Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition

Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world envir...

Full description

Saved in:
Bibliographic Details
Published inSensors (Basel, Switzerland) Vol. 22; no. 19; p. 7324
Main Authors Bento, Nuno, Rebelo, Joana, Barandas, Marília, Carreiro, André V., Campagner, Andrea, Cabitza, Federico, Gamboa, Hugo
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 27.09.2022
MDPI
Subjects
Online AccessGet full text
ISSN1424-8220
1424-8220
DOI10.3390/s22197324

Cover

Abstract Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world environments. As deep neural networks are becoming increasingly popular in recent work, there is a need for an explicit comparison between handcrafted and deep representations in Out-of-Distribution (OOD) settings. This paper compares both approaches in multiple domains using homogenized public datasets. First, we compare several metrics to validate three different OOD settings. In our main experiments, we then verify that even though deep learning initially outperforms models with handcrafted features, the situation is reversed as the distance from the training distribution increases. These findings support the hypothesis that handcrafted features may generalize better across specific domains.
AbstractList Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world environments. As deep neural networks are becoming increasingly popular in recent work, there is a need for an explicit comparison between handcrafted and deep representations in Out-of-Distribution (OOD) settings. This paper compares both approaches in multiple domains using homogenized public datasets. First, we compare several metrics to validate three different OOD settings. In our main experiments, we then verify that even though deep learning initially outperforms models with handcrafted features, the situation is reversed as the distance from the training distribution increases. These findings support the hypothesis that handcrafted features may generalize better across specific domains.
Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world environments. As deep neural networks are becoming increasingly popular in recent work, there is a need for an explicit comparison between handcrafted and deep representations in Out-of-Distribution (OOD) settings. This paper compares both approaches in multiple domains using homogenized public datasets. First, we compare several metrics to validate three different OOD settings. In our main experiments, we then verify that even though deep learning initially outperforms models with handcrafted features, the situation is reversed as the distance from the training distribution increases. These findings support the hypothesis that handcrafted features may generalize better across specific domains.Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world environments. As deep neural networks are becoming increasingly popular in recent work, there is a need for an explicit comparison between handcrafted and deep representations in Out-of-Distribution (OOD) settings. This paper compares both approaches in multiple domains using homogenized public datasets. First, we compare several metrics to validate three different OOD settings. In our main experiments, we then verify that even though deep learning initially outperforms models with handcrafted features, the situation is reversed as the distance from the training distribution increases. These findings support the hypothesis that handcrafted features may generalize better across specific domains.
Audience Academic
Author Bento, Nuno
Barandas, Marília
Cabitza, Federico
Campagner, Andrea
Gamboa, Hugo
Carreiro, André V.
Rebelo, Joana
AuthorAffiliation 3 Dipartimento di Informatica, Sistemistica e Comunicazione, Università degli Studi di Milano-Bicocca, 20126 Milan, Italy
4 IRCCS Istituto Ortopedico Galeazzi, 20161 Milan, Italy
1 Associação Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal
2 Laboratório de Instrumentação, Engenharia Biomédica e Física da Radiação (LIBPhys–UNL), Departamento de Física, Faculdade de Ciências e Tecnologia (FCT), Universidade Nova de Lisboa, 2829-516 Caparica, Portugal
AuthorAffiliation_xml – name: 1 Associação Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal
– name: 3 Dipartimento di Informatica, Sistemistica e Comunicazione, Università degli Studi di Milano-Bicocca, 20126 Milan, Italy
– name: 2 Laboratório de Instrumentação, Engenharia Biomédica e Física da Radiação (LIBPhys–UNL), Departamento de Física, Faculdade de Ciências e Tecnologia (FCT), Universidade Nova de Lisboa, 2829-516 Caparica, Portugal
– name: 4 IRCCS Istituto Ortopedico Galeazzi, 20161 Milan, Italy
Author_xml – sequence: 1
  givenname: Nuno
  orcidid: 0000-0001-7279-1890
  surname: Bento
  fullname: Bento, Nuno
– sequence: 2
  givenname: Joana
  orcidid: 0000-0003-0385-053X
  surname: Rebelo
  fullname: Rebelo, Joana
– sequence: 3
  givenname: Marília
  orcidid: 0000-0002-9445-4809
  surname: Barandas
  fullname: Barandas, Marília
– sequence: 4
  givenname: André V.
  orcidid: 0000-0002-4234-5336
  surname: Carreiro
  fullname: Carreiro, André V.
– sequence: 5
  givenname: Andrea
  orcidid: 0000-0002-0027-5157
  surname: Campagner
  fullname: Campagner, Andrea
– sequence: 6
  givenname: Federico
  orcidid: 0000-0002-4065-3415
  surname: Cabitza
  fullname: Cabitza, Federico
– sequence: 7
  givenname: Hugo
  orcidid: 0000-0002-4022-7424
  surname: Gamboa
  fullname: Gamboa, Hugo
BookMark eNp9Uk1v1DAQjVAR_YAD_8ASF4q0bfyROLkgrba0W6kCCcE5mtjj4FViBydZtPx6nKaqaIWwD7bevHnPM-PT5Mh5h0nylqYXnJfp5cAYLSVn4kVyQgUTq4Kx9Oiv-3FyOgy7NGWc8-JVcsxzxnPB5Emy3_iuh2BdQ7bgtApgRtTkGmGcAg4kYuQKsSefcQrQkq_YRxjdCKP1biDGB3LlO7CO3KDDSLG_70MkItupA0fWarR7Ox5irvKNs3P0dfLSQDvgm4fzLPl-_enbZru6-3Jzu1nfrVSW0XFFMwqFrJmuM9CFKKDWhTbK5IIqUVAlZal0BozyWkvAHOqcpVLFZXRtipSfJbeLrvawq_pgOwiHyoOt7gEfmgrCaFWLVWGwZoJjVkgp6rQoQRssmVCpLPNasKj1YdGaXA-HX9C2j4I0reZBVI-DiOSPC7mf6g61ih2LvXnygqcRZ39Ujd9XZSYZEzQKvH8QCP7nhMNYdXZQ2Lbg0E9DxSTLaBnNZq93z6g7PwUX-zqzBKesFDPrYmE1EKu1zvjoq-LW2FkVP5SxEV9LkWeclulc7_mSoIIfhoDmv-VePuMqu3yRaGLbf2T8AS272uI
CitedBy_id crossref_primary_10_1109_JSEN_2024_3356651
crossref_primary_10_3390_electronics12244924
crossref_primary_10_1016_j_robot_2023_104615
crossref_primary_10_3390_s23146511
crossref_primary_10_3390_s23010125
crossref_primary_10_3390_app13074175
crossref_primary_10_1016_j_eswa_2024_126295
crossref_primary_10_3390_w15061088
crossref_primary_10_1016_j_compmedimag_2024_102438
crossref_primary_10_3390_s23208449
crossref_primary_10_3390_s23125715
Cites_doi 10.1016/j.eswa.2016.04.032
10.1109/ACCESS.2020.3010715
10.1186/s12911-020-01224-9
10.1080/02664760802192981
10.1109/ISCE.2019.8901021
10.1016/j.neucom.2020.10.056
10.1109/SMC.2015.263
10.1016/j.neucom.2020.09.091
10.12720/ijsps.1.2.256-262
10.1145/3537972.3537996
10.1145/2413097.2413148
10.3390/s22062360
10.3390/e20080592
10.1016/j.cmpb.2021.106288
10.1109/ACCESS.2018.2890675
10.1109/ISBI.2019.8759281
10.1186/1475-925X-14-S2-S6
10.3390/s21062141
10.3390/s21237853
10.1371/journal.pone.0075196
10.1088/1742-5468/ac3a74
10.1145/3410531.3414311
10.1109/ICSENS.2016.7808590
10.3390/s140610146
10.5220/0005699601900197
10.3390/s22093401
10.1016/j.softx.2020.100456
10.1109/PERCOM.2016.7456521
10.3390/s21186316
10.1109/ISWC.2012.13
10.1016/B978-1-78548-236-6.50002-7
10.1145/3265689.3265705
10.1109/SERVICES.2019.00084
10.3390/s21051669
10.3390/s19143213
10.1007/978-3-319-13105-4
10.1371/journal.pone.0237009
10.1016/j.patrec.2018.02.010
10.1109/ICITR51448.2020.9310792
10.3390/s19010057
10.3390/s18020679
10.1038/s42256-020-00257-z
10.1007/s10994-008-5059-5
ContentType Journal Article
Copyright COPYRIGHT 2022 MDPI AG
2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2022 by the authors. 2022
Copyright_xml – notice: COPYRIGHT 2022 MDPI AG
– notice: 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2022 by the authors. 2022
DBID AAYXX
CITATION
3V.
7X7
7XB
88E
8FI
8FJ
8FK
ABUWG
AFKRA
AZQEC
BENPR
CCPQU
DWQXO
FYUFA
GHDGH
K9.
M0S
M1P
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
PRINS
7X8
5PM
ADTOC
UNPAY
DOA
DOI 10.3390/s22197324
DatabaseName CrossRef
ProQuest Central (Corporate)
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central
ProQuest Central Essentials
ProQuest Central
ProQuest One Community College
ProQuest Central Korea
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Health & Medical Complete (Alumni)
Health & Medical Collection (Alumni Edition)
Medical Database
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database (Proquest)
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
Unpaywall for CDI: Periodical Content
Unpaywall
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Central China
ProQuest Central
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Health & Medical Research Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
ProQuest Hospital Collection (Alumni)
ProQuest Health & Medical Complete
ProQuest Medical Library
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList
Publicly Available Content Database

CrossRef

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
– sequence: 3
  dbid: BENPR
  name: AUTh Library subscriptions: ProQuest Central
  url: http://www.proquest.com/pqcentral?accountid=15518
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1424-8220
ExternalDocumentID oai_doaj_org_article_8feb243e58774b089adfe924c0796b42
10.3390/s22197324
PMC9572241
A746531902
10_3390_s22197324
GeographicLocations Portugal
Washington, D.C
GeographicLocations_xml – name: Washington, D.C
– name: Portugal
GrantInformation_xml – fundername: FCT—Fundação para a Ciência e a Tecnologia
  grantid: E!114310
GroupedDBID ---
123
2WC
53G
5VS
7X7
88E
8FE
8FG
8FI
8FJ
AADQD
AAHBH
AAYXX
ABDBF
ABUWG
ACUHS
ADBBV
ADMLS
AENEX
AFKRA
AFZYC
ALMA_UNASSIGNED_HOLDINGS
BENPR
BPHCQ
BVXVI
CCPQU
CITATION
CS3
D1I
DU5
E3Z
EBD
ESX
F5P
FYUFA
GROUPED_DOAJ
GX1
HH5
HMCUK
HYE
IAO
ITC
KQ8
L6V
M1P
M48
MODMG
M~E
OK1
OVT
P2P
P62
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQQKQ
PROAC
PSQYO
RNS
RPM
TUS
UKHRP
XSB
~8M
3V.
7XB
8FK
AZQEC
DWQXO
K9.
PKEHL
PQEST
PQUKI
PRINS
7X8
PUEGO
5PM
ADRAZ
ADTOC
IPNFZ
RIG
UNPAY
ID FETCH-LOGICAL-c551t-151a87b2db5ad848abd8dfcf641c481c779cd5a213bd7ae6ab6207ccccfdbf803
IEDL.DBID M48
ISSN 1424-8220
IngestDate Fri Oct 03 12:35:47 EDT 2025
Sun Oct 26 03:24:33 EDT 2025
Tue Sep 30 17:19:07 EDT 2025
Thu Oct 02 10:40:38 EDT 2025
Tue Oct 07 07:35:36 EDT 2025
Mon Oct 20 16:50:14 EDT 2025
Thu Oct 16 04:42:13 EDT 2025
Thu Apr 24 22:53:58 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 19
Language English
License Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
cc-by
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c551t-151a87b2db5ad848abd8dfcf641c481c779cd5a213bd7ae6ab6207ccccfdbf803
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-4065-3415
0000-0002-0027-5157
0000-0002-4234-5336
0000-0001-7279-1890
0000-0003-0385-053X
0000-0002-9445-4809
0000-0002-4022-7424
OpenAccessLink http://journals.scholarsportal.info/openUrl.xqy?doi=10.3390/s22197324
PMID 36236427
PQID 2724312944
PQPubID 2032333
ParticipantIDs doaj_primary_oai_doaj_org_article_8feb243e58774b089adfe924c0796b42
unpaywall_primary_10_3390_s22197324
pubmedcentral_primary_oai_pubmedcentral_nih_gov_9572241
proquest_miscellaneous_2725199734
proquest_journals_2724312944
gale_infotracacademiconefile_A746531902
crossref_primary_10_3390_s22197324
crossref_citationtrail_10_3390_s22197324
PublicationCentury 2000
PublicationDate 20220927
PublicationDateYYYYMMDD 2022-09-27
PublicationDate_xml – month: 9
  year: 2022
  text: 20220927
  day: 27
PublicationDecade 2020
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Sensors (Basel, Switzerland)
PublicationYear 2022
Publisher MDPI AG
MDPI
Publisher_xml – name: MDPI AG
– name: MDPI
References ref_50
Soleimani (ref_5) 2021; 426
ref_14
ref_58
ref_13
ref_56
ref_11
ref_55
ref_10
ref_54
Balcan (ref_19) 2008; 72
ref_51
ref_18
ref_17
ref_16
Gholamiangonabadi (ref_33) 2020; 8
Wang (ref_8) 2019; 119
Gretton (ref_52) 2012; 13
Xu (ref_31) 2019; 7
ref_24
ref_23
ref_22
ref_21
ref_28
Bousquet (ref_20) 2008; 35
ref_27
ref_26
Ahuja (ref_36) 2021; 34
ref_35
ref_34
ref_32
ref_30
Geirhos (ref_15) 2020; 2
ref_39
ref_38
ref_37
Barandas (ref_12) 2020; 11
Ronao (ref_29) 2016; 59
Cabitza (ref_53) 2020; 20
ref_47
ref_46
ref_45
ref_44
Cabitza (ref_25) 2021; 208
ref_43
ref_41
ref_40
ref_1
Shakya (ref_49) 2018; 8
ref_2
Ahmad (ref_3) 2013; 1
ref_48
ref_9
Shoaib (ref_42) 2014; 14
Nakkiran (ref_57) 2021; 2021
ref_4
ref_7
ref_6
References_xml – ident: ref_55
– ident: ref_26
– ident: ref_51
– volume: 59
  start-page: 235
  year: 2016
  ident: ref_29
  article-title: Human activity recognition with smartphone sensors using deep learning neural networks
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2016.04.032
– volume: 8
  start-page: 133982
  year: 2020
  ident: ref_33
  article-title: Deep neural networks for human activity recognition with wearable sensors: Leave-one-subject-out cross-validation for model selection
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.3010715
– volume: 20
  start-page: 1
  year: 2020
  ident: ref_53
  article-title: As if sand were stone. New concepts and metrics to probe the ground on which to build trustable AI
  publication-title: BMC Med. Inform. Decis. Mak.
  doi: 10.1186/s12911-020-01224-9
– volume: 35
  start-page: 1011
  year: 2008
  ident: ref_20
  article-title: Diagnostics of prior-data agreement in applied Bayesian analysis
  publication-title: J. Appl. Stat.
  doi: 10.1080/02664760802192981
– ident: ref_16
– ident: ref_18
  doi: 10.1109/ISCE.2019.8901021
– volume: 426
  start-page: 26
  year: 2021
  ident: ref_5
  article-title: Cross-subject transfer learning in human activity recognition systems using generative adversarial networks
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.10.056
– ident: ref_13
  doi: 10.1109/SMC.2015.263
– ident: ref_27
  doi: 10.1016/j.neucom.2020.09.091
– volume: 34
  start-page: 3438
  year: 2021
  ident: ref_36
  article-title: Invariance principle meets information bottleneck for out-of-distribution generalization
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 1
  start-page: 256
  year: 2013
  ident: ref_3
  article-title: Reviews on various inertial measurement unit (IMU) sensor applications
  publication-title: Int. J. Signal Process. Syst.
  doi: 10.12720/ijsps.1.2.256-262
– ident: ref_39
  doi: 10.1145/3537972.3537996
– ident: ref_41
  doi: 10.1145/2413097.2413148
– ident: ref_58
– ident: ref_34
  doi: 10.3390/s22062360
– volume: 8
  start-page: 577
  year: 2018
  ident: ref_49
  article-title: Comparative study of machine learning and deep learning architecture for human activity recognition using accelerometer data
  publication-title: Int. J. Mach. Learn. Comput.
– ident: ref_23
  doi: 10.3390/e20080592
– volume: 208
  start-page: 106288
  year: 2021
  ident: ref_25
  article-title: The importance of being external. methodological insights for the external validation of machine learning models in medicine
  publication-title: Comput. Methods Programs Biomed.
  doi: 10.1016/j.cmpb.2021.106288
– volume: 7
  start-page: 9893
  year: 2019
  ident: ref_31
  article-title: InnoHAR: A deep neural network for complex human activity recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2890675
– ident: ref_56
– ident: ref_10
– ident: ref_21
  doi: 10.1109/ISBI.2019.8759281
– ident: ref_45
  doi: 10.1186/1475-925X-14-S2-S6
– ident: ref_9
  doi: 10.3390/s21062141
– ident: ref_17
– ident: ref_30
  doi: 10.3390/s21237853
– ident: ref_43
  doi: 10.1371/journal.pone.0075196
– volume: 2021
  start-page: 124003
  year: 2021
  ident: ref_57
  article-title: Deep double descent: Where bigger models and more data hurt
  publication-title: J. Stat. Mech. Theory Exp.
  doi: 10.1088/1742-5468/ac3a74
– ident: ref_7
  doi: 10.1145/3410531.3414311
– ident: ref_14
  doi: 10.1109/ICSENS.2016.7808590
– ident: ref_28
– volume: 14
  start-page: 10146
  year: 2014
  ident: ref_42
  article-title: Fusion of smartphone motion sensors for physical activity recognition
  publication-title: Sensors
  doi: 10.3390/s140610146
– ident: ref_48
  doi: 10.5220/0005699601900197
– ident: ref_2
  doi: 10.3390/s22093401
– ident: ref_11
– volume: 11
  start-page: 100456
  year: 2020
  ident: ref_12
  article-title: TSFEL: Time series feature extraction library
  publication-title: SoftwareX
  doi: 10.1016/j.softx.2020.100456
– ident: ref_46
  doi: 10.1109/PERCOM.2016.7456521
– ident: ref_32
  doi: 10.3390/s21186316
– ident: ref_40
  doi: 10.1109/ISWC.2012.13
– ident: ref_22
  doi: 10.1016/B978-1-78548-236-6.50002-7
– ident: ref_6
  doi: 10.1145/3265689.3265705
– ident: ref_37
– ident: ref_47
  doi: 10.1109/SERVICES.2019.00084
– ident: ref_38
  doi: 10.3390/s21051669
– ident: ref_1
  doi: 10.3390/s19143213
– ident: ref_44
  doi: 10.1007/978-3-319-13105-4
– volume: 13
  start-page: 723
  year: 2012
  ident: ref_52
  article-title: A kernel two-sample test
  publication-title: J. Mach. Learn. Res.
– ident: ref_24
  doi: 10.1371/journal.pone.0237009
– volume: 119
  start-page: 3
  year: 2019
  ident: ref_8
  article-title: Deep learning for sensor-based activity recognition: A survey
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2018.02.010
– ident: ref_54
– ident: ref_50
  doi: 10.1109/ICITR51448.2020.9310792
– ident: ref_35
  doi: 10.3390/s19010057
– ident: ref_4
  doi: 10.3390/s18020679
– volume: 2
  start-page: 665
  year: 2020
  ident: ref_15
  article-title: Shortcut learning in deep neural networks
  publication-title: Nat. Mach. Intell.
  doi: 10.1038/s42256-020-00257-z
– volume: 72
  start-page: 89
  year: 2008
  ident: ref_19
  article-title: A theory of learning with similarity functions
  publication-title: Mach. Learn.
  doi: 10.1007/s10994-008-5059-5
SSID ssj0023338
Score 2.4825788
Snippet Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects,...
SourceID doaj
unpaywall
pubmedcentral
proquest
gale
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Enrichment Source
Index Database
StartPage 7324
SubjectTerms accelerometer
Accuracy
Adaptation
Algorithms
Datasets
Deep learning
domain generalization
human activity recognition
Hypotheses
Neural networks
Sensors
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LbxMxELZQL8AB8RSBUpmHBJdVs7Z37T2mL0VIcKio1Js1fixUSp2oSUD8e2Z2nVWigrg0R-_IcuZhf7Pr-YaxD0G5AKpFC4BWBTqFLKh8syhFaEqBAAFaejXw5Ws9vVCfL6vLrVZfdCespwfuFXdoWsz9lIyVQaDixqaB0EZMGvxYN7VT3e6Lo5tkKqdaEjOvnkdIYlJ_uBQYmFoKtXP6dCT9t7fi29cj76_TAn7_gtls6-w5e8weZdDIJ_1in7B7MT1lD7eoBJ-xn8d9Q8H0nU8hBX9Dzb8DJ4S3xoya4xg_iXHBiY0D5zrvbsDmwqO05Ihd-cn8Gq4Sz0zUuUCT40j3pp9PfN9pgp9vLh3N03N2cXb67Xha5J4KhUdstCrwgAejnQiugmCUARdMaH1bq9IrU3qtGx8qEKV0QUOswdVirD3-2uBaM5Yv2F6ap_iS8RZqg1MECZjVRB2bWMoyKFQ44D7SiBH7tNG19ZlwnPpezCwmHmQWO5hlxN4NooueZeNvQkdksEGAiLG7AXQXm93F_s9dRuwjmdtS-OJiPOQqBPxLRIRlJ5oI5xAloeT-xiNsjuulFRonR4ikcDVvh8cYkfSZBVKcrzuZiq7vSJTRO560s_TdJ-nqR8ft3VSaQNWIvR987t8aeXUXGnnNHggq6aAvbXqf7a1u1vENAq2VO-hi6g_KZyja
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: ProQuest Central
  dbid: BENPR
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwELbK9gAcEE-xpSDzkOASdeM4cXJAaPvSCokVWlGpt2j8SFtpcZZ9FPHvmUmc0FWBHO2R5Xhm7Bl75hvG3lmpLcgKOQBKRigUSUTpm1EsbBELNBCgoquBL9NsciY_n6fnO2za5cJQWGW3JzYbta0N3ZEfCCXwrBOFlJ8WPyKqGkWvq10JDQilFezHBmLsDtsVhIw1YLuHJ9Ovs94FS9Aja_GFEnT2D1YCFVYlQm6dSg14_-0t-nbY5N2NX8CvnzCf3ziTTh-yB8GY5OOW-4_YjvOP2f0bEINP2PVRW2jQX_AJeGuWVBTccrL8Nuhpc2zjx84tOKF04FizJjI2JCT5FUeblh_X3-HK84BQHRI3ObY0LwB8bNoKFHzWBSPV_ik7Oz35djSJQq2FyOCCrSM8-CFXWlidgs1lDtrmtjJVJmMj89goVRibgogTbRW4DHQmRsrgV1ld5aPkGRv42rvnjFeQ5TiETQC9Hadc4eIkthIXHHB_KcSQfejWujQBiJzqYcxLdEiILWXPliF705MuWvSNvxEdEsN6AgLMbhrq5UUZ9K_MK6dRgFyao72rR3kBtnLoe5qRKjItcVLvid0lqTVOxkDITsBfIoCscqwIiA6tJ6Tc7ySiDPq-Kv9I55C97rtRU-n5BbyrNw1NSmE9CdKoLUnamvp2j7-6bDC_i1SRsTVkb3uZ-_eK7P1_ii_YPUFJHPS2pvbZYL3cuJdoWq31q6AvvwFS8Sb1
  priority: 102
  providerName: ProQuest
– databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwELagewAOvBGFBZmHBJdsGseJkxMqu6wqJFZoRaXlFPm5VBSnaptF8OuZSdyoZUFCIkdnYjnxePxNPPMNIS8NV0ZyBzMgBY9AKdII0zejhJkyYQAQpMNfAx9O8smUvz_Lzray-DGsElzxWWukMQsrgh1sFDMWJ2UsYPePF8a9uQj_kpIcNlSsSJdeJXt5Bmh8QPamJx_Hn9ukovB0RyiUgncfrxisUOxmZxtq2fov2-TLcZLXGr-QP77L-XxrEzq-ReRm-F3sydeDZq0O9M_fmB3_5_1uk5sBodJxp1J3yBXr75IbW7yF98jFYVe90J_TifRGL7HSuKEIJxtw3ym00SNrFxSpP6Cv0zbcNmQ5-RUFoEyP6m9y5mmgvQ7ZoBRa2mMFOtZdWQt6uolwqv19Mj1-9-lwEoUCDpEGILaOAE3IQihmVCZNwQupTGGcdjlPNC8SLUSpTSZZkiojpM2lytlIaLicUa4YpQ_IwNfePiTUybyALkwqwYWywpY2SRMDH6eUYLRKNiSvN_NZ6cBujkU25hV4OTj1VT_1Q_K8F110lB5_EnqLStELIAt321Avz6uwqKvCWcV4arMCQLQaFaU0zoJDq0eizBWHQb1ClarQVsBgtAwpD_BKyLpVjQWy2wEkA8n9jdZVwYisKiagc8BjHEbzrL8Nyx_PdKS3ddPKZBgrlIKM2NHWnaHv3vGzLy2ReJkJRHBD8qLX679_kUf_JPWYXGeYIILndmKfDNbLxj4B2LZWT8PK_AV1Wz6h
  priority: 102
  providerName: Unpaywall
Title Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition
URI https://www.proquest.com/docview/2724312944
https://www.proquest.com/docview/2725199734
https://pubmed.ncbi.nlm.nih.gov/PMC9572241
https://www.mdpi.com/1424-8220/22/19/7324/pdf?version=1664336963
https://doaj.org/article/8feb243e58774b089adfe924c0796b42
UnpaywallVersion publishedVersion
Volume 22
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVFSB
  databaseName: Free Full-Text Journals in Chemistry
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: HH5
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: http://abc-chemistry.org/
  providerName: ABC ChemistRy
– providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: KQ8
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: KQ8
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: DOA
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVEBS
  databaseName: EBSCOhost Academic Search Ultimate
  customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: ABDBF
  dateStart: 20081201
  isFulltext: true
  titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn
  providerName: EBSCOhost
– providerCode: PRVEBS
  databaseName: Inspec with Full Text
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: ADMLS
  dateStart: 20081201
  isFulltext: true
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  providerName: EBSCOhost
– providerCode: PRVFQY
  databaseName: GFMER Free Medical Journals
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: GX1
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: http://www.gfmer.ch/Medical_journals/Free_medical.php
  providerName: Geneva Foundation for Medical Education and Research
– providerCode: PRVFQY
  databaseName: GFMER Free Medical Journals
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: GX1
  dateStart: 0
  isFulltext: true
  titleUrlDefault: http://www.gfmer.ch/Medical_journals/Free_medical.php
  providerName: Geneva Foundation for Medical Education and Research
– providerCode: PRVHPJ
  databaseName: ROAD : Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: M~E
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVAQN
  databaseName: PubMed Central
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: RPM
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/
  providerName: National Library of Medicine
– providerCode: PRVPQU
  databaseName: AUTh Library subscriptions: ProQuest Central
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: BENPR
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central Health & Medical Collection (via ProQuest)
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: 7X7
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Technology Collection
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: 8FG
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/technologycollection1
  providerName: ProQuest
– providerCode: PRVFZP
  databaseName: Scholars Portal Journals: Open Access
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 20250930
  omitProxy: true
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: M48
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: http://journals.scholarsportal.info
  providerName: Scholars Portal
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1ZbxMxELZ6SFAeEKcIlMgcErxsyXq9a-8DQukRIqRGVUSk8LTytaVS6k1zAP33zOylRi0v5CEP3pHl9czY36w93xDy3nJtFc9BA0rwAIwiCjB9MwiZTUMGAEHl-GngdJQMJ_zbNJ5ukabGZj2ByztDO6wnNVnMDv5cXX8Bh_-MESeE7J-WDNxOADLYJruwQaVYweGUt4cJLIIwrCIV2hTfI_dg-Y4AgYuNXakk77-9RN--Nnl_7efq-reazW7sSYNH5GENJmm_0v5jsuX8E_LgBsXgU_LrqCo06M_pUHlrFlgU3FJEfmuItCm00WPn5hRZOqCvcXkztk5I8ksKmJYeF5fqwtOaobpO3KTQUp4A0L6pKlDQcXMZqfDPyGRw8v1oGNS1FgIDmGkVwMavpNDM6lhZyaXSVtrc5AkPDZehESI1NlYsjLQVyiVKJ6wnDPxyq3PZi56THV9494LQXCUSurCRgmjHCZe6MAoth7lXsL6krEM-NnOdmZqIHOthzDIISFBDWauhDnnbis4r9o27hA5RYa0AEmaXDcXiPKv9L5O504xHLpaAd3VPpsrmDmJP0xNpojkM6gOqO0NDg8EYVWcnwCshQVbWF0hEB-gJJPcbi8gac82YgM4BOnEYzZv2MXgqHr8o74p1KRPjtZ4IZMSGJW0MffOJv_hZcn6nsUCw1SHvWpv794y8_O_-X5E9hvkdeOwm9snOarF2rwF1rXSXbIupgH85-Nolu4cno7Nxt_yC0S29Ddomo7P-j7-VvDU8
linkProvider Scholars Portal
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZKORQOiKfYUsC8BJeoie3EyQGhpUu1pY9D1Up7S_1KqbQ4231Q9U_xG5nJq10VuDVHZ2Q5nvE84plvCHlvhbZKFMABJUUAQsEDLN8MImaziIGDoAr8NbB_kAyPxfdRPFohv9taGEyrbHVipahtafAf-SaTDGwdy4T4MjkPsGsU3q62LTRqsdh1lxcQss0-7wyAvx8Y2_52tDUMmq4CgQHvYB6AiVOp1MzqWNlUpErb1BamSERkRBoZKTNjY8Uirq1ULlE6YaE08BRWF2nIYd475K7goEvg_MjRVYDHId6r0Ys4z8LNGQN1IDkTSzavag1w0wDcTMpcW_iJurxQ4_E1i7f9kDxoXFXar2XrEVlx_jG5fw3A8An5tVW3MfSndKi8NVNsOW4p-pULiOMpjNGBcxOKGCAw12GVd9uUO_kZBY-ZDsqf6szTBv-6KQulMFLdL9C-qftb0MM21an0T8nxrez5M7LqS--eE1qoJIUpLFcQSznpMhfxyArYcAXaK2M98qnd69w0MOfYbWOcQ7iDbMk7tvTI2450UmN7_I3oKzKsI0A47mqgnJ7mzenO08JpEE8Xp-BN6zDNlC0cRLYmlFmiBSzqI7I7R6UBizGqqX2AT0L4rbwvEeYOfDOg3GglIm-0ySy_kv0eedO9Bj2AlzvKu3JR0cSYNMSBRi5J0tLSl9_4sx8VongWS3TleuRdJ3P_3pH1_y_xNVkbHu3v5Xs7B7svyD2G5SJ4iyc3yOp8unAvwYmb61fVyaHk5LaP6h8I7l_y
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ZbxMxELZKkTgeEKcIFDCX6Msqu17v2vuAUGiIUgoVqqiUt8XXlkrBG3JQ9a_x65jZq40KvDWP9shyPIdn1jPfEPLKcm0VL4ADSvAAhCIOsHwziJjNIgYOgirw08Dn_XR8yD9OkskG-d3WwmBaZWsTK0NtS4PfyPtMMLjrWMZ5v2jSIr4MR-9mPwPsIIUvrW07jVpE9tzpCYRvi7e7Q-D1a8ZGH77ujIOmw0BgwFNYBnDdKSk0szpRVnKptJW2MEXKI8NlZITIjE0Ui2JthXKp0ikLhYFfYXUhwxjWvUKuijjOMJ1QTM6CvRhivxrJCCbD_oKBaRAx42v3X9Um4OJlcDFB8_rKz9TpiZpOz91-o9vkVuO20kEtZ3fIhvN3yc1zYIb3yK-duqWhP6Jj5a2ZY_txS9HHXEFMT2GMDp2bUcQDgbUOqhzcpvTJLyh4z3RY_lDHnjZY2E2JKIWR6q2BDkzd64IetGlPpb9PDi_lzB-QTV9695DQQqUSlrCxgrjKCZe5KI4shwNXYMky1iPb7VnnpoE8x84b0xxCH2RL3rGlR150pLMa5-NvRO-RYR0BQnNXA-X8KG80PZeF0yCqLpHgWetQZsoWDqJcE4os1Rw29QbZnaMBgc0Y1dRBwF9CKK58IBDyDvw0oNxqJSJvLMsiP9ODHnneTYNNwIce5V25qmgSTCCKgUasSdLa1tdn_PH3Cl08SwS6dT3yspO5f5_Io_9v8Rm5Bkqaf9rd33tMbjCsHMEHPbFFNpfzlXsC_txSP60Uh5Jvl62pfwBFlGQ1
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwELagewAOvBGFBZmHBJdsGseJkxMqu6wqJFZoRaXlFPm5VBSnaptF8OuZSdyoZUFCIkdnYjnxePxNPPMNIS8NV0ZyBzMgBY9AKdII0zejhJkyYQAQpMNfAx9O8smUvz_Lzray-DGsElzxWWukMQsrgh1sFDMWJ2UsYPePF8a9uQj_kpIcNlSsSJdeJXt5Bmh8QPamJx_Hn9ukovB0RyiUgncfrxisUOxmZxtq2fov2-TLcZLXGr-QP77L-XxrEzq-ReRm-F3sydeDZq0O9M_fmB3_5_1uk5sBodJxp1J3yBXr75IbW7yF98jFYVe90J_TifRGL7HSuKEIJxtw3ym00SNrFxSpP6Cv0zbcNmQ5-RUFoEyP6m9y5mmgvQ7ZoBRa2mMFOtZdWQt6uolwqv19Mj1-9-lwEoUCDpEGILaOAE3IQihmVCZNwQupTGGcdjlPNC8SLUSpTSZZkiojpM2lytlIaLicUa4YpQ_IwNfePiTUybyALkwqwYWywpY2SRMDH6eUYLRKNiSvN_NZ6cBujkU25hV4OTj1VT_1Q_K8F110lB5_EnqLStELIAt321Avz6uwqKvCWcV4arMCQLQaFaU0zoJDq0eizBWHQb1ClarQVsBgtAwpD_BKyLpVjQWy2wEkA8n9jdZVwYisKiagc8BjHEbzrL8Nyx_PdKS3ddPKZBgrlIKM2NHWnaHv3vGzLy2ReJkJRHBD8qLX679_kUf_JPWYXGeYIILndmKfDNbLxj4B2LZWT8PK_AV1Wz6h
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=Comparing+Handcrafted+Features+and+Deep+Neural+Representations+for+Domain+Generalization+in+Human+Activity+Recognition&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Bento%2C+Nuno&rft.au=Rebelo%2C+Joana&rft.au=Barandas%2C+Mar%C3%ADlia&rft.au=Carreiro%2C+Andr%C3%A9+V.&rft.date=2022-09-27&rft.pub=MDPI&rft.eissn=1424-8220&rft.volume=22&rft.issue=19&rft_id=info:doi/10.3390%2Fs22197324&rft_id=info%3Apmid%2F36236427&rft.externalDocID=PMC9572241
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon