl64kmnCaCF8MYw2ynqvXlujdAXzBDF5VEhnj7j12oaqvy17e42mDOdp53a7vwKhJJ1lkivwcbflyH7d_kBeuwFTuc3z7tw48rPdV9bfz9Cess5lTKgD4_o9ERZcSwKLT6kyGLZV266-R0MtJ3Y0aJYKwbe0owHPiOU6niil2jDzyZzl7Dt7PeTfc8iY0VEou7-zyx1gluBRqz10Zrb_MgSaLWSqdU8EY4IkKucFwUhnvpkVYFpD4ml4Y7ofkbqI0nY38ATJBEvbOZ9JpCgN7IgCdXNhch11znDUhXD7q0UXWcml_cl5X3kaqSsCkJmzJi04Cj9ZKHpeTG_ybvExjriRGHBjRXaJbRKGdlJtD7RP7Wlm__veoDbJ3ffO2X_YvB5Tt4SddZZq40oTafLvwhbNrH-d1s-r56834BkO3Vhg
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=ParaLabel%3A+Autonomous+Parameter+Learning+for+Cross-Domain+Step+Counting+in+Wearable+Sensors&rft.jtitle=IEEE+sensors+journal&rft.au=Alinia%2C+Parastoo&rft.au=Fallahzadeh%2C+Ramin&rft.au=Connolly%2C+Christopher+P&rft.au=Ghasemzadeh%2C+Hassan&rft.date=2020-12-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=20&rft.issue=23&rft.spage=13867&rft_id=info:doi/10.1109%2FJSEN.2020.3009231&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon