Sequential Human Gait Classification With Distributed Radar Sensor Fusion

This paper presents different information fusion approaches to classify human gait patterns and falls in a radar sensors network. The human gaits classified in this work are both individual and sequential, continuous gait collected by a FMCW radar and three UWB pulse radar placed at different spatia...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE sensors journal Jg. 21; H. 6; S. 7590 - 7603
Hauptverfasser:	Li, Haobo, Mehul, Ajay, Le Kernec, Julien, Gurbuz, Sevgi Z., Fioranelli, Francesco
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 15.03.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Classification Classifiers Data integration Decision trees Doppler radar fall detection Gait gait analysis Legged locomotion machine learning Multisensor fusion Neural networks Pulse radar Radar RF sensing Sensor fusion Sensor phenomena and characterization Sensors Ultra wideband radar Ultrawideband radar Walking
ISSN:	1530-437X, 1558-1748
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	This paper presents different information fusion approaches to classify human gait patterns and falls in a radar sensors network. The human gaits classified in this work are both individual and sequential, continuous gait collected by a FMCW radar and three UWB pulse radar placed at different spatial locations. Sequential gaits are those containing multiple gait styles performed one after the other, with natural transitions in between, including fall events developing from walking gait in some cases. The proposed information fusion approaches operate at signal and decision level. For the signal level combination, a simple trilateration algorithm is implemented on the range data from the 3 UWB radar sensors, achieving good classification results with the proposed Bi-LSTM (Bidirectional LSTM neural network) as classifier, without exploiting conventional micro-Doppler information. For the decision level fusion, the classification results of individual radars using the Bi-LSTM network are combined with a robust Naive Bayes Combiner (NBC), and this showed subsequent improvement compared to the single radar case thanks to multi-perspective views of the subjects. Compared to conventional SVM and Random Forest classifiers, the proposed approach yields +20% and +17% improvement in the classification accuracy of individual gaits for the range-only trilateration method and NBC decision fusion method, respectively. When classifying sequential gaits, the overall accuracy for the two proposed methods reaches 93% and 90%, with validation via a 'leaving one participant out' approach to test the robustness with subjects unknown to the network.
AbstractList	This paper presents different information fusion approaches to classify human gait patterns and falls in a radar sensors network. The human gaits classified in this work are both individual and sequential, continuous gait collected by a FMCW radar and three UWB pulse radar placed at different spatial locations. Sequential gaits are those containing multiple gait styles performed one after the other, with natural transitions in between, including fall events developing from walking gait in some cases. The proposed information fusion approaches operate at signal and decision level. For the signal level combination, a simple trilateration algorithm is implemented on the range data from the 3 UWB radar sensors, achieving good classification results with the proposed Bi-LSTM (Bidirectional LSTM neural network) as classifier, without exploiting conventional micro-Doppler information. For the decision level fusion, the classification results of individual radars using the Bi-LSTM network are combined with a robust Naive Bayes Combiner (NBC), and this showed subsequent improvement compared to the single radar case thanks to multi-perspective views of the subjects. Compared to conventional SVM and Random Forest classifiers, the proposed approach yields +20% and +17% improvement in the classification accuracy of individual gaits for the range-only trilateration method and NBC decision fusion method, respectively. When classifying sequential gaits, the overall accuracy for the two proposed methods reaches 93% and 90%, with validation via a ’leaving one participant out’ approach to test the robustness with subjects unknown to the network.
Author	Fioranelli, Francesco Le Kernec, Julien Gurbuz, Sevgi Z. Li, Haobo Mehul, Ajay
Author_xml	– sequence: 1 givenname: Haobo orcidid: 0000-0002-8464-9565 surname: Li fullname: Li, Haobo email: h.li.4@research.gla.ac.uk organization: James Watt School of Engineering, University of Glasgow, Glasgow, U.K – sequence: 2 givenname: Ajay surname: Mehul fullname: Mehul, Ajay email: aanbuselvam@crimson.ua.edu organization: Department of Computer Science, University of Alabama, Tuscaloosa, AL, USA – sequence: 3 givenname: Julien orcidid: 0000-0003-2124-6803 surname: Le Kernec fullname: Le Kernec, Julien email: julien.lekernec@glasgow.ac.uk organization: James Watt School of Engineering, University of Glasgow, Glasgow, U.K – sequence: 4 givenname: Sevgi Z. orcidid: 0000-0001-7487-9087 surname: Gurbuz fullname: Gurbuz, Sevgi Z. email: szgurbuz@ua.edu organization: Department of Electrical and Computer Engineering, University of Alabama, Tuscaloosa, AL, USA – sequence: 5 givenname: Francesco orcidid: 0000-0001-8254-8093 surname: Fioranelli fullname: Fioranelli, Francesco email: f.fioranelli@tudelft.nl organization: Microwave Sensing, Signals and Systems (MS3) Section, TU Delft, Delft, The Netherlands
BookMark	eNp9kD1PwzAURS0EEm3hByAWS8wpduz4Y0SlX6gCiYJgs2zHEa7apNjOwL8noRUDA9N7wz3vPp0hOK2b2gFwhdEYYyRvH9bTx3GOcjQmiDIp8QkY4KIQGeZUnPY7QRkl_P0cDGPcIIQlL_gALNfus3V18noLF-1O13CufYKTrY7RV97q5Jsavvn0Ae99TMGbNrkSPutSB7h2dWwCnLWxC12As0pvo7s8zhF4nU1fJots9TRfTu5WmSWEpQxjKktnCksrbXleUMwow04IK00ptCGSSE4NIQgzbgtnGOKY5qVBUhpdaTICN4e7-9B0r8ekNk0b6q5S5VTmomCSiC6FDykbmhiDq9Q--J0OXwoj1RtTvTHVG1NHYx3D_zDWpx8BKWi__Ze8PpDeOffbJAliAiPyDTiRejg
CODEN	ISJEAZ
CitedBy_id	crossref_primary_10_1007_s00521_022_07776_3 crossref_primary_10_1109_THMS_2021_3131675 crossref_primary_10_1109_ACCESS_2021_3122516 crossref_primary_10_1016_j_patcog_2024_111101 crossref_primary_10_1109_TGRS_2022_3189746 crossref_primary_10_3390_rs13183791 crossref_primary_10_3390_s21113643 crossref_primary_10_1109_ACCESS_2024_3514140 crossref_primary_10_1109_JSEN_2024_3513983 crossref_primary_10_1016_j_bspc_2022_103741 crossref_primary_10_5515_KJKIEES_2025_36_1_51 crossref_primary_10_3390_s21093158 crossref_primary_10_1109_JSEN_2023_3323323 crossref_primary_10_3390_rs14010123 crossref_primary_10_1109_TGRS_2021_3122332 crossref_primary_10_1049_rsn2_12249 crossref_primary_10_1109_ACCESS_2023_3289402 crossref_primary_10_1038_s41598_025_97757_y crossref_primary_10_1109_JSEN_2022_3232085 crossref_primary_10_1109_JSEN_2024_3454714 crossref_primary_10_3390_s21134291 crossref_primary_10_3390_app15137446 crossref_primary_10_1109_ACCESS_2022_3228639 crossref_primary_10_1109_JIOT_2023_3330996 crossref_primary_10_1109_TIM_2024_3457967 crossref_primary_10_3390_s23115100 crossref_primary_10_1109_JSEN_2022_3154092 crossref_primary_10_1016_j_dsp_2023_103964 crossref_primary_10_1109_JSEN_2024_3432636 crossref_primary_10_1016_j_smhl_2022_100334 crossref_primary_10_1109_JIOT_2023_3242417 crossref_primary_10_1016_j_neucom_2024_128313 crossref_primary_10_3390_s23031457 crossref_primary_10_1109_JSEN_2023_3267820 crossref_primary_10_1109_TGRS_2023_3345829 crossref_primary_10_1109_JSEN_2024_3482291
Cites_doi	10.1109/JSEN.2016.2628099 10.1109/COMPEM.2019.8779144 10.1109/JSEN.2018.2872894 10.1109/JSEN.2020.3006386 10.1049/iet-rsn.2015.0144 10.1109/JSEN.2019.2917375 10.1109/TMTT.2017.2650911 10.1162/neco.1997.9.8.1735 10.1111/jgs.15304 10.1109/MPOT.2019.2906977 10.1109/RADAR.2019.8835661 10.1109/JSEN.2014.2370945 10.1007/s10115-012-0586-6 10.1016/j.neunet.2005.06.042 10.1016/j.dsp.2019.01.013 10.1109/JSEN.2020.3004581 10.1109/LGRS.2015.2491329 10.1109/MSP.2019.2903715 10.1109/TMTT.2017.2650909 10.1109/RADAR.2019.8835611 10.1109/EuRAD.2014.6991233 10.1016/j.medengphy.2016.12.011 10.1109/JSEN.2017.2697077 10.1109/MSP.2015.2499314 10.1109/LGRS.2015.2452311 10.1109/LGRS.2016.2539386 10.1109/IMBIOC.2019.8777855 10.1109/TGRS.2019.2929096 10.1109/PIERS-FALL.2017.8293530 10.1109/ICASSP.2013.6638947 10.1109/JSEN.2019.2946095 10.1109/JERM.2018.2827099 10.23919/EURAD.2017.8249173 10.1109/MSP.2018.2890128 10.1049/iet-rsn.2015.0118 10.1109/TGRS.2009.2012849 10.1109/TAES.2018.2799758 10.1049/iet-rsn.2018.5054 10.1109/TGRS.2019.2908758 10.1109/TBME.2019.2893528 10.1109/TAES.2018.2883847 10.1109/TBME.2014.2319333 10.1109/TAES.2019.2910980 10.1109/ASRU.2015.7404814
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/JSEN.2020.3046991
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals (WRLC) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) 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	7603
ExternalDocumentID	10_1109_JSEN_2020_3046991 9306810
Genre	orig-research
GrantInformation_xml	– fundername: University of Glasgow Mobility Scholarship through the research exchange to the University of Alabama funderid: 10.13039/100011531 – fundername: U.K. Engineering and Physical Sciences Research Council (EPSRC) grantid: EP/R041679/1 (INSHEP) funderid: 10.13039/501100000266
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 ESBDL F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c336t-1149deb5c4fac725416461e88c9bd8ab393974b330167c5eb607142db099bafa3
IEDL.DBID	RIE
ISICitedReferencesCount	63
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000636053600050&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 10:06:45 EDT 2025 Tue Nov 18 22:15:17 EST 2025 Sat Nov 29 05:43:07 EST 2025 Wed Aug 27 02:44:32 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c336t-1149deb5c4fac725416461e88c9bd8ab393974b330167c5eb607142db099bafa3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-7487-9087 0000-0003-2124-6803 0000-0002-8464-9565 0000-0001-8254-8093
OpenAccessLink	https://ieeexplore.ieee.org/document/9306810
PQID	2492856938
PQPubID	75733
PageCount	14
ParticipantIDs	crossref_primary_10_1109_JSEN_2020_3046991 ieee_primary_9306810 crossref_citationtrail_10_1109_JSEN_2020_3046991 proquest_journals_2492856938
PublicationCentury	2000
PublicationDate	2021-03-15
PublicationDateYYYYMMDD	2021-03-15
PublicationDate_xml	– month: 03 year: 2021 text: 2021-03-15 day: 15
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE sensors journal
PublicationTitleAbbrev	JSEN
PublicationYear	2021
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 ref34 ref12 ref37 ref36 ref14 ref31 ref30 ref33 ref11 ref32 ref10 ref2 ref1 ref39 ref17 ref38 ref16 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref42 ref41 ref22 ref44 ref21 ref43 kim (ref15) 2009; 47 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 kay (ref45) 1993
References_xml	– ident: ref1 doi: 10.1109/JSEN.2016.2628099 – ident: ref41 doi: 10.1109/COMPEM.2019.8779144 – ident: ref31 doi: 10.1109/JSEN.2018.2872894 – ident: ref28 doi: 10.1109/JSEN.2020.3006386 – ident: ref35 doi: 10.1049/iet-rsn.2015.0144 – ident: ref34 doi: 10.1109/JSEN.2019.2917375 – year: 1993 ident: ref45 publication-title: Fundamentals of Statistical Signal Processing – ident: ref10 doi: 10.1109/TMTT.2017.2650911 – ident: ref19 doi: 10.1162/neco.1997.9.8.1735 – ident: ref2 doi: 10.1111/jgs.15304 – ident: ref12 doi: 10.1109/MPOT.2019.2906977 – ident: ref43 doi: 10.1109/RADAR.2019.8835661 – ident: ref3 doi: 10.1109/JSEN.2014.2370945 – ident: ref39 doi: 10.1007/s10115-012-0586-6 – ident: ref22 doi: 10.1016/j.neunet.2005.06.042 – ident: ref24 doi: 10.1016/j.dsp.2019.01.013 – ident: ref42 doi: 10.1109/JSEN.2020.3004581 – ident: ref17 doi: 10.1109/LGRS.2015.2491329 – ident: ref6 doi: 10.1109/MSP.2019.2903715 – ident: ref11 doi: 10.1109/TMTT.2017.2650909 – ident: ref5 doi: 10.1109/RADAR.2019.8835611 – ident: ref37 doi: 10.1109/EuRAD.2014.6991233 – ident: ref32 doi: 10.1016/j.medengphy.2016.12.011 – ident: ref9 doi: 10.1109/JSEN.2017.2697077 – ident: ref8 doi: 10.1109/MSP.2015.2499314 – ident: ref38 doi: 10.1109/LGRS.2015.2452311 – ident: ref44 doi: 10.1109/LGRS.2016.2539386 – ident: ref26 doi: 10.1109/IMBIOC.2019.8777855 – ident: ref33 doi: 10.1109/TGRS.2019.2929096 – ident: ref36 doi: 10.1109/PIERS-FALL.2017.8293530 – ident: ref40 doi: 10.1109/ICASSP.2013.6638947 – ident: ref27 doi: 10.1109/JSEN.2019.2946095 – ident: ref30 doi: 10.1109/JERM.2018.2827099 – ident: ref20 doi: 10.23919/EURAD.2017.8249173 – ident: ref7 doi: 10.1109/MSP.2018.2890128 – ident: ref14 doi: 10.1049/iet-rsn.2015.0118 – volume: 47 start-page: 1328 year: 2009 ident: ref15 article-title: Human activity classification based on micro-Doppler signatures using a support vector machine publication-title: IEEE Trans Geosci Remote Sens doi: 10.1109/TGRS.2009.2012849 – ident: ref16 doi: 10.1109/TAES.2018.2799758 – ident: ref21 doi: 10.1049/iet-rsn.2018.5054 – ident: ref25 doi: 10.1109/TGRS.2019.2908758 – ident: ref4 doi: 10.1109/TBME.2019.2893528 – ident: ref18 doi: 10.1109/TAES.2018.2883847 – ident: ref29 doi: 10.1109/TBME.2014.2319333 – ident: ref13 doi: 10.1109/TAES.2019.2910980 – ident: ref23 doi: 10.1109/ASRU.2015.7404814
SSID	ssj0019757
Score	2.54993
Snippet	This paper presents different information fusion approaches to classify human gait patterns and falls in a radar sensors network. The human gaits classified in...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	7590
SubjectTerms	Algorithms Classification Classifiers Data integration Decision trees Doppler radar fall detection Gait gait analysis Legged locomotion machine learning Multisensor fusion Neural networks Pulse radar Radar RF sensing Sensor fusion Sensor phenomena and characterization Sensors Ultra wideband radar Ultrawideband radar Walking
Title	Sequential Human Gait Classification With Distributed Radar Sensor Fusion
URI	https://ieeexplore.ieee.org/document/9306810 https://www.proquest.com/docview/2492856938
Volume	21
WOSCitedRecordID	wos000636053600050&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/eLvHCXMwlV3dS8MwED_mENQHPzbF6ZQ8-CTWtU3bJI-imx_IEOfH3kqSZmwwNtk6wf_eXNYNRRF860MC5X695n6Xu98BnMTUUEn9nmeoMl5k6bWnuK896cvA8CQwkVP7fLln7TbvdsVDCc6WvTDGGFd8Zs7x0d3lZ2M9w1RZQ9j4lmM_1QpjbN6rtbwxEMypeloH9r2Ism5xgxn4onHXabYtEwwtQUU2KIJvZ5AbqvLjT-yOl9bW_15sGzaLMJJczHHfgZIZVWDji7hgBdaK-eb9jyrcdlzFtPXmIXFpe3ItBzlxEzGxVsjBQ14HeZ9coZIuDsEyGXmUmZyQjmW64wlpzTCxtgvPrebT5Y1XDFHwNKVJ7lm-IzKjYh31pGaWDqKgmIWBa6EyLhUVNiKJFKXYj6Bjo1BwLgozZUNHJXuS7kF5NB6ZfSBca5P4oZBMWtePEpmwTEQqwf0JC1UN_IVZU10ojOOgi2HqmIYvUkQiRSTSAokanC63vM3lNf5aXEXTLxcWVq9BfYFdWjjgNEUhRB4ngvKD33cdwnqI5SlYmhfXoZxPZuYIVvV7PphOjt239Qkyf8pE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwED5EhemDv8Xp1Dz4JFbbJm2TR1Hn1DnETd1bSdKMDcYmWyf435vL6lAUwbc-JFDu6zX3Xe6-AziKqKGS-h3PUGU8Zum1p7ivPenLwPA4MMypfT7Xk0aDt9viYQ5OZr0wxhhXfGZO8dHd5WdDPcFU2Zmw8S3HfqqFiLEwmHZrze4MROJ0Pa0L-x6jSbu4wwx8cXbbvGpYLhhaiop8UATfTiE3VuXHv9gdMNXV_73aGqwUgSQ5nyK_DnNmsAHLX-QFN6BUTDjvvm_CTdPVTFt_7hOXuCfXspcTNxMTq4UcQOSll3fJJWrp4hgsk5FHmckRaVquOxyR6gRTa1vwVL1qXdS8YoyCpymNc88yHpEZFWnWkTqxhBAlxSwQXAuVcamosDEJU5RiR4KOjELJORZmygaPSnYk3Yb5wXBgdoBwrU3sh0Im0jo_i2WcZIKpGPfHSajK4H-aNdWFxjiOuuinjmv4IkUkUkQiLZAow_Fsy-tUYOOvxZto-tnCwuplqHxilxYuOE5RCpFHsaB89_ddh1Cqte7raf2mcbcHSyEWq2ChXlSB-Xw0MfuwqN_y3nh04L6zD-OlzYs
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=Sequential+Human+Gait+Classification+With+Distributed+Radar+Sensor+Fusion&rft.jtitle=IEEE+sensors+journal&rft.au=Li%2C+Haobo&rft.au=Mehul%2C+Ajay&rft.au=Le+Kernec%2C+Julien&rft.au=Gurbuz%2C+Sevgi+Z.&rft.date=2021-03-15&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=21&rft.issue=6&rft.spage=7590&rft.epage=7603&rft_id=info:doi/10.1109%2FJSEN.2020.3046991&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2020_3046991
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