Identifying Key Training Load and Intensity Indicators in Ice Hockey Using Unsupervised Machine Learning

To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and heart rate (HR) recording throughout a four-week (29 days) competitive period (23 practice sessions and 8 competitive games in 17 elite Danish p...

Full description

Saved in:
Bibliographic Details
Published inResearch quarterly for exercise and sport Vol. 96; no. 1; pp. 21 - 33
Main Authors Rago, Vincenzo, Fernandes, Tiago, Mohr, Magni
Format Journal Article
LanguageEnglish
Published United States Routledge 02.01.2025
Subjects
Online AccessGet full text

Cover

Loading…
Abstract To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and heart rate (HR) recording throughout a four-week (29 days) competitive period (23 practice sessions and 8 competitive games in 17 elite Danish players (n = 427 observations). Within-individual correlations among accelerometer- (total accelerations [Acc tot ], accelerations >2 m·s −2 [Acc2], total accelerations [Dec tot ], decelerations <- 2 m·s −2 [Dec2]), among HR-derived (time >85% maximum HR [t85%HR max ], Edwards' TL and modified training impulse) TL indicators, and between acceleration- and HR-derived TL parameters were large to almost perfect (r = 0.69-0.99). No significant correlations were observed between accelerometer- and HR-derived intensity indicators. Three between- and two within-components were found. The K-means++ cluster analysis revealed five and four clusters for between- and within-loadings, respectively. The least Euclidean distance from their centroid for each cluster was reported by session-duration, Acc tot , Dec2, TRIMP MOD , %t85HR max for between-loadings, whereas session-duration, Acc2, t85HR max and Dec2/min for within-loadings. Specific TL or intensity variables might be relevant to identify similar between-subject groups (e.g. individual player, playing positions), or temporal patterns (e.g. changes in TL or intensity over time). Our study provides insights about the redundancy associated with the use of multiple TL and intensity variables in ice hockey.
AbstractList To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and heart rate (HR) recording throughout a four-week (29 days) competitive period (23 practice sessions and 8 competitive games in 17 elite Danish players (n = 427 observations). Within-individual correlations among accelerometer- (total accelerations [Acctot], accelerations >2 m·s-2 [Acc2], total accelerations [Dectot], decelerations <- 2 m·s-2 [Dec2]), among HR-derived (time >85% maximum HR [t85%HRmax], Edwards' TL and modified training impulse) TL indicators, and between acceleration- and HR-derived TL parameters were large to almost perfect (r = 0.69-0.99). No significant correlations were observed between accelerometer- and HR-derived intensity indicators. Three between- and two within-components were found. The K-means++ cluster analysis revealed five and four clusters for between- and within-loadings, respectively. The least Euclidean distance from their centroid for each cluster was reported by session-duration, Acctot, Dec2, TRIMPMOD, %t85HRmax for between-loadings, whereas session-duration, Acc2, t85HRmax and Dec2/min for within-loadings. Specific TL or intensity variables might be relevant to identify similar between-subject groups (e.g. individual player, playing positions), or temporal patterns (e.g. changes in TL or intensity over time). Our study provides insights about the redundancy associated with the use of multiple TL and intensity variables in ice hockey.To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and heart rate (HR) recording throughout a four-week (29 days) competitive period (23 practice sessions and 8 competitive games in 17 elite Danish players (n = 427 observations). Within-individual correlations among accelerometer- (total accelerations [Acctot], accelerations >2 m·s-2 [Acc2], total accelerations [Dectot], decelerations <- 2 m·s-2 [Dec2]), among HR-derived (time >85% maximum HR [t85%HRmax], Edwards' TL and modified training impulse) TL indicators, and between acceleration- and HR-derived TL parameters were large to almost perfect (r = 0.69-0.99). No significant correlations were observed between accelerometer- and HR-derived intensity indicators. Three between- and two within-components were found. The K-means++ cluster analysis revealed five and four clusters for between- and within-loadings, respectively. The least Euclidean distance from their centroid for each cluster was reported by session-duration, Acctot, Dec2, TRIMPMOD, %t85HRmax for between-loadings, whereas session-duration, Acc2, t85HRmax and Dec2/min for within-loadings. Specific TL or intensity variables might be relevant to identify similar between-subject groups (e.g. individual player, playing positions), or temporal patterns (e.g. changes in TL or intensity over time). Our study provides insights about the redundancy associated with the use of multiple TL and intensity variables in ice hockey.
To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and heart rate (HR) recording throughout a four-week (29 days) competitive period (23 practice sessions and 8 competitive games in 17 elite Danish players (  = 427 observations). Within-individual correlations among accelerometer- (total accelerations [Acc ], accelerations >2 m·s [Acc2], total accelerations [Dec ], decelerations <- 2 m·s [Dec2]), among HR-derived (time >85% maximum HR [t85%HR ], Edwards' TL and modified training impulse) TL indicators, and between acceleration- and HR-derived TL parameters were large to almost perfect (  = 0.69-0.99). No significant correlations were observed between accelerometer- and HR-derived intensity indicators. Three between- and two within-components were found. The K-means++ cluster analysis revealed five and four clusters for between- and within-loadings, respectively. The least Euclidean distance from their centroid for each cluster was reported by session-duration, Acc , Dec2, TRIMP , %t85HR for between-loadings, whereas session-duration, Acc2, t85HR and Dec2/min for within-loadings. Specific TL or intensity variables might be relevant to identify similar between-subject groups (e.g. individual player, playing positions), or temporal patterns (e.g. changes in TL or intensity over time). Our study provides insights about the redundancy associated with the use of multiple TL and intensity variables in ice hockey.
To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and heart rate (HR) recording throughout a four-week (29 days) competitive period (23 practice sessions and 8 competitive games in 17 elite Danish players (n = 427 observations). Within-individual correlations among accelerometer- (total accelerations [Acc tot ], accelerations >2 m·s −2 [Acc2], total accelerations [Dec tot ], decelerations <- 2 m·s −2 [Dec2]), among HR-derived (time >85% maximum HR [t85%HR max ], Edwards' TL and modified training impulse) TL indicators, and between acceleration- and HR-derived TL parameters were large to almost perfect (r = 0.69-0.99). No significant correlations were observed between accelerometer- and HR-derived intensity indicators. Three between- and two within-components were found. The K-means++ cluster analysis revealed five and four clusters for between- and within-loadings, respectively. The least Euclidean distance from their centroid for each cluster was reported by session-duration, Acc tot , Dec2, TRIMP MOD , %t85HR max for between-loadings, whereas session-duration, Acc2, t85HR max and Dec2/min for within-loadings. Specific TL or intensity variables might be relevant to identify similar between-subject groups (e.g. individual player, playing positions), or temporal patterns (e.g. changes in TL or intensity over time). Our study provides insights about the redundancy associated with the use of multiple TL and intensity variables in ice hockey.
Author Mohr, Magni
Rago, Vincenzo
Fernandes, Tiago
Author_xml – sequence: 1
  givenname: Vincenzo
  orcidid: 0000-0002-9445-4008
  surname: Rago
  fullname: Rago, Vincenzo
  email: vincenzo.rago@universidadeeuropeia.pt
  organization: Universidade Europeia
– sequence: 2
  givenname: Tiago
  orcidid: 0000-0001-5714-410X
  surname: Fernandes
  fullname: Fernandes, Tiago
  organization: Karlsruhe Institute of Technology
– sequence: 3
  givenname: Magni
  orcidid: 0000-0002-1749-8533
  surname: Mohr
  fullname: Mohr, Magni
  organization: University of Southern Denmark
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38959981$$D View this record in MEDLINE/PubMed
BookMark eNp9kUFvEzEQha2qiKaFnwDykcsGj71eOzdQRWlEEJfmvJrYs61hYwd7Q7X_nl0l5chcZkb63tNo3jW7jCkSY-9ALEFY8VFII0A1ZimFrJdSNQIaecEWEhpbKSvrS7aYmWqGrth1KT_FVKDgNbtSdqVXKwsL9rT2FIfQjSE-8m808oeMIc7LJqHnGD1fx4FiCcM4TT44HFIuPES-dsTvk_s1ibZlVmxjOR4o_wmFPP-O7ilE4hvCPPu9Ya867Au9Pfcbtr378nB7X21-fF3fft5UTkE9VCurPVjcOVk3TmuJGsHvlATrAZ11pLzxWjRgANHsrCGixgrhoTYgVa1u2IeT7yGn30cqQ7sPxVHfY6R0LK0SRhshdAMT-v6MHnd78u0hhz3msX35zgToE-ByKiVT9w8B0c4ptC8ptHMK7TmFSffppAuxS3mPzyn3vh1w7FPuMkYXpjv-b_EXXSCNEQ
Cites_doi 10.1007/s40279-017-0830-z
10.1007/978-0-387-95922-1_14
10.1519/jsc.0000000000001999
10.1249/mss.0000000000002370
10.1080/02640410903178344
10.3390/sports9090117
10.1123/ijspp.2018-0571
10.21500/20112084.844
10.1123/ijspp.2021-0188
10.1136/bmj.310.6977.446
10.1348/000711005x67599
10.1186/s40798-019-0202-3
10.5114/biolsport.2023.114282
10.1123/ijspp.2015-0791
10.1080/10691898.2005.11910642
10.1519/jsc.0000000000001611
10.1080/15438627.2021.1954517
10.2165/00007256-200333070-00004
10.1287/inte.1110.0612
10.1093/biomet/87.4.954
10.1519/jsc.0000000000003915
10.1016/0377-0427(87)90125-7
10.1126/science.aaa8415
10.1080/02640414.2017.1306090
10.1519/jsc.0000000000001081
10.1519/JSC.0000000000003324
10.21595/jme.2020.21433
10.1016/j.aca.2004.09.074
10.2478/hukin-2022-000078
10.1123/ijspp.2017-0299
10.1519/jsc.0000000000003490
10.1348/000711007x265894
10.1080/02640410600811817
10.1111/sms.14284
10.1515/hukin-2015-0040
10.1007/s40279-019-01170-1
10.1007/s40279-014-0230-6
ContentType Journal Article
Copyright 2024 SHAPE America 2024
Copyright_xml – notice: 2024 SHAPE America 2024
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1080/02701367.2024.2360162
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
DeliveryMethod fulltext_linktorsrc
Discipline Education
Recreation & Sports
EISSN 2168-3824
EndPage 33
ExternalDocumentID 38959981
10_1080_02701367_2024_2360162
2360162
Genre Research Article
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: Portuguese Foundation for Science and Technology
  grantid: 2021.0581.BD
GroupedDBID ---
-ET
-~X
.QK
0BK
0R~
123
186
29P
2FS
4.4
7RV
85S
8R4
8R5
AADCL
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
AAWTL
ABCCY
ABFIM
ABJNI
ABLIJ
ABLJU
ABPAQ
ABPEM
ABPPZ
ABTAI
ABXUL
ABXYU
ACCUC
ACGFO
ACGFS
ACGOD
ACHQT
ACNCT
ACPRK
ACTIO
ACTOA
ADCVX
ADGTB
ADYSH
AEISY
AEKEX
AENEX
AEYOC
AGDLA
AGMYJ
AHDZW
AHMBA
AIJEM
AKBVH
AKOOK
ALIPV
ALMA_UNASSIGNED_HOLDINGS
ALQZU
ASUFR
AVBZW
AWYRJ
BEJHT
BKOMP
BLC
BLEHA
BMOTO
CCCUG
CJNVE
DGFLZ
DKSSO
DU5
DXH
EBD
EBS
EX3
E~B
E~C
F5P
FJW
G-F
GTTXZ
HF~
HZ~
IPNFZ
KYCEM
LJTGL
M0P
M4Z
NHB
O9-
P2P
PRG
Q2X
RIG
RNANH
ROSJB
RTWRZ
RWL
RXW
S-F
S10
STATR
TAE
TBQAZ
TDBHL
TFL
TFT
TFW
TN5
TNTFI
TRJHH
TTHFI
TUROJ
TWZ
U5U
UHB
UKR
ULE
UMD
UT5
VQA
WH7
WOW
XZL
YCJ
YNT
YR5
ZCA
ZGOLN
~01
~S~
AAGDL
AAHIA
AAYXX
AFRVT
AIYEW
AMPGV
CITATION
DGEBU
H13
NX.
.GJ
0-V
07C
07N
2KS
3EH
3O-
41~
53G
6TJ
7X7
88E
88I
8A4
8AF
8AO
8C1
8FE
8FH
8FI
8FJ
8G5
9M8
AAYJJ
AAYLN
ABBYM
ABGOO
ABUWG
ACBWF
ACLAH
ACOJY
ACSVP
ADBBV
ADXHL
AERWE
AETEA
AFHKK
AFKRA
AFYVU
AGNAY
AIDAL
AIIKL
AIKWM
AJUXI
AKCKI
ALEEW
ALSLI
AMATQ
APROO
ARALO
AYGLJ
AZQEC
BBNVY
BCR
BCU
BEC
BENPR
BHPHI
BKEYQ
BKNYI
BPHCQ
BRMHY
BUAEY
BVXVI
BWQWQ
CCPQU
CGR
CUY
CVF
C~Y
DADXH
DCMBD
DWQXO
D~A
ECM
EIF
EJD
EORKJ
FYUFA
GNUQQ
GUQSH
HCIFZ
HMCUK
HTOLE
IBTYS
K9-
LK8
LPU
M0R
M1P
M2O
M2P
M2Q
M7P
MVM
NAPCQ
NEJ
NPM
NUSFT
OHT
OMK
ONUMK
P-O
PEA
PHGZM
PHGZT
PMFND
PQEDU
PQQKQ
PROAC
PSQYO
S0X
SJFOW
SKT
UAP
UKHRP
ULY
UQL
VJK
XOL
YQJ
YYP
YYQ
ZCG
ZGI
ZHY
ZKB
ZY4
7X8
ID FETCH-LOGICAL-c314t-985d18abc246c552a5a1db3218d1ac8ce3d7d506171aa7b87eee6800d14712343
ISSN 0270-1367
2168-3824
IngestDate Fri Jul 11 07:21:10 EDT 2025
Tue Jun 10 01:31:03 EDT 2025
Tue Jul 01 05:25:37 EDT 2025
Thu Mar 06 04:56:09 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Heart rate
physiology
team sports
wearable technology
tracking
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c314t-985d18abc246c552a5a1db3218d1ac8ce3d7d506171aa7b87eee6800d14712343
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-1749-8533
0000-0002-9445-4008
0000-0001-5714-410X
PMID 38959981
PQID 3075700561
PQPubID 23479
PageCount 13
ParticipantIDs proquest_miscellaneous_3075700561
crossref_primary_10_1080_02701367_2024_2360162
informaworld_taylorfrancis_310_1080_02701367_2024_2360162
pubmed_primary_38959981
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2025-01-02
PublicationDateYYYYMMDD 2025-01-02
PublicationDate_xml – month: 01
  year: 2025
  text: 2025-01-02
  day: 02
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Research quarterly for exercise and sport
PublicationTitleAlternate Res Q Exerc Sport
PublicationYear 2025
Publisher Routledge
Publisher_xml – name: Routledge
References e_1_3_3_30_1
Edwards S. (e_1_3_3_12_1) 1993
e_1_3_3_18_1
e_1_3_3_17_1
e_1_3_3_39_1
e_1_3_3_19_1
e_1_3_3_14_1
e_1_3_3_37_1
e_1_3_3_13_1
e_1_3_3_38_1
e_1_3_3_16_1
e_1_3_3_35_1
e_1_3_3_15_1
e_1_3_3_36_1
e_1_3_3_10_1
e_1_3_3_33_1
e_1_3_3_34_1
e_1_3_3_31_1
e_1_3_3_11_1
e_1_3_3_32_1
e_1_3_3_7_1
e_1_3_3_6_1
e_1_3_3_9_1
e_1_3_3_8_1
e_1_3_3_29_1
e_1_3_3_28_1
e_1_3_3_25_1
e_1_3_3_24_1
e_1_3_3_27_1
e_1_3_3_26_1
e_1_3_3_3_1
e_1_3_3_21_1
e_1_3_3_2_1
e_1_3_3_20_1
e_1_3_3_5_1
e_1_3_3_23_1
e_1_3_3_4_1
e_1_3_3_22_1
References_xml – ident: e_1_3_3_22_1
  doi: 10.1007/s40279-017-0830-z
– ident: e_1_3_3_32_1
  doi: 10.1007/978-0-387-95922-1_14
– ident: e_1_3_3_21_1
  doi: 10.1519/jsc.0000000000001999
– ident: e_1_3_3_35_1
  doi: 10.1249/mss.0000000000002370
– ident: e_1_3_3_38_1
  doi: 10.1080/02640410903178344
– ident: e_1_3_3_16_1
  doi: 10.3390/sports9090117
– ident: e_1_3_3_11_1
  doi: 10.1123/ijspp.2018-0571
– ident: e_1_3_3_10_1
  doi: 10.21500/20112084.844
– ident: e_1_3_3_25_1
  doi: 10.1123/ijspp.2021-0188
– ident: e_1_3_3_6_1
  doi: 10.1136/bmj.310.6977.446
– ident: e_1_3_3_31_1
  doi: 10.1348/000711005x67599
– ident: e_1_3_3_9_1
  doi: 10.1186/s40798-019-0202-3
– ident: e_1_3_3_24_1
  doi: 10.5114/biolsport.2023.114282
– ident: e_1_3_3_5_1
  doi: 10.1123/ijspp.2015-0791
– ident: e_1_3_3_15_1
  doi: 10.1080/10691898.2005.11910642
– ident: e_1_3_3_34_1
  doi: 10.1519/jsc.0000000000001611
– ident: e_1_3_3_23_1
  doi: 10.1080/15438627.2021.1954517
– ident: e_1_3_3_2_1
  doi: 10.2165/00007256-200333070-00004
– ident: e_1_3_3_8_1
  doi: 10.1287/inte.1110.0612
– ident: e_1_3_3_39_1
  doi: 10.1093/biomet/87.4.954
– ident: e_1_3_3_27_1
  doi: 10.1519/jsc.0000000000003915
– ident: e_1_3_3_28_1
  doi: 10.1016/0377-0427(87)90125-7
– ident: e_1_3_3_19_1
  doi: 10.1126/science.aaa8415
– ident: e_1_3_3_20_1
  doi: 10.1080/02640414.2017.1306090
– ident: e_1_3_3_30_1
  doi: 10.1519/jsc.0000000000001081
– ident: e_1_3_3_4_1
  doi: 10.1519/JSC.0000000000003324
– ident: e_1_3_3_13_1
  doi: 10.21595/jme.2020.21433
– ident: e_1_3_3_17_1
  doi: 10.1016/j.aca.2004.09.074
– ident: e_1_3_3_26_1
  doi: 10.2478/hukin-2022-000078
– ident: e_1_3_3_18_1
  doi: 10.1123/ijspp.2017-0299
– start-page: 113
  volume-title: The heart rate monitor book
  year: 1993
  ident: e_1_3_3_12_1
– ident: e_1_3_3_3_1
  doi: 10.1519/jsc.0000000000003490
– ident: e_1_3_3_33_1
  doi: 10.1348/000711007x265894
– ident: e_1_3_3_29_1
  doi: 10.1080/02640410600811817
– ident: e_1_3_3_36_1
  doi: 10.1111/sms.14284
– ident: e_1_3_3_7_1
  doi: 10.1515/hukin-2015-0040
– ident: e_1_3_3_14_1
  doi: 10.1007/s40279-019-01170-1
– ident: e_1_3_3_37_1
  doi: 10.1007/s40279-014-0230-6
SSID ssj0000131
Score 2.411338
Snippet To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and...
SourceID proquest
pubmed
crossref
informaworld
SourceType Aggregation Database
Index Database
Publisher
StartPage 21
SubjectTerms Acceleration
Accelerometry
Adult
Athletic Performance - physiology
Competitive Behavior - physiology
Heart rate
Heart Rate - physiology
Hockey - physiology
Humans
Machine Learning
Male
Physical Conditioning, Human - methods
Physical Conditioning, Human - physiology
physiology
team sports
tracking
Wearable Electronic Devices
wearable technology
Young Adult
Title Identifying Key Training Load and Intensity Indicators in Ice Hockey Using Unsupervised Machine Learning
URI https://www.tandfonline.com/doi/abs/10.1080/02701367.2024.2360162
https://www.ncbi.nlm.nih.gov/pubmed/38959981
https://www.proquest.com/docview/3075700561
Volume 96
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Lb9MwGLdgu3BBUF7lJSMhLlWqObYT54jQpm6UIaEU7RY5jtvlkkxretlfz-dXkqIiBpeocusm6u_nr9_7Q-gjUTQVFZMRvHsSsZSDHEw0jUqa6hMmiWK2jvvbZbJYsYsrPgq02-qSrpyru4N1Jf-DKqwBrqZK9h-Q7b8UFuA14AtXQBiu98LYVdm6SqWvcLhzP-9htmxl5TN9bYY6aNrnjYnI2Nk6dTM7h-O8aM0JnrmkgVWz3d0YubHVJvHCZFjq0Hx1M9ZgQ6qeKcd06aCua7gf3WTvak3lIYK0se7YnzXwq7lrf_dguzylGj7Vg99e37o6ok1Tj90SMbduiZGnMiaJiKhwBdJzfWDNi1830HaPZkGWHhTxPicyTm23ObDwYzaPqekqEw__aSGOf_m9OFstl0V-epU_RMcx2BIgDI_zHxeLxajLmB1b2T9dKPQyLdgP3WZPhdlrcPtnM8WqK_kT9NjbGfizI81T9EA3EzOi26fzTNBkMBjwJ2yH3W-foesRpTBQCgdKYUMpDHjhnlJ4oBSuGwyUwo5S2FIKjymFPaVwoNRztDo7zb8sIj-MI1KUsC7KBK-IkKWKWaI4jyWXpCopaIgVkUooTau04kYhJlKmpUi11glYIxUB9SemjL5AR03b6FcIU840CHsNYkAwlmSZWnO1pjQB1VioREzRPPy-xY3ruVKQ0MrWA1IYQAoPyBRlYxSKzjq71m4yTUH_svdDgKwAyWrCZbLR7Q72gTad2la5U_TSYdk_Dqj5PMsEeX2P3W_Qo-GAvEVH3e1OvwNNtivfeyb-AhIvmoA
linkProvider Taylor & Francis
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6V7QEuPJbX8jQScMtSvxLnwKHqQ9l2twe0K_UWHNsLVaVsxWaFys_ir_CHGDtOaStVPVQ9cIsUORl7Hp6xZ74BeE8Nz5QVOsG3G4nIJNrB1PGk4pnbEJoaEeq4JwdpMRN7h_JwDX53tTA-rdLH0PMWKCLYaq_c_jC6S4n7hKFUgBrD8I6JIeMeUoTFxMp9d_oTw7bl59E28vgDY7s7060iiZ0FEsOpaJJcSUuVrgwTqZGSaamprThud5Zqo4zjNrPS7-5U66xSmXMuRdfKUrTljAuO370D6zIXXPVgffplryjOgVa1XRCRyMRT2dUNXUX4hR3xAl7q1V5v2P12H8Cfbt3apJfj4aqphubXJUjJ_2thH8L96IyTzVZ7HsGaq_u-j3XMeelD_59XTT6S0BF--Ri-t9XNoUKMIMFkGvtskPFCW4LTJ7EyoDnFJ38T5nsakaOajIwjxcJbThKSNcisXq5OvL1eOksmIbPVkQh6--0JzG5l-k-hVy9q9xwIl8KhRXSoKwpD9jw3c2nmnKfoPyqTqgEMO6kpT1pgkpJ2eK-RjaVnYxnZOID8vGyVTTgRmrftW0p-zdh3nSCWaH78nZKu3WKF49DlzAKe7ACetRJ6Rg76whKjefriBn9-C3eL6WRcjkcH-y_hHvPdl_0BGHsFvebHyr1Gl7Cp3kQdJPD1tqXzL9nFX9o
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwEB4tXQlx4VFe5TlIwC1l_UrSAwfEUqX7EkKttLfg2A4gpLSiqdDyr_gr_CLGjgO7SCsOaA_cIkVOxp6HZ-yZbwCeMiOy3Eqd0NudRGaK7GDqRFKJzO1IzYwMddyHR2mxkHvH6ngLvve1MD6t0sfQdQcUEWy1V-6VrfuMuBcUSQWkMYruuBxz4RFFeMyr3HcnXylqW7-c7RKLn3E-fTN_XSSxsUBiBJNtMsmVZbmuDJepUYprpZmtBO12lmmTGydsZpXf3JnWWZVnzrmUPCvLyJRzIQV99xJspx5-bwDb83d7RXEKs6prgkhEJp7KvmzoPMLPbIhn4FLPd3rD5je9Bj_6ZetyXj6PN201Nt_-QJT8r9b1OlyNrji-6nTnBmy5Zui7WMeMlyEMf_vU-BxDP_j1TfjY1TaH-jAkgnEeu2zgwVJbpNljrAtoT-jJ34P5jkb4qcGZcVgsvd3EkKqBi2a9WXlrvXYWD0Neq8MIefvhFiwuZPq3YdAsG3cXUCjpyB460pScAvbJxNTK1EKk5D3mJs1HMO6Fplx1sCQl69FeIxtLz8YysnEEk9OiVbbhPKjumreU4i9jn_RyWJLx8TdKunHLDY0jhzMLaLIjuNMJ6C9yyBNWFMuze__w58dw-e3utDyYHe3fhyvct172p1_8AQzaLxv3kPzBtnoUNRDh_UUL50__jF5-
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=Identifying+Key+Training+Load+and+Intensity+Indicators+in+Ice+Hockey+Using+Unsupervised+Machine+Learning&rft.jtitle=Research+quarterly+for+exercise+and+sport&rft.au=Rago%2C+Vincenzo&rft.au=Fernandes%2C+Tiago&rft.au=Mohr%2C+Magni&rft.date=2025-01-02&rft.issn=2168-3824&rft.eissn=2168-3824&rft.volume=96&rft.issue=1&rft.spage=21&rft_id=info:doi/10.1080%2F02701367.2024.2360162&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0270-1367&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0270-1367&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0270-1367&client=summon