Nonnegative decomposition of functional count data

We present a novel decomposition of nonnegative functional count data that draws on concepts from nonnegative matrix factorization. Our decomposition, which we refer to as NARFD (nonnegative and regularized function decomposition), enables the study of patterns in variation across subjects in a high...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Biometrics Ročník 76; číslo 4; s. 1273 - 1284
Hlavní autoři: Backenroth, Daniel, Shinohara, Russell T., Schrack, Jennifer A., Goldsmith, Jeff
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Blackwell Publishing Ltd 01.12.2020
Témata:
ISSN:0006-341X, 1541-0420, 1541-0420
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We present a novel decomposition of nonnegative functional count data that draws on concepts from nonnegative matrix factorization. Our decomposition, which we refer to as NARFD (nonnegative and regularized function decomposition), enables the study of patterns in variation across subjects in a highly interpretable manner. Prototypic modes of variation are estimated directly on the observed scale of the data, are local, and are transparently added together to reconstruct observed functions. This contrasts with generalized functional principal component analysis, an alternative approach that estimates functional principal components on a transformed scale, produces components that typically vary across the entire functional domain, and reconstructs observations using complex patterns of cancellation and multiplication of functional principal components. NARFD is implemented using an alternating minimization algorithm, and we evaluate our approach in simulations. We apply NARFD to an accelerometer dataset comprising observations of physical activity for healthy older Americans.
AbstractList We present a novel decomposition of nonnegative functional count data that draws on concepts from nonnegative matrix factorization. Our decomposition, which we refer to as NARFD (nonnegative and regularized function decomposition), enables the study of patterns in variation across subjects in a highly interpretable manner. Prototypic modes of variation are estimated directly on the observed scale of the data, are local, and are transparently added together to reconstruct observed functions. This contrasts with generalized functional principal component analysis, an alternative approach that estimates functional principal components on a transformed scale, produces components that typically vary across the entire functional domain, and reconstructs observations using complex patterns of cancellation and multiplication of functional principal components. NARFD is implemented using an alternating minimization algorithm, and we evaluate our approach in simulations. We apply NARFD to an accelerometer dataset comprising observations of physical activity for healthy older Americans.
We present a novel decomposition of nonnegative functional count data that draws on concepts from nonnegative matrix factorization. Our decomposition, which we refer to as NARFD (nonnegative and regularized function decomposition), enables the study of patterns in variation across subjects in a highly interpretable manner. Prototypic modes of variation are estimated directly on the observed scale of the data, are local, and are transparently added together to reconstruct observed functions. This contrasts with generalized functional principal component analysis, an alternative approach that estimates functional principal components on a transformed scale, produces components that typically vary across the entire functional domain, and reconstructs observations using complex patterns of cancellation and multiplication of functional principal components. NARFD is implemented using an alternating minimization algorithm, and we evaluate our approach in simulations. We apply NARFD to an accelerometer dataset comprising observations of physical activity for healthy older Americans.
We present a novel decomposition of nonnegative functional count data that draws on concepts from nonnegative matrix factorization. Our decomposition, which we refer to as NARFD (nonnegative and regularized function decomposition), enables the study of patterns in variation across subjects in a highly interpretable manner. Prototypic modes of variation are estimated directly on the observed scale of the data, are local, and are transparently added together to reconstruct observed functions. This contrasts with generalized functional principal component analysis, an alternative approach that estimates functional principal components on a transformed scale, produces components that typically vary across the entire functional domain, and reconstructs observations using complex patterns of cancellation and multiplication of functional principal components. NARFD is implemented using an alternating minimization algorithm, and we evaluate our approach in simulations. We apply NARFD to an accelerometer dataset comprising observations of physical activity for healthy older Americans.We present a novel decomposition of nonnegative functional count data that draws on concepts from nonnegative matrix factorization. Our decomposition, which we refer to as NARFD (nonnegative and regularized function decomposition), enables the study of patterns in variation across subjects in a highly interpretable manner. Prototypic modes of variation are estimated directly on the observed scale of the data, are local, and are transparently added together to reconstruct observed functions. This contrasts with generalized functional principal component analysis, an alternative approach that estimates functional principal components on a transformed scale, produces components that typically vary across the entire functional domain, and reconstructs observations using complex patterns of cancellation and multiplication of functional principal components. NARFD is implemented using an alternating minimization algorithm, and we evaluate our approach in simulations. We apply NARFD to an accelerometer dataset comprising observations of physical activity for healthy older Americans.
Author Backenroth, Daniel
Schrack, Jennifer A.
Shinohara, Russell T.
Goldsmith, Jeff
Author_xml – sequence: 1
  givenname: Daniel
  orcidid: 0000-0002-9581-8870
  surname: Backenroth
  fullname: Backenroth, Daniel
  email: daniel.backenroth@gmail.com
  organization: Columbia University
– sequence: 2
  givenname: Russell T.
  orcidid: 0000-0001-8627-8203
  surname: Shinohara
  fullname: Shinohara, Russell T.
  organization: University of Pennsylvania
– sequence: 3
  givenname: Jennifer A.
  surname: Schrack
  fullname: Schrack, Jennifer A.
  organization: Johns Hopkins Bloomberg School of Public Health
– sequence: 4
  givenname: Jeff
  surname: Goldsmith
  fullname: Goldsmith, Jeff
  organization: Columbia University
BackLink https://www.ncbi.nlm.nih.gov/pubmed/31970756$$D View this record in MEDLINE/PubMed
BookMark eNqFkUtLxDAUhYMoOo5u_AFScCNCNblJWrNU8QU-NgruQprcSqRtxqZV_PdmnHEjoneTG_jOgXvOJlntQoeE7DB6yNIcVT60h4wD0BUyYVKwnAqgq2RCKS1yLtjTBtmM8SV9laSwTjY4UyUtZTEhcBe6Dp_N4N8wc2hDOwvRDz50WaizeuzsfDdNZsPYDZkzg9kia7VpIm4v3yl5vDh_OLvKb-4vr89ObnIrFNC8hGOsDRfcgaotqgKdQcEqcKKy6IShTEhVWigcSKwlrwxYpWyJUjjJkU_J_sJ31ofXEeOgWx8tNo3pMIxRgwQBJUjG_0e5EADqWJYJ3fuBvoSxTxcmShQqmaYgE7W7pMaqRadnvW9N_6G_g0sAXQC2DzH2WGvrBzPPauiNbzSjet6Nnnejv7pJkoMfkm_XX2G2gN99gx9_kPr0-v52ofkERdWdKg
CitedBy_id crossref_primary_10_3390_s21041545
crossref_primary_10_1007_s10182_025_00531_8
crossref_primary_10_1111_sjos_12719
crossref_primary_10_1111_rssb_12543
Cites_doi 10.1111/j.2517-6161.1964.tb00553.x
10.1214/009053604000001156
10.1093/biostatistics/kxt029
10.1111/j.1541-0420.2012.01808.x
10.1111/biom.12083
10.1093/biomet/asn010
10.1145/1102351.1102451
10.1093/gerona/glt199
10.1007/978-0-387-21706-2
10.1198/106186002853
10.1198/016214504000001745
10.1007/s10182-009-0113-6
10.1137/0916069
10.1214/08-AOAS206
10.1146/annurev-statistics-041715-033624
10.1016/j.neuroimage.2014.11.045
10.1111/biom.12963
10.1214/18-AOAS1135
10.1109/TKDE.2012.51
10.1111/j.1467-9868.2010.00749.x
10.1007/s00421-005-0112-6
10.1109/ASPAA.2003.1285860
10.1111/j.1467-9868.2008.00656.x
10.1016/j.csda.2016.07.010
10.1111/biom.12278
10.1038/44565
10.1561/2200000055
10.1109/TSP.2013.2285514
ContentType Journal Article
Copyright 2020 The International Biometric Society
2020 The International Biometric Society.
Copyright_xml – notice: 2020 The International Biometric Society
– notice: 2020 The International Biometric Society.
DBID AAYXX
CITATION
NPM
JQ2
7X8
7S9
L.6
DOI 10.1111/biom.13220
DatabaseName CrossRef
PubMed
ProQuest Computer Science Collection
MEDLINE - Academic
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
PubMed
ProQuest Computer Science Collection
MEDLINE - Academic
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList
AGRICOLA
ProQuest Computer Science Collection
PubMed
MEDLINE - Academic
CrossRef
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Statistics
Biology
Mathematics
EISSN 1541-0420
EndPage 1284
ExternalDocumentID 31970756
10_1111_biom_13220
BIOM13220
Genre article
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: National Heart, Lung, and Blood Institute
  funderid: R01HL123407
– fundername: National Institute of Biomedical Imaging and Bioengineering
  funderid: R21EB018917
– fundername: National Institute of Mental Health
  funderid: R01MH112847
– fundername: National Institute of Neurological Disorders and Stroke
  funderid: R01NS097423‐01; R01NS060910; R01NS085211; R21NS93349
– fundername: NHLBI NIH HHS
  grantid: R01 HL123407
– fundername: NIBIB NIH HHS
  grantid: R21 EB018917
– fundername: NINDS NIH HHS
  grantid: R01 NS085211
– fundername: NIMH NIH HHS
  grantid: R01 MH112847
– fundername: NINDS NIH HHS
  grantid: R01 NS060910
– fundername: NINDS NIH HHS
  grantid: R21 NS093349
– fundername: NINDS NIH HHS
  grantid: R01 NS097423
GroupedDBID ---
-~X
.3N
.4S
.DC
.GA
.GJ
.Y3
05W
0R~
10A
1OC
23N
2AX
2QV
3-9
31~
33P
36B
3SF
3V.
4.4
44B
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
53G
5GY
5HH
5LA
5RE
5VS
66C
6J9
702
7PT
7X7
8-0
8-1
8-3
8-4
8-5
88E
88I
8AF
8C1
8FE
8FG
8FH
8FI
8FJ
8R4
8R5
8UM
930
A03
A8Z
AAESR
AAEVG
AAHBH
AAHHS
AANHP
AANLZ
AAONW
AASGY
AAUAY
AAXRX
AAYCA
AAZKR
AAZSN
ABBHK
ABCQN
ABCUV
ABDBF
ABDFA
ABEJV
ABEML
ABFAN
ABJCF
ABJNI
ABLJU
ABMNT
ABPPZ
ABPVW
ABTAH
ABUWG
ABXSQ
ABXVV
ABYWD
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFO
ACGFS
ACGOD
ACIWK
ACKIV
ACMTB
ACNCT
ACPOU
ACPRK
ACRPL
ACSCC
ACTMH
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIPN
ADIZJ
ADKYN
ADMGS
ADNMO
ADODI
ADOZA
ADULT
ADVOB
ADXAS
ADZMN
ADZOD
AEEZP
AEGXH
AEIGN
AEIMD
AELPN
AENEX
AEQDE
AEUPB
AEUQT
AEUYR
AFBPY
AFDVO
AFEBI
AFFTP
AFGKR
AFKRA
AFPWT
AFVYC
AFWVQ
AFZJQ
AGTJU
AHMBA
AIAGR
AIBGX
AIURR
AIWBW
AJAOE
AJBDE
AJXKR
ALAGY
ALEEW
ALIPV
ALMA_UNASSIGNED_HOLDINGS
ALRMG
ALUQN
AMBMR
AMYDB
APXXL
ARAPS
ARCSS
ASPBG
AS~
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZQEC
AZVAB
BAFTC
BBNVY
BCRHZ
BDRZF
BENPR
BFHJK
BGLVJ
BHBCM
BHPHI
BMNLL
BMXJE
BNHUX
BPHCQ
BROTX
BRXPI
BVXVI
BY8
CAG
CCPQU
COF
CS3
D-E
D-F
DCZOG
DPXWK
DQDLB
DR2
DRFUL
DRSTM
DSRWC
DWQXO
DXH
EAD
EAP
EBC
EBD
EBS
ECEWR
EDO
EJD
EMB
EMK
EMOBN
EST
ESX
F00
F01
F04
F5P
FD6
FEDTE
FXEWX
FYUFA
G-S
G.N
GNUQQ
GODZA
GS5
H.T
H.X
HCIFZ
HF~
HGD
HMCUK
HQ6
HVGLF
HZI
HZ~
IHE
IPSME
IX1
J0M
JAAYA
JAC
JBMMH
JBZCM
JENOY
JHFFW
JKQEH
JLEZI
JLXEF
JMS
JPL
JSODD
JST
K48
K6V
K7-
KOP
L6V
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LK8
LOXES
LP6
LP7
LUTES
LW6
LYRES
M1P
M2P
M7P
M7S
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MVM
MXFUL
MXSTM
N04
N05
N9A
NF~
NHB
NU-
O66
O9-
OIG
OJZSN
OWPYF
P0-
P2P
P2W
P2X
P4D
P62
PQQKQ
PROAC
PSQYO
PTHSS
Q.N
Q11
Q2X
QB0
R.K
RNS
ROL
ROX
RWL
RX1
RXW
SA0
SUPJJ
SV3
TAE
TN5
TUS
UAP
UB1
UKHRP
V8K
VQA
W8V
W99
WBKPD
WH7
WIH
WIK
WOHZO
WQJ
WRC
WYISQ
X6Y
XBAML
XG1
XSW
ZGI
ZXP
ZY4
ZZTAW
~02
~IA
~KM
~WT
AAMMB
AAWIL
AAYXX
ABAWQ
ABGNP
ACHJO
ADNBA
AEFGJ
AEOTA
AFFHD
AGLNM
AGQPQ
AGXDD
AHGBF
AIDQK
AIDYY
AIHAF
AJBYB
AJNCP
CITATION
H13
O8X
PHGZM
PHGZT
PJZUB
PPXIY
PQGLB
NPM
PKN
AGORE
JQ2
7X8
ESTFP
7S9
L.6
ID FETCH-LOGICAL-c4920-728efa343d29fce96edae41b2d4bced4a014597c26d25ef53ba2c99c7e54d53e3
IEDL.DBID DRFUL
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000510500300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0006-341X
1541-0420
IngestDate Fri Oct 03 00:10:39 EDT 2025
Sat Sep 27 22:19:40 EDT 2025
Wed Aug 13 08:35:24 EDT 2025
Wed Feb 19 02:29:49 EST 2025
Sat Nov 29 02:10:07 EST 2025
Tue Nov 18 20:51:18 EST 2025
Wed Jan 22 16:31:05 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords accelerometers
nonnegative matrix factorization
functional data
Language English
License 2020 The International Biometric Society.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4920-728efa343d29fce96edae41b2d4bced4a014597c26d25ef53ba2c99c7e54d53e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-8627-8203
0000-0002-9581-8870
OpenAccessLink https://www.ncbi.nlm.nih.gov/pmc/articles/7375931
PMID 31970756
PQID 2469252322
PQPubID 35366
PageCount 12
ParticipantIDs proquest_miscellaneous_2524272513
proquest_miscellaneous_2344229857
proquest_journals_2469252322
pubmed_primary_31970756
crossref_citationtrail_10_1111_biom_13220
crossref_primary_10_1111_biom_13220
wiley_primary_10_1111_biom_13220_BIOM13220
PublicationCentury 2000
PublicationDate December 2020
PublicationDateYYYYMMDD 2020-12-01
PublicationDate_xml – month: 12
  year: 2020
  text: December 2020
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Washington
PublicationTitle Biometrics
PublicationTitleAlternate Biometrics
PublicationYear 2020
Publisher Blackwell Publishing Ltd
Publisher_xml – name: Blackwell Publishing Ltd
References 2006; 96
2013; 69
2013; 25
2012
2015; 71
2019; 75
1995; 16
2013; 62
2002; 11
2014; 69
2003; 16
2014; 24
2005
2015; 108
1964; 26
2003
2002
2012; 13
2008; 95
2008; 70
1999; 401
2016; 3
2001
2005; 100
2009; 93
2011; 73
2014; 15
2017
2016
2009; 4
2018; 12
2005; 33
2017; 105
2016; 9
e_1_2_8_28_1
e_1_2_8_29_1
e_1_2_8_24_1
e_1_2_8_25_1
Donoho D.L. (e_1_2_8_10_1) 2003; 16
e_1_2_8_26_1
e_1_2_8_27_1
Du P. (e_1_2_8_11_1) 2014; 24
e_1_2_8_3_1
Ypma J. (e_1_2_8_37_1) 2017
e_1_2_8_2_1
e_1_2_8_7_1
e_1_2_8_6_1
e_1_2_8_9_1
e_1_2_8_8_1
e_1_2_8_21_1
e_1_2_8_22_1
e_1_2_8_23_1
Gillis N. (e_1_2_8_13_1) 2012; 13
e_1_2_8_17_1
e_1_2_8_18_1
e_1_2_8_19_1
e_1_2_8_36_1
e_1_2_8_14_1
e_1_2_8_35_1
e_1_2_8_15_1
e_1_2_8_16_1
Lin X. (e_1_2_8_20_1) 2016
Box G.E.P. (e_1_2_8_5_1) 1964; 26
e_1_2_8_32_1
e_1_2_8_31_1
e_1_2_8_34_1
Bertsekas D.P. (e_1_2_8_4_1) 2012
e_1_2_8_12_1
e_1_2_8_33_1
e_1_2_8_30_1
References_xml – volume: 69
  start-page: 973
  year: 2014
  end-page: 979
  article-title: Assessing the “physical cliff”: detailed quantification of aging and physical activity
  publication-title: Journal of Gerontology: Medical Sciences
– volume: 33
  start-page: 774
  year: 2005
  end-page: 805
  article-title: Generalized functional linear models
  publication-title: Annals of Statistics
– volume: 401
  start-page: 788
  year: 1999
  end-page: 791
  article-title: Learning the parts of objects by non‐negative matrix factorization
  publication-title: Nature
– start-page: 85
  year: 2012
  end-page: 120
– volume: 73
  start-page: 3
  year: 2011
  end-page: 36
  article-title: Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models
  publication-title: Journal of the Royal Statistical Society: Series B
– start-page: 1
  year: 2005
  end-page: 4
  article-title: First results on uniqueness of sparse non‐negative matrix factorization
– start-page: 617
  year: 2001
  end-page: 624
– start-page: 792
  year: 2005
  end-page: 799
  article-title: Non‐negative tensor factorization with applications to statistics and computer vision
– volume: 96
  start-page: 517
  year: 2006
  end-page: 524
  article-title: Effect of combined movement and heart rate monitor placement on physical activity estimates during treadmill locomotion and free‐living
  publication-title: European Journal of Applied Physiology
– volume: 16
  start-page: 1190
  year: 1995
  end-page: 1208
  article-title: A limited memory algorithm for bound constrained optimization
  publication-title: SIAM Journal on Scientific Computing
– volume: 24
  start-page: 1017
  year: 2014
  end-page: 1041
  article-title: Penalized likelihood functional regression
  publication-title: Statistica Sinica
– volume: 69
  start-page: 903
  year: 2013
  end-page: 913
  article-title: Multilevel cross‐dependent binary longitudinal data
  publication-title: Biometrics
– volume: 75
  start-page: 48
  year: 2019
  end-page: 57
  article-title: Registration for exponential family functional data
  publication-title: Biometrics
– year: 2016
– volume: 13
  start-page: 3349
  year: 2012
  end-page: 3386
  article-title: Sparse and unique nonnegative matrix factorization through data preprocessing
  publication-title: Journal of Machine Learning Research
– volume: 95
  start-page: 415
  year: 2008
  end-page: 436
  article-title: On the asymptotics of penalized splines
  publication-title: Biometrika
– volume: 11
  start-page: 735
  year: 2002
  end-page: 757
  article-title: Selecting the number of knots for penalized splines
  publication-title: Journal of Computational and Graphical Statistics
– volume: 108
  start-page: 1
  year: 2015
  end-page: 16
  article-title: Finding imaging patterns of structural covariance via non‐negative matrix factorization
  publication-title: NeuroImage
– volume: 105
  start-page: 46
  year: 2017
  end-page: 52
  article-title: A note on modeling sparse exponential‐family functional response curves
  publication-title: Computational Statistics and Data Analysis
– volume: 93
  start-page: 307
  year: 2009
  end-page: 333
  article-title: A Bayesian latent variable approach to functional principal components analysis with binary and count
  publication-title: Advances in Statistical Analysis
– volume: 100
  start-page: 577
  year: 2005
  end-page: 590
  article-title: Functional data analysis for sparse longitudinal data
  publication-title: Journal of the American Statistical Association
– volume: 69
  start-page: 41
  year: 2013
  end-page: 51
  article-title: Corrected confidence bands for functional data using principal components
  publication-title: Biometrics
– start-page: 177
  year: 2003
  end-page: 180
  article-title: Non‐negative matrix factorization for polyphonic music transcription
– volume: 70
  start-page: 703
  year: 2008
  end-page: 723
  article-title: Modelling sparse generalized longitudinal observations with latent Gaussian processes
  publication-title: Journal of the Royal Statistical Society: Series B
– volume: 71
  start-page: 344
  year: 2015
  end-page: 353
  article-title: Generalized multilevel function‐on‐scalar regression and principal component analysis
  publication-title: Biometrics
– volume: 62
  start-page: 211
  year: 2013
  end-page: 224
  article-title: Non‐negative matrix factorization revisited: uniqueness and algorithm for symmetric decomposition
  publication-title: IEEE Transactions on Signal Processing
– year: 2002
– volume: 3
  start-page: 257
  year: 2016
  end-page: 295
  article-title: Functional data analysis
  publication-title: Annual Review of Statistics and Its Application
– volume: 26
  start-page: 211
  year: 1964
  end-page: 252
  article-title: An analysis of transformations (with discussion)
  publication-title: Journal of the Royal Statistical Society B
– volume: 9
  start-page: 1
  year: 2016
  end-page: 118
  article-title: Generalized low rank models
  publication-title: Foundations and Trends® in Machine Learning
– volume: 12
  start-page: 1871
  year: 2018
  end-page: 1893
  article-title: Functional principal variance component testing for a genetic association study of HIV progression
  publication-title: The Annals of Applied Statistics
– year: 2017
– volume: 25
  start-page: 1336
  year: 2013
  end-page: 1353
  article-title: Nonnegative matrix factorization: a comprehensive review
  publication-title: IEEE Transactions on Knowledge and Data Engineering
– volume: 15
  start-page: 102
  year: 2014
  end-page: 116
  article-title: Normalization and extraction of interpretable metrics from raw accelerometry data
  publication-title: Biostatistics
– volume: 4
  start-page: 458
  year: 2009
  end-page: 488
  article-title: Multilevel functional principal component analysis
  publication-title: Annals of Applied Statistics
– volume: 16
  start-page: 1141
  year: 2003
  end-page: 1148
  article-title: When does non‐negative matrix factorization give a correct decomposition into parts?
  publication-title: Advances in Neural Information Processing Systems
– volume: 13
  start-page: 3349
  year: 2012
  ident: e_1_2_8_13_1
  article-title: Sparse and unique nonnegative matrix factorization through data preprocessing
  publication-title: Journal of Machine Learning Research
– start-page: 85
  volume-title: Optimization for Machine Learning
  year: 2012
  ident: e_1_2_8_4_1
– volume: 26
  start-page: 211
  year: 1964
  ident: e_1_2_8_5_1
  article-title: An analysis of transformations (with discussion)
  publication-title: Journal of the Royal Statistical Society B
  doi: 10.1111/j.2517-6161.1964.tb00553.x
– volume-title: NNLM: Fast and Versatile Non‐Negative Matrix Factorization
  year: 2016
  ident: e_1_2_8_20_1
– ident: e_1_2_8_21_1
  doi: 10.1214/009053604000001156
– ident: e_1_2_8_3_1
  doi: 10.1093/biostatistics/kxt029
– ident: e_1_2_8_14_1
  doi: 10.1111/j.1541-0420.2012.01808.x
– ident: e_1_2_8_24_1
  doi: 10.1111/biom.12083
– ident: e_1_2_8_19_1
  doi: 10.1093/biomet/asn010
– ident: e_1_2_8_25_1
  doi: 10.1145/1102351.1102451
– ident: e_1_2_8_23_1
  doi: 10.1093/gerona/glt199
– ident: e_1_2_8_31_1
  doi: 10.1007/978-0-387-21706-2
– volume: 16
  start-page: 1141
  year: 2003
  ident: e_1_2_8_10_1
  article-title: When does non‐negative matrix factorization give a correct decomposition into parts?
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_8_22_1
  doi: 10.1198/106186002853
– ident: e_1_2_8_28_1
– ident: e_1_2_8_36_1
  doi: 10.1198/016214504000001745
– ident: e_1_2_8_30_1
  doi: 10.1007/s10182-009-0113-6
– ident: e_1_2_8_7_1
  doi: 10.1137/0916069
– ident: e_1_2_8_9_1
  doi: 10.1214/08-AOAS206
– volume-title: nloptr: R Interface to NLopt
  year: 2017
  ident: e_1_2_8_37_1
– ident: e_1_2_8_32_1
  doi: 10.1146/annurev-statistics-041715-033624
– volume: 24
  start-page: 1017
  year: 2014
  ident: e_1_2_8_11_1
  article-title: Penalized likelihood functional regression
  publication-title: Statistica Sinica
– ident: e_1_2_8_27_1
  doi: 10.1016/j.neuroimage.2014.11.045
– ident: e_1_2_8_35_1
  doi: 10.1111/biom.12963
– ident: e_1_2_8_2_1
  doi: 10.1214/18-AOAS1135
– ident: e_1_2_8_33_1
  doi: 10.1109/TKDE.2012.51
– ident: e_1_2_8_34_1
  doi: 10.1111/j.1467-9868.2010.00749.x
– ident: e_1_2_8_8_1
– ident: e_1_2_8_6_1
  doi: 10.1007/s00421-005-0112-6
– ident: e_1_2_8_26_1
  doi: 10.1109/ASPAA.2003.1285860
– ident: e_1_2_8_16_1
  doi: 10.1111/j.1467-9868.2008.00656.x
– ident: e_1_2_8_12_1
  doi: 10.1016/j.csda.2016.07.010
– ident: e_1_2_8_15_1
  doi: 10.1111/biom.12278
– ident: e_1_2_8_18_1
  doi: 10.1038/44565
– ident: e_1_2_8_29_1
  doi: 10.1561/2200000055
– ident: e_1_2_8_17_1
  doi: 10.1109/TSP.2013.2285514
SSID ssj0009502
Score 2.333791
Snippet We present a novel decomposition of nonnegative functional count data that draws on concepts from nonnegative matrix factorization. Our decomposition, which we...
SourceID proquest
pubmed
crossref
wiley
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1273
SubjectTerms Accelerometers
Algorithms
data collection
Decomposition
functional data
Functionals
Multiplication
nonnegative matrix factorization
Physical activity
principal component analysis
Principal components analysis
Title Nonnegative decomposition of functional count data
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fbiom.13220
https://www.ncbi.nlm.nih.gov/pubmed/31970756
https://www.proquest.com/docview/2469252322
https://www.proquest.com/docview/2344229857
https://www.proquest.com/docview/2524272513
Volume 76
WOSCitedRecordID wos000510500300001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1541-0420
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009502
  issn: 0006-341X
  databaseCode: DRFUL
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB50VdCDj_VVX1T0olDZnaSbBrz4WhR0FVHZW0nTxIvsiquC_95M2q2KIoi3QCdlSGaSmeTLNwDbrGkJaaEj68LdiKocRZlqZq6VWNloZTzxXHp356LTSbpdeTUC-8O3MAU_RHXgRp7h12tycJUNPjk5PU_fo1zKJexj6AyX12Ds-Lp9e_6JdLdRsIUTvos3uyU9KSF5Pnp_3ZC-RZlfg1a_67Rn_qfvLEyX0WZ4UJjHHIyYXh0mivqTb3WYuqhIWwd1mKTAs-BtngfsEALm3tOCh7kh5HkJ7wr7NqTdsDhEDH2xiZCApgtw2z65OTqNyvoKkebSZY0CE2MV4yxHabWRLZMrw5sZ5jzTJueKrhyl0NjKMTY2ZplCLaUWJuZ5zAxbhFqv3zPLECouhJTW9XPTi408M1YypYivnaP7dwA7w0FOdUk-TjUwHtJhEkLDk_rhCWCrkn0sKDd-lFobzlVaut0gRZfso0utEQPYrD47h6FbENUz_RcnwzhHlEksfpEhtYUL_VgAS4UdVKq4NUu4OKsVwK6f7l90TA_PLi98a-UvwqswiZTVe9DMGtSen17MOozrV2cDTxswKrrJRmnq72Wd_wY
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEB6kVdSDj_parbqiF4WVNsk2m6Ov0mJbRVR6W7LZxIu04gv892ay27WiFMRbYCfLkMwkM8mXbwAOaN0g0kIFxoa7AVY5ChJZT2wrMqLWSFjkuPTuO7zXi_p9cZ1jc_AtTMYPURy4oWe49RodHA-kx7wc36cfYzJlM_Yys3YUlqB8ftO864yx7tYyunAEeLF6P-cnRSjPV-_vO9KPMPN71Oq2nebiPxVegoU83vRPMgNZhik9qMBMVoHyowLz3YK29aUCcxh6ZszNK0B6iIF5cMTgfqoRe54DvPyh8XE_zI4RfVduwkeo6SrcNS9uz1pBXmEhUEzYvJGTSBtJGU2JMEqLhk6lZvWEpCxROmUSLx0FV6SRklCbkCaSKCEU1yFLQ6rpGpQGw4HeAF8yzoUwtp-dYFJLE20ElRIZ2xmx__bgcDTKscrpx7EKxmM8SkNweGI3PB7sF7JPGenGr1LV0WTFueO9xMSm-8Qm14R4sFd8ti6D9yByoIdvVoYyRoiIQj5BBtXmNvijHqxnhlCoYlctbiOthgdHbr4n6Biftq-6rrX5F-FdmG3ddjtxp9273II5gjm-g9BUofT6_Ka3YVq9W3t43skt_hOojgId
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1ZS8QwEB5kPdAHj_WqZ0VfFCq7Sdo0j16L4rqKuLJvJc3hi-yKF_jvzaTdqiiC-BbopAzJTDKTfPkGYIc2LSItVGRduBthlaMol83ctVIrGknOUs-ld9vmnU7a64mrEpuDb2EKfojqwA09w6_X6ODmQdtPXo7v0_cxmXIZ-yiLReL8cvT4utVtf2LdbRR04QjwYs1eyU-KUJ6P3l93pG9h5teo1W87rZl_KjwL02W8GR4UBjIHI6Zfh_GiAuVbHaYuKtrWpzpMYuhZMDfPA-kgBubOE4OH2iD2vAR4hQMb4n5YHCOGvtxEiFDTBei2Tm6OTqOywkKkmHB5IyepsZIyqomwyojEaGlYMyea5cpoJvHSUXBFEk1iY2OaS6KEUNzETMfU0EWo9Qd9swyhZJwLYV0_N8GkoXNjBZUSGdsZcf8OYHc4ypkq6cexCsZ9NkxDcHgyPzwBbFeyDwXpxo9Sa8PJykrHe8qIS_eJS64JCWCr-uxcBu9BZN8MXpwMZYwQkcb8FxlUm7vgjwawVBhCpYpbtbiLtJIA9vx8_6Jjdnh2eeFbK38R3oSJq-NW1j7rnK_CJMEU3yNo1qD2_Phi1mFMvTpzeNwoDf4dMDcBmA
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=Nonnegative+decomposition+of+functional+count+data&rft.jtitle=Biometrics&rft.au=Backenroth%2C+Daniel&rft.au=Shinohara%2C+Russell+T.&rft.au=Schrack%2C+Jennifer+A&rft.au=Goldsmith%2C+Jeff&rft.date=2020-12-01&rft.issn=0006-341X&rft.volume=76&rft.issue=4+p.1273-1284&rft.spage=1273&rft.epage=1284&rft_id=info:doi/10.1111%2Fbiom.13220&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0006-341X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0006-341X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0006-341X&client=summon