Choose your explanation: a comparison of SHAP and Grad-CAM in human activity recognition

Explaining machine learning (ML) models using eXplainable AI (XAI) techniques has become essential to make them more transparent and trustworthy. This is especially important in high-risk environments like healthcare, where understanding model decisions is critical to ensure ethical, sound, and trus...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Vol. 55; no. 17; p. 1107
Main Authors: Tempel, Felix, Groos, Daniel, Ihlen, Espen Alexander F., Adde, Lars, Strümke, Inga
Format: Journal Article
Language:English
Published: New York Springer US 01.11.2025
Springer Nature B.V
Subjects:
ISSN:0924-669X, 1573-7497
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Explaining machine learning (ML) models using eXplainable AI (XAI) techniques has become essential to make them more transparent and trustworthy. This is especially important in high-risk environments like healthcare, where understanding model decisions is critical to ensure ethical, sound, and trustworthy outcome predictions. However, users are often confused about which explanability method to choose for their specific use case. We present a comparative analysis of two explainability methods, Shapley Additive Explanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM), within the domain of human activity recognition (HAR) utilizing graph convolutional networks (GCNs). By evaluating these methods on skeleton-based input representation from two real-world datasets, including a healthcare-critical cerebral palsy (CP) case, this study provides vital insights into both approaches’ strengths, limitations, and differences, offering a roadmap for selecting the most appropriate explanation method based on specific models and applications. We qualitatively and quantitatively compare the two methods, focusing on feature importance ranking and model sensitivity through perturbation experiments. While SHAP provides detailed input feature attribution, Grad-CAM delivers faster, spatially oriented explanations, making both methods complementary depending on the application’s requirements. Given the importance of XAI in enhancing trust and transparency in ML models, particularly in sensitive environments like healthcare, our research demonstrates how SHAP and Grad-CAM could complement each other to provide model explanations.
AbstractList Explaining machine learning (ML) models using eXplainable AI (XAI) techniques has become essential to make them more transparent and trustworthy. This is especially important in high-risk environments like healthcare, where understanding model decisions is critical to ensure ethical, sound, and trustworthy outcome predictions. However, users are often confused about which explanability method to choose for their specific use case. We present a comparative analysis of two explainability methods, Shapley Additive Explanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM), within the domain of human activity recognition (HAR) utilizing graph convolutional networks (GCNs). By evaluating these methods on skeleton-based input representation from two real-world datasets, including a healthcare-critical cerebral palsy (CP) case, this study provides vital insights into both approaches’ strengths, limitations, and differences, offering a roadmap for selecting the most appropriate explanation method based on specific models and applications. We qualitatively and quantitatively compare the two methods, focusing on feature importance ranking and model sensitivity through perturbation experiments. While SHAP provides detailed input feature attribution, Grad-CAM delivers faster, spatially oriented explanations, making both methods complementary depending on the application’s requirements. Given the importance of XAI in enhancing trust and transparency in ML models, particularly in sensitive environments like healthcare, our research demonstrates how SHAP and Grad-CAM could complement each other to provide model explanations.
ArticleNumber 1107
Author Ihlen, Espen Alexander F.
Strümke, Inga
Groos, Daniel
Tempel, Felix
Adde, Lars
Author_xml – sequence: 1
  givenname: Felix
  orcidid: 0009-0005-6310-408X
  surname: Tempel
  fullname: Tempel, Felix
  email: felix.e.f.tempel@ntnu.no
  organization: Faculty of Informatics, Norwegian University of Science and Technology
– sequence: 2
  givenname: Daniel
  surname: Groos
  fullname: Groos, Daniel
  organization: Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology
– sequence: 3
  givenname: Espen Alexander F.
  surname: Ihlen
  fullname: Ihlen, Espen Alexander F.
  organization: Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology
– sequence: 4
  givenname: Lars
  surname: Adde
  fullname: Adde, Lars
  organization: Department of Clinical and Molecular Medicine, NTNU, Clinic of Rehabilitation, St. Olavs Hospital, Trondheim University Hospital
– sequence: 5
  givenname: Inga
  surname: Strümke
  fullname: Strümke, Inga
  organization: Faculty of Informatics, Norwegian University of Science and Technology
BookMark eNp9kM9LwzAYhoNMcE7_AU8Bz9H8atJ6G0U3YaKgwm4hbZKtY0tq0on77-2s4M3Td3nf5-V7zsHIB28BuCL4hmAsbxPBPC8QphnCohA5YidgTDLJkOSFHIExLihHQhTLM3Ce0gZjzBgmY7As1yEkCw9hH6H9arfa664J_g5qWIddq2OTgofBwdf59AVqb-AsaoPK6RNsPFzvd9pDXXfNZ9MdYLR1WPnmCLgAp05vk738vRPw_nD_Vs7R4nn2WE4XqKZCUkRYVbhMG0uosZhXrnJOMGIJN8Y5ZwQuLGPM5bXL8lpTa6gQ3HJuRFVVTrIJuB64bQwfe5s6telf8f2kYlQyyTNOaZ-iQ6qOIaVonWpjs9PxoAhWR4NqMKh6g-rHoGJ9iQ2l1If9ysY_9D-tbyzBdlg
Cites_doi 10.1109/CIHMCompanion65205.2025.11002697
10.4018/978-1-7998-0134-4.ch006
10.3390/s23020634
10.1109/ICASSP43922.2022.9746621
10.1162/netn_a_00451
10.1109/IECON43393.2020.9254361
10.1007/978-3-030-91608-4_33
10.1109/TPAMI.2022.3157033
10.3934/jdg.2020018
10.1007/s10957-017-1159-3
10.1016/j.dsp.2017.10.011
10.1007/s10479-021-04099-9
10.3934/jdg.2025017
10.1109/TAI.2023.3266418
10.1609/aaai.v32i1.12328
10.1016/S0140-6736(96)10182-3
10.1016/j.media.2018.06.001
10.1109/TNNLS.2020.3027314
10.1109/WACV.2018.00097
10.1016/j.compbiomed.2023.106668
10.48550/arXiv.2101.00905
10.1109/TPAMI.2019.2916873
10.1142/S021848852350040X
10.1109/ACCESS.2024.3377103
10.48550/arXiv.2501.09592
10.3390/s24061940
10.1016/j.jped.2015.12.003
10.1515/9781400829156-012
10.1145/2939672.2939778
10.1109/TPAMI.2022.3209686
10.1145/3394171.3413802
10.1007/s11263-019-01228-7
10.48550/arXiv.1312.6034
10.1016/j.procs.2022.08.105
10.1007/s00521-019-04051-w
10.1109/CVPR.2016.115
10.1016/j.techfore.2025.124265
10.1016/j.artint.2021.103502
10.48550/arXiv.1810.03292
10.1007/978-3-030-99203-3_9
10.1007/s10479-017-2405-7
10.3934/jimo.2023084
10.1016/j.artmed.2023.102616
10.1186/s12916-019-1426-2
10.1016/j.compeleceng.2024.109370
10.1038/s41467-023-44141-x
10.1007/978-3-030-83620-7_7
10.1016/j.compbiomed.2025.109838
10.1001/jamanetworkopen.2022.21325
10.48550/arXiv.2204.11351
10.1016/j.cmpb.2022.107161
10.1016/j.dajour.2023.100230
ContentType Journal Article
Copyright The Author(s) 2025
The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2025
– notice: The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1007/s10489-025-06968-3
DatabaseName Springer Nature OA Free Journals
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList CrossRef

Computer and Information Systems Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1573-7497
ExternalDocumentID 10_1007_s10489_025_06968_3
GrantInformation_xml – fundername: NTNU Norwegian University of Science and Technology (incl St. Olavs Hospital - Trondheim University Hospital)
GroupedDBID -~C
-~X
.86
.DC
.VR
06D
0R~
0VY
1N0
203
23M
2J2
2JN
2JY
2KG
2LR
2~H
30V
4.4
406
408
409
40D
40E
5GY
5VS
67Z
6NX
77I
77K
7WY
8FL
8TC
8UJ
95-
95.
95~
96X
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AAPKM
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
ABAKF
ABBBX
ABBRH
ABBXA
ABDBE
ABDZT
ABECU
ABFSG
ABFTV
ABHLI
ABHQN
ABIVO
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABRTQ
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABWNU
ABXPI
ACAOD
ACDTI
ACGFS
ACHSB
ACHXU
ACIWK
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACSNA
ACSTC
ACZOJ
ADHHG
ADHIR
ADIMF
ADKFA
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEMSY
AENEX
AEOHA
AEPYU
AETLH
AEVLU
AEXYK
AEZWR
AFBBN
AFDZB
AFHIU
AFLOW
AFOHR
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHPBZ
AHSBF
AHWEU
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AIXLP
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARMRJ
ASPBG
ATHPR
AVWKF
AXYYD
AYFIA
AYJHY
AZFZN
B-.
BA0
BENPR
BGNMA
BSONS
C6C
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
EBLON
EBS
EIOEI
ESBYG
FEDTE
FERAY
FFXSO
FIGPU
FNLPD
FRRFC
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ7
GQ8
GXS
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
I09
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K60
K6~
KDC
KOV
LAK
LLZTM
M4Y
MA-
N9A
NB0
NPVJJ
NQJWS
O93
O9G
O9I
O9J
OAM
P19
P2P
P9O
PF0
PT4
PT5
QOK
QOS
R89
R9I
RHV
RNS
ROL
RPX
RSV
S16
S1Z
S27
S3B
SAP
SCO
SDH
SDM
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
TSG
TSK
TSV
TUC
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
YLTOR
Z45
ZMTXR
~A9
~EX
-Y2
1SB
2.D
28-
2P1
2VQ
5QI
8FE
8FG
AAAVM
AAOBN
AARHV
AAYTO
AAYXX
ABJCF
ABQSL
ABULA
ABUWG
ACBXY
ADHKG
AEBTG
AEFIE
AEKMD
AFEXP
AFFHD
AFGCZ
AFKRA
AGGDS
AGQPQ
AJBLW
ARAPS
AZQEC
BBWZM
BDATZ
BEZIV
BGLVJ
BPHCQ
CAG
CCPQU
CITATION
COF
DWQXO
EJD
FINBP
FRNLG
FSGXE
GNUQQ
H13
HCIFZ
K6V
K7-
KOW
L6V
M0C
M7S
N2Q
NDZJH
NU0
O9-
OVD
P62
PHGZM
PHGZT
PQBIZ
PQBZA
PQGLB
PQQKQ
PROAC
PSYQQ
PTHSS
Q2X
R4E
RNI
RZC
RZE
RZK
S26
S28
SCJ
SCLPG
T16
TEORI
ZY4
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c2672-13b9f5ade12de04bfbff631e14ddfffd609e333f8cf58ca2ed2664e44d6bbbf73
IEDL.DBID RSV
ISSN 0924-669X
IngestDate Sat Nov 22 03:12:49 EST 2025
Thu Nov 27 00:52:08 EST 2025
Fri Nov 21 01:12:01 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 17
Keywords HAR
XAI
SHAP
Explainable AI
Human Activity Recognition
Grad-CAM
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2672-13b9f5ade12de04bfbff631e14ddfffd609e333f8cf58ca2ed2664e44d6bbbf73
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0009-0005-6310-408X
OpenAccessLink https://link.springer.com/10.1007/s10489-025-06968-3
PQID 3273745422
PQPubID 326365
ParticipantIDs proquest_journals_3273745422
crossref_primary_10_1007_s10489_025_06968_3
springer_journals_10_1007_s10489_025_06968_3
PublicationCentury 2000
PublicationDate 2025-11-01
PublicationDateYYYYMMDD 2025-11-01
PublicationDate_xml – month: 11
  year: 2025
  text: 2025-11-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
– name: Boston
PublicationSubtitle The International Journal of Research on Intelligent Systems for Real Life Complex Problems
PublicationTitle Applied intelligence (Dordrecht, Netherlands)
PublicationTitleAbbrev Appl Intell
PublicationYear 2025
Publisher Springer US
Springer Nature B.V
Publisher_xml – name: Springer US
– name: Springer Nature B.V
References 6968_CR2
6968_CR14
6968_CR58
6968_CR1
6968_CR15
6968_CR59
6968_CR3
6968_CR11
Z Sadeghi (6968_CR7) 2024; 118
6968_CR57
6968_CR50
6968_CR51
S Ergün (6968_CR33) 2021; 307
G Montavon (6968_CR9) 2018; 73
Q Gao (6968_CR18) 2023; 14
6968_CR26
6968_CR27
S Nazir (6968_CR13) 2023; 156
KN Pellano (6968_CR22) 2024; 24
6968_CR28
6968_CR21
CJ Kelly (6968_CR16) 2019; 17
6968_CR23
6968_CR24
C Einspieler (6968_CR31) 2016; 92
6968_CR20
F Tempel (6968_CR19) 2025; 188
6968_CR60
A Chaddad (6968_CR5) 2023; 23
E Tjoa (6968_CR8) 2021; 32
6968_CR29
6968_CR36
RM Cabral-Carvalho (6968_CR55) 2025; 9
RR Selvaraju (6968_CR25) 2020; 128
6968_CR37
6968_CR38
6968_CR32
HW Loh (6968_CR6) 2022; 226
6968_CR34
6968_CR35
C Einspieler (6968_CR47) 2004
F Tempel (6968_CR42) 2024; 12
6968_CR30
S Parisot (6968_CR39) 2018; 48
K Aas (6968_CR56) 2021; 298
J Allgaier (6968_CR12) 2023; 143
A Vellido (6968_CR17) 2020; 32
S Bharati (6968_CR4) 2024; 5
6968_CR48
6968_CR49
6968_CR43
6968_CR44
6968_CR45
6968_CR40
6968_CR41
A Bessadok (6968_CR54) 2023; 45
HF Prechtl (6968_CR46) 1997; 349
C Molnar (6968_CR53) 2022
V Vishwarupe (6968_CR10) 2022; 204
R Hassan (6968_CR52) 2025; 219
References_xml – ident: 6968_CR43
  doi: 10.1109/CIHMCompanion65205.2025.11002697
– ident: 6968_CR32
  doi: 10.4018/978-1-7998-0134-4.ch006
– volume: 23
  start-page: 634
  issue: 2
  year: 2023
  ident: 6968_CR5
  publication-title: Sensors
  doi: 10.3390/s23020634
– ident: 6968_CR21
  doi: 10.1109/ICASSP43922.2022.9746621
– volume: 9
  start-page: 761
  issue: 2
  year: 2025
  ident: 6968_CR55
  publication-title: Network Neuroscience
  doi: 10.1162/netn_a_00451
– ident: 6968_CR23
  doi: 10.1109/IECON43393.2020.9254361
– ident: 6968_CR11
  doi: 10.1007/978-3-030-91608-4_33
– volume-title: Prechtl’s Method on the Qualitative Assessment of General Movements in Preterm
  year: 2004
  ident: 6968_CR47
– ident: 6968_CR30
  doi: 10.1109/TPAMI.2022.3157033
– ident: 6968_CR36
  doi: 10.3934/jdg.2020018
– ident: 6968_CR37
  doi: 10.1007/s10957-017-1159-3
– volume: 73
  start-page: 1
  year: 2018
  ident: 6968_CR9
  publication-title: Digital Signal Process
  doi: 10.1016/j.dsp.2017.10.011
– volume: 307
  start-page: 127
  year: 2021
  ident: 6968_CR33
  publication-title: Ann Oper Res
  doi: 10.1007/s10479-021-04099-9
– ident: 6968_CR34
  doi: 10.3934/jdg.2025017
– volume: 5
  start-page: 1429
  issue: 4
  year: 2024
  ident: 6968_CR4
  publication-title: IEEE Trans Artif Intell
  doi: 10.1109/TAI.2023.3266418
– ident: 6968_CR45
  doi: 10.1609/aaai.v32i1.12328
– volume: 349
  start-page: 1361
  issue: 9062
  year: 1997
  ident: 6968_CR46
  publication-title: The Lancet
  doi: 10.1016/S0140-6736(96)10182-3
– volume: 48
  start-page: 117
  year: 2018
  ident: 6968_CR39
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2018.06.001
– ident: 6968_CR24
– volume: 32
  start-page: 4793
  issue: 11
  year: 2021
  ident: 6968_CR8
  publication-title: IEEE T Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2020.3027314
– ident: 6968_CR57
  doi: 10.1109/WACV.2018.00097
– volume: 156
  year: 2023
  ident: 6968_CR13
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2023.106668
– ident: 6968_CR50
  doi: 10.48550/arXiv.2101.00905
– ident: 6968_CR1
  doi: 10.1109/TPAMI.2019.2916873
– ident: 6968_CR3
– ident: 6968_CR38
  doi: 10.1142/S021848852350040X
– volume: 12
  start-page: 39505
  year: 2024
  ident: 6968_CR42
  publication-title: IEEE access practical innovations open solutions
  doi: 10.1109/ACCESS.2024.3377103
– ident: 6968_CR60
  doi: 10.48550/arXiv.2501.09592
– volume: 24
  start-page: 1940
  issue: 6
  year: 2024
  ident: 6968_CR22
  publication-title: Sensors
  doi: 10.3390/s24061940
– volume: 92
  start-page: 64
  issue: 3
  year: 2016
  ident: 6968_CR31
  publication-title: Jornal de Pediatria
  doi: 10.1016/j.jped.2015.12.003
– ident: 6968_CR41
  doi: 10.1515/9781400829156-012
– ident: 6968_CR27
  doi: 10.1145/2939672.2939778
– volume: 45
  start-page: 5833
  issue: 5
  year: 2023
  ident: 6968_CR54
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2022.3209686
– ident: 6968_CR20
  doi: 10.1145/3394171.3413802
– volume: 128
  start-page: 336
  issue: 2
  year: 2020
  ident: 6968_CR25
  publication-title: Int J Comput Vision
  doi: 10.1007/s11263-019-01228-7
– ident: 6968_CR26
  doi: 10.48550/arXiv.1312.6034
– volume: 204
  start-page: 869
  year: 2022
  ident: 6968_CR10
  publication-title: Procedia Comput Sci
  doi: 10.1016/j.procs.2022.08.105
– volume: 32
  start-page: 18069
  issue: 24
  year: 2020
  ident: 6968_CR17
  publication-title: Neural Comput Appl
  doi: 10.1007/s00521-019-04051-w
– ident: 6968_CR58
– ident: 6968_CR2
  doi: 10.1109/CVPR.2016.115
– ident: 6968_CR49
– volume: 219
  year: 2025
  ident: 6968_CR52
  publication-title: Technol Forecast Soc Chang
  doi: 10.1016/j.techfore.2025.124265
– volume: 298
  year: 2021
  ident: 6968_CR56
  publication-title: Artif Intell
  doi: 10.1016/j.artint.2021.103502
– ident: 6968_CR29
  doi: 10.48550/arXiv.1810.03292
– volume-title: Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, Second, edition
  year: 2022
  ident: 6968_CR53
– ident: 6968_CR28
  doi: 10.1007/978-3-030-99203-3_9
– ident: 6968_CR40
  doi: 10.1007/s10479-017-2405-7
– ident: 6968_CR35
  doi: 10.3934/jimo.2023084
– volume: 143
  year: 2023
  ident: 6968_CR12
  publication-title: Artifl Intell Med
  doi: 10.1016/j.artmed.2023.102616
– volume: 17
  start-page: 195
  issue: 1
  year: 2019
  ident: 6968_CR16
  publication-title: BMC Med
  doi: 10.1186/s12916-019-1426-2
– volume: 118
  year: 2024
  ident: 6968_CR7
  publication-title: Comput Elect Eng
  doi: 10.1016/j.compeleceng.2024.109370
– ident: 6968_CR59
– volume: 14
  start-page: 8294
  issue: 1
  year: 2023
  ident: 6968_CR18
  publication-title: Nature Commun
  doi: 10.1038/s41467-023-44141-x
– ident: 6968_CR15
  doi: 10.1007/978-3-030-83620-7_7
– volume: 188
  year: 2025
  ident: 6968_CR19
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2025.109838
– ident: 6968_CR48
  doi: 10.1001/jamanetworkopen.2022.21325
– ident: 6968_CR51
  doi: 10.48550/arXiv.2204.11351
– volume: 226
  year: 2022
  ident: 6968_CR6
  publication-title: Comput Methods Prog Biomed
  doi: 10.1016/j.cmpb.2022.107161
– ident: 6968_CR14
  doi: 10.1016/j.dajour.2023.100230
– ident: 6968_CR44
SSID ssj0003301
Score 2.4007807
Snippet Explaining machine learning (ML) models using eXplainable AI (XAI) techniques has become essential to make them more transparent and trustworthy. This is...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Index Database
Publisher
StartPage 1107
SubjectTerms Artificial Intelligence
Artificial neural networks
Computer Science
Datasets
Decision making
Explainable artificial intelligence
Health care
Human activity recognition
Kinematics
Machine learning
Machines
Manufacturing
Mechanical Engineering
Processes
Trustworthiness
Title Choose your explanation: a comparison of SHAP and Grad-CAM in human activity recognition
URI https://link.springer.com/article/10.1007/s10489-025-06968-3
https://www.proquest.com/docview/3273745422
Volume 55
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1573-7497
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003301
  issn: 0924-669X
  databaseCode: RSV
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwELagMLBQnqJQkAc2sJTYju2wVRWlC1VFAXWLHD9EJZRUTUHw73HcpAUEAyij41P02ee7i-_uA-CcBVxyzZymqVAjanGERCQsiiPnixgulHs82QQfDMR4HA-rorCiznavryT9Sf2p2I2W6T1OWlB2dEFkHWw4cydKdbwbPS7PXxehe548F1kgxuJxVSrzs4yv5mjlY367FvXWptf833fugO3Ku4SdxXbYBWsm2wPNmrkBVoq8D8bdpzwvDHx3E6B5mz7LxU_BKyihWjITwtzCUb8zhDLT8GYmNep2buEkg57YD5YlESXzBFwmIeXZAXjoXd93-6jiWEAKM45RSNLYRlKbEGsT0NSm1jISmpBqba3VLIgNIcQKZSOhJDbaWXRqKNUsTVPLySFoZHlmjgB0wZslJgwMJ6lzsrCkLtTiTAWplbGgpgUuaqiT6aKVRrJqmlyCljjQEg9aQlqgXa9GUqlVkRDnbHEaUYxb4LJGfzX8u7Tjv71-ArZwuYC-5rANGvPZizkFm-p1PilmZ367fQDLdc7T
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fS8MwED50Cvri_InTqXnwTQNtkiatb2M4J25juCl7K2mToCCtbFP0vzft2k1FH5Q-pjnKl1zurrm7D-CUO0IKxa2mxa7CzBAP-55vcOBZX0QLP7ZPTjYhej1_NAr6RVHYpMx2L68k85P6U7Eby9J7rDQn6-iC6TKsMGuxskS-28H9_Py1EXrOk2cjC8x5MCpKZX6W8dUcLXzMb9eiubVpVf_3nZuwUXiXqDHbDluwpJNtqJbMDahQ5B0YNR_SdKLRu52A9Nvzk5z9FLxAEsVzZkKUGjRoN_pIJgpdjaXCzUYXPSYoJ_ZDWUlExjyB5klIabILd63LYbONC44FHBMuCHZpFBhPKu0SpR0WmcgYTl3tMqWMMYo7gaaUGj82nh9LopW16EwzpngURUbQPagkaaL3AdngzVDtOlrQyDpZRDIbagkeO5GRgc90Dc5KqMPnWSuNcNE0OQMttKCFOWghrUG9XI2wUKtJSK2zJZjHCKnBeYn-Yvh3aQd_e_0E1trDbifsXPduDmGdZIuZ1x_WoTIdv-gjWI1fp4-T8XG-9T4AhzrRtw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDLZ4CXFhPMVgQA7cIKJN0qTlNg0GCJgm8dBuVdokAgm10zYQ_HuSrt0AwQGhHttYlR3XduPPH8AB94QUiltPS32FmSEBDoPQ4CiwuYgWYWqvgmxCdDphrxd1P6H4i2736khyjGlwU5qy0XFfmeNPwDfmWn2sZM9Nd8F0FuaZIw1y9frtw-RbbKv1gjPPVhmY86hXwmZ-lvE1NE3zzW9HpEXkadf-_84rsFxmnag53iarMKOzNahVjA6odPB16LUe83yo0btdgPRb_1mOfxaeIInSCWMhyg26vWh2kcwUOh9IhVvNG_SUoYLwDzmohGOkQJPmpDzbgPv22V3rApfcCzglXBDs0yQygVTaJ0p7LDGJMZz62mdKGWMU9yJNKTVhaoIwlUQrG-mZZkzxJEmMoJswl-WZ3gJkizpDte9pQRObfBHJbAkmeOolRkYh03U4rNQe98cjNuLpMGWntNgqLS6UFtM6NCrLxKW7DWNqkzDBAkZIHY4qS0xv_y5t-2-P78Ni97QdX192rnZgiThbFrDEBsyNBi96FxbS19HTcLBX7MIPYaPamw
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=Choose+your+explanation%3A+a+comparison+of+SHAP+and+Grad-CAM+in+human+activity+recognition&rft.jtitle=Applied+intelligence+%28Dordrecht%2C+Netherlands%29&rft.au=Tempel%2C+Felix&rft.au=Groos%2C+Daniel&rft.au=Ihlen%2C+Espen+Alexander+F.&rft.au=Adde%2C+Lars&rft.date=2025-11-01&rft.pub=Springer+US&rft.issn=0924-669X&rft.eissn=1573-7497&rft.volume=55&rft.issue=17&rft_id=info:doi/10.1007%2Fs10489-025-06968-3&rft.externalDocID=10_1007_s10489_025_06968_3
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0924-669X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0924-669X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0924-669X&client=summon