Improved time series clustering based on new geometric frameworks

•We use the geometrical information of the time series via Takens embedding.•We analyze the geometrical information obtained by the embedding on the Stiefel, the unit sphere and the Rn×p manifolds.•We point out the gain obtained by such an embedding with respect to traditional time series clustering...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition Vol. 124; p. 108423
Main Authors: Péalat, Clément, Bouleux, Guillaume, Cheutet, Vincent
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.04.2022
Elsevier
Subjects:
ISSN:0031-3203, 1873-5142
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract •We use the geometrical information of the time series via Takens embedding.•We analyze the geometrical information obtained by the embedding on the Stiefel, the unit sphere and the Rn×p manifolds.•We point out the gain obtained by such an embedding with respect to traditional time series clustering approaches.•We analyze over 79 times series databases different frameworks.•The advocated framework is the Stiefel embedding followed by the UMAP and HDBSCAN algorithms. Most existing methods for time series clustering rely on distances calculated from the entire raw data using the Euclidean distance or Dynamic Time Warping distance. In this work, we propose to embed the time series onto higher-dimensional spaces to obtain geometric representations of the time series themselves. Particularly, the embedding on Rn×p, on the Stiefel manifold and on the unit Sphere are analyzed for their performances with respect to several yet well-known clustering algorithms. The gain brought by the geometrical representation for the time series clustering is illustrated through a large benchmark of databases. We particularly exhibit that, firstly, the embedding of the time series on higher dimensional spaces gives better results than classical approaches and, secondly, that the embedding on the Stiefel manifold - in conjunction with UMAP and HDBSCAN clustering algorithms - is the recommended framework for time series clustering.
AbstractList Most existing methods for time series clustering rely on distances calculated from the entire raw data using the Euclidean distance or Dynamic Time Warping distance. In this work, we propose to embed the time series onto higher-dimensional spaces to obtain geometric representations of the time series them- selves. Particularly, the embedding on R n ×p , on the Stiefel manifold and on the unit Sphere are analyzed for their performances with respect to several yet well-known clustering algorithms. The gain brought by the geometrical representation for the time series clustering is illustrated through a large benchmark of databases. We particularly exhibit that, firstly, the embedding of the time series on higher dimensional spaces gives better results than classical approaches and, secondly, that the embedding on the Stiefel manifold - in conjunction with UMAP and HDBSCAN clustering algorithms - is the recommended frame- work for time series clustering.
•We use the geometrical information of the time series via Takens embedding.•We analyze the geometrical information obtained by the embedding on the Stiefel, the unit sphere and the Rn×p manifolds.•We point out the gain obtained by such an embedding with respect to traditional time series clustering approaches.•We analyze over 79 times series databases different frameworks.•The advocated framework is the Stiefel embedding followed by the UMAP and HDBSCAN algorithms. Most existing methods for time series clustering rely on distances calculated from the entire raw data using the Euclidean distance or Dynamic Time Warping distance. In this work, we propose to embed the time series onto higher-dimensional spaces to obtain geometric representations of the time series themselves. Particularly, the embedding on Rn×p, on the Stiefel manifold and on the unit Sphere are analyzed for their performances with respect to several yet well-known clustering algorithms. The gain brought by the geometrical representation for the time series clustering is illustrated through a large benchmark of databases. We particularly exhibit that, firstly, the embedding of the time series on higher dimensional spaces gives better results than classical approaches and, secondly, that the embedding on the Stiefel manifold - in conjunction with UMAP and HDBSCAN clustering algorithms - is the recommended framework for time series clustering.
ArticleNumber 108423
Author Péalat, Clément
Cheutet, Vincent
Bouleux, Guillaume
Author_xml – sequence: 1
  givenname: Clément
  surname: Péalat
  fullname: Péalat, Clément
  email: clement.pealat@insa-lyon.fr
– sequence: 2
  givenname: Guillaume
  surname: Bouleux
  fullname: Bouleux, Guillaume
  email: guillaume.bouleux@insa-lyon.fr
– sequence: 3
  givenname: Vincent
  surname: Cheutet
  fullname: Cheutet, Vincent
  email: vincent.cheutet@insa-lyon.fr
BackLink https://hal.science/hal-03457460$$DView record in HAL
BookMark eNqFkD1PwzAQhi1UJNrCP2DIypDiryQuA1JVAa1UiQVmy7EvxSWJK9u04t_jKrAwwHSnez9OeiZo1LseELomeEYwKW93s72K2m1nFFOSToJTdobGRFQsLwinIzTGmJGcUcwu0CSEHcakSsIYLdbd3rsDmCzaDrIA3kLIdPsRYlr7bVarkETXZz0csy24DqK3Omu86uDo_Hu4ROeNagNcfc8pen18eFmu8s3z03q52OSaiTLmBuNS15UoBC-ZouVccAGYccJqDQKMNhWtOVBlGoWZwVBTaDTlrGzonBTApuhm6H1Trdx72yn_KZ2ycrXYyNMtlRUVL_GBJO_d4NXeheChkdpGFa3ro1e2lQTLEzi5kwM4eQInB3ApzH-Ff779E7sfYpAgHCx4GbSFXoOxHnSUxtm_C74ALL6Log
CitedBy_id crossref_primary_10_1016_j_rse_2023_113969
crossref_primary_10_1016_j_compbiomed_2023_106655
crossref_primary_10_1109_TSMC_2025_3577606
crossref_primary_10_1016_j_compbiomed_2024_109255
crossref_primary_10_1016_j_eswa_2023_120620
crossref_primary_10_1016_j_patcog_2025_111708
crossref_primary_10_1002_itl2_395
crossref_primary_10_3390_electronics14081660
Cites_doi 10.1109/TPAMI.2019.2913863
10.1016/j.patcog.2021.108142
10.1016/S0362-546X(96)00149-6
10.1007/s11263-009-0273-6
10.1109/ICCV.2007.4409044
10.1063/1.3227736
10.1103/PhysRevE.55.6162
10.1109/JBHI.2014.2350996
10.1137/16M1074485
10.1016/0024-3795(92)90251-5
10.1109/JBHI.2018.2882748
10.3390/e20090717
10.1109/TPAMI.2020.2986319
10.1016/j.patrec.2021.02.004
10.1016/j.knosys.2017.05.026
10.1016/j.patcog.2019.05.040
10.1109/TPAMI.2011.52
10.1145/3068335
10.1007/BF01908075
10.1109/BHI.2019.8834507
10.1002/widm.30
10.1002/cpa.3160300502
10.1016/j.ymssp.2013.06.018
10.1109/TIT.2019.2923217
ContentType Journal Article
Copyright 2021
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: 2021
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID AAYXX
CITATION
1XC
VOOES
DOI 10.1016/j.patcog.2021.108423
DatabaseName CrossRef
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle CrossRef
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-5142
ExternalDocumentID oai:HAL:hal-03457460v1
10_1016_j_patcog_2021_108423
S0031320321005999
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
1XC
VOOES
ID FETCH-LOGICAL-c386t-d006cb7858463a269848e03413bce8edcd72b4e2adfa03d0eb2efc2436f2915e3
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000782989900012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Sat Nov 29 15:04:43 EST 2025
Sat Nov 29 07:29:08 EST 2025
Tue Nov 18 22:03:35 EST 2025
Fri Feb 23 02:39:32 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords UMAP
HDBSCAN
Stiefel manifold
Time series
Embedding
Clustering
Delayed coordinate embedding
Stiefel Manifold
Language English
License Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c386t-d006cb7858463a269848e03413bce8edcd72b4e2adfa03d0eb2efc2436f2915e3
ORCID 0000-0001-8009-8156
0000-0003-1920-2609
OpenAccessLink https://hal.science/hal-03457460
ParticipantIDs hal_primary_oai_HAL_hal_03457460v1
crossref_citationtrail_10_1016_j_patcog_2021_108423
crossref_primary_10_1016_j_patcog_2021_108423
elsevier_sciencedirect_doi_10_1016_j_patcog_2021_108423
PublicationCentury 2000
PublicationDate 2022-04-01
PublicationDateYYYYMMDD 2022-04-01
PublicationDate_xml – month: 04
  year: 2022
  text: 2022-04-01
  day: 01
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2022
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Yang, Liang, Wang, Rosin, Yang (bib0012) 2020; 42
Sigal, Balan, Black (bib0009) 2010; 87
Rosenberg, Hirschberg (bib0037) 2007
Karim, Majumdar, Darabi (bib0042) 2021; 43
Javed, Suk Lee, Rizzo (bib0016) 2020; 1
Gautama, Mandic, Van Hulle (bib0041) 2003; vol. 6
O’Reilly, Moessner, Nati (bib0019) 2017; 133
Schubert, Sander, Ester, Kriegel, Xu (bib0034) 2017; 42
Kavitha, Punithavalli (bib0006) 2010; 8
Li, Jung (bib0005) 2021; 145
Gudmundsson (bib0032) 2014
Bouleux (bib0002) 2013; 41
Sun, Yang, Liu, Chen, Rao, Bai (bib0018) 2019; 95
Karcher (bib0029) 1977; 30
Kaufman, Rousseeuw (bib0033) 1990; vol. 344
C. Pealat, G. Bouleux, V. Cheutet, Extracting Most Impacting Emergency Department Patient Flow By Embedding Laboratory-confirmed and Clinical Diagnosis on The Stiefel Manifold, Proceedings of 2019 IEEE EMBS International Conference on Biomedical Health Informatics (BHI) (2019). ISSN: 2641-3590.
Kriegel, Kröger, Sander, Zimek (bib0035) 2011; 1
Nguyen, Brun, Lezoray, Bougleux (bib0010) 2019
Rodrigues, Congedo, Jutten (bib0011) 2018
Campello, Moulavi, Sander (bib0025) 2013; 7819
Bouleux, Dugast, Marcon (bib0020) 2019; 65
M. Cuturi, M. Blondel, Soft-DTW: a differentiable loss function for time-series, Proceedings of the 34th International Conference on Machine Learning (2017).
Xu, Chen, Li, Luo, Yang (bib0015) 2021; 120
Fakhrazari, Vakilzadian (bib0017) 2017
Miao, Ben-Israel (bib0030) 1992; 171
Bouleux, Marcon, Mory (bib0003) 2015; 19
R. Li, T. P. Tian, S. Sclaroff, Simultaneous Learning of Nonlinear Manifold and Dynamical Models for High-dimensional Time Series, in: 2007 IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brazil, 2007.
Mittal, Goyal, Hemanth, Sethi (bib0036) 2019
Hubert, Arabie (bib0038) 1985
Rhodes, Morari (bib0040) 1997; 55
Turaga, Veeraraghavan, Srivastava, Chellappa (bib0014) 2011; 33
Xu, Wunsch (bib0001) 2008
Dugast, Bouleux, Mory, Marcon (bib0004) 2019; 23
Oates, Firoiu, Cohen (bib0007) 1999
R. Zimmermann, A matrix-algebraic algorithm for the Riemannian logarithm on the Stiefel manifold under the canonical metric, 2016
Z. Wang, T. Oates, Imaging time-series to improve classification and imputation, 24th International Joint Conference on Artificial Intelligence (2015).
L. Mc, J. Healy, J. Melville, UMAP: uniform manifold approximation and projection for dimension reduction, 2018
Dugast, Bouleux, Marcon (bib0021) 2018; 20
C. Pealat, G. Bouleux, V. Cheutet, Improved Time-Series Clustering with UMAP dimension reduction method, Proceedings of 22nd International Conference on Pattern Recognition (2020).
Stark, Broomhead, Davies, Huke (bib0022) 1997; 30
Gao, Jin (bib0023) 2009; 19
B. St Thomas, L. Lin, L.H. Lim, S. Mukherjee, Learning subspaces of different dimension, 2014
Xu (10.1016/j.patcog.2021.108423_bib0001) 2008
Karcher (10.1016/j.patcog.2021.108423_bib0029) 1977; 30
Dugast (10.1016/j.patcog.2021.108423_bib0004) 2019; 23
Kavitha (10.1016/j.patcog.2021.108423_bib0006) 2010; 8
Sun (10.1016/j.patcog.2021.108423_bib0018) 2019; 95
Bouleux (10.1016/j.patcog.2021.108423_bib0020) 2019; 65
Mittal (10.1016/j.patcog.2021.108423_bib0036) 2019
10.1016/j.patcog.2021.108423_bib0039
10.1016/j.patcog.2021.108423_bib0013
Hubert (10.1016/j.patcog.2021.108423_bib0038) 1985
Gao (10.1016/j.patcog.2021.108423_bib0023) 2009; 19
Fakhrazari (10.1016/j.patcog.2021.108423_bib0017) 2017
10.1016/j.patcog.2021.108423_bib0031
Oates (10.1016/j.patcog.2021.108423_bib0007) 1999
Gautama (10.1016/j.patcog.2021.108423_bib0041) 2003; vol. 6
Yang (10.1016/j.patcog.2021.108423_bib0012) 2020; 42
Campello (10.1016/j.patcog.2021.108423_bib0025) 2013; 7819
Javed (10.1016/j.patcog.2021.108423_bib0016) 2020; 1
Schubert (10.1016/j.patcog.2021.108423_bib0034) 2017; 42
Stark (10.1016/j.patcog.2021.108423_bib0022) 1997; 30
Gudmundsson (10.1016/j.patcog.2021.108423_sbref0032) 2014
O’Reilly (10.1016/j.patcog.2021.108423_bib0019) 2017; 133
Sigal (10.1016/j.patcog.2021.108423_bib0009) 2010; 87
Rodrigues (10.1016/j.patcog.2021.108423_bib0011) 2018
Miao (10.1016/j.patcog.2021.108423_bib0030) 1992; 171
10.1016/j.patcog.2021.108423_bib0008
Bouleux (10.1016/j.patcog.2021.108423_bib0003) 2015; 19
10.1016/j.patcog.2021.108423_bib0027
10.1016/j.patcog.2021.108423_bib0028
Turaga (10.1016/j.patcog.2021.108423_bib0014) 2011; 33
Li (10.1016/j.patcog.2021.108423_bib0005) 2021; 145
10.1016/j.patcog.2021.108423_bib0026
Xu (10.1016/j.patcog.2021.108423_bib0015) 2021; 120
10.1016/j.patcog.2021.108423_bib0024
Rhodes (10.1016/j.patcog.2021.108423_bib0040) 1997; 55
Dugast (10.1016/j.patcog.2021.108423_bib0021) 2018; 20
Kaufman (10.1016/j.patcog.2021.108423_bib0033) 1990; vol. 344
Rosenberg (10.1016/j.patcog.2021.108423_bib0037) 2007
Karim (10.1016/j.patcog.2021.108423_bib0042) 2021; 43
Bouleux (10.1016/j.patcog.2021.108423_bib0002) 2013; 41
Kriegel (10.1016/j.patcog.2021.108423_bib0035) 2011; 1
Nguyen (10.1016/j.patcog.2021.108423_bib0010) 2019
References_xml – start-page: 476
  year: 2017
  end-page: 481
  ident: bib0017
  article-title: A survey on time series data mining
  publication-title: 2017 IEEE International Conference on Electro Information Technology (EIT)
– volume: 23
  start-page: 2174
  year: 2019
  end-page: 2181
  ident: bib0004
  article-title: Improving health care management through persistent homology of time-varying variability of emergency department patient flow
  publication-title: IEEE J. Biomed. Heal. Inform.
– volume: 43
  start-page: 3309
  year: 2021
  end-page: 3320
  ident: bib0042
  article-title: Adversarial attacks on time series
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 1
  start-page: 231
  year: 2011
  end-page: 240
  ident: bib0035
  article-title: Density-based clustering
  publication-title: WIREs Data Min. Knowl. Discov.
– volume: 19
  start-page: 1929
  year: 2015
  end-page: 1936
  ident: bib0003
  article-title: Early index for detection of pediatric emergency department crowding
  publication-title: IEEE J. Biomed. Health Inform.
– volume: 7819
  start-page: 160
  year: 2013
  end-page: 172
  ident: bib0025
  article-title: Density-based clustering based on hierarchical density estimates
  publication-title: Adv. Data Min.
– volume: 33
  start-page: 2273
  year: 2011
  end-page: 2286
  ident: bib0014
  article-title: Statistical computations on Grassmann and Stiefel manifolds for image and video-based recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 133
  start-page: 1
  year: 2017
  end-page: 16
  ident: bib0019
  article-title: Univariate and multivariate time series manifold learning
  publication-title: Knowl. Based Syst.
– volume: 95
  start-page: 24
  year: 2019
  end-page: 35
  ident: bib0018
  article-title: Univariate time series classification using information geometry
  publication-title: Pattern Recognit.
– reference: R. Zimmermann, A matrix-algebraic algorithm for the Riemannian logarithm on the Stiefel manifold under the canonical metric, 2016,
– reference: L. Mc, J. Healy, J. Melville, UMAP: uniform manifold approximation and projection for dimension reduction, 2018,
– year: 2008
  ident: bib0001
  article-title: Clustering
– reference: R. Li, T. P. Tian, S. Sclaroff, Simultaneous Learning of Nonlinear Manifold and Dynamical Models for High-dimensional Time Series, in: 2007 IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brazil, 2007.
– volume: 19
  start-page: 033137
  year: 2009
  ident: bib0023
  article-title: Complex network from time series based on phase space reconstruction
  publication-title: Chaos
– year: 1985
  ident: bib0038
  article-title: Comparing partitions
  publication-title: J. Classif.
– volume: 1
  start-page: 100001
  year: 2020
  ident: bib0016
  article-title: A benchmark study on time series clustering
  publication-title: Mach. Learn. Appl.
– reference: B. St Thomas, L. Lin, L.H. Lim, S. Mukherjee, Learning subspaces of different dimension, 2014,
– volume: vol. 344
  start-page: 68
  year: 1990
  end-page: 125
  ident: bib0033
  article-title: Finding Groups in Data: An Introduction to Cluster Analysis
– volume: 65
  start-page: 6484
  year: 2019
  end-page: 6495
  ident: bib0020
  article-title: Information topological characterization of periodically correlated processes by dilation operators
  publication-title: IEEE Trans. Inf. Theory
– volume: 171
  start-page: 81
  year: 1992
  end-page: 98
  ident: bib0030
  article-title: On principal angles between subspaces in Rn
  publication-title: Linear Algebra Appl.
– volume: 8
  year: 2010
  ident: bib0006
  article-title: Clustering time series data stream - a literature survey
  publication-title: Int. J. Comput. Sci.Inf. Secur.
– start-page: 130
  year: 2014
  ident: bib0032
  article-title: An introduction to Riemannian geometry
  publication-title: Lecture Notes
– reference: C. Pealat, G. Bouleux, V. Cheutet, Improved Time-Series Clustering with UMAP dimension reduction method, Proceedings of 22nd International Conference on Pattern Recognition (2020).
– start-page: 17
  year: 1999
  end-page: 21
  ident: bib0007
  article-title: Clustering time series with hidden Markov models and dynamic time warping
  publication-title: Proceedings of the IJCAI-99 Workshop on Neural, Symbolic and Reinforcement Learning Methods for Sequence Learning
– volume: 87
  start-page: 4
  year: 2010
  end-page: 27
  ident: bib0009
  article-title: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion
  publication-title: Int. J. Comput. Vis.
– volume: 30
  start-page: 509
  year: 1977
  end-page: 541
  ident: bib0029
  article-title: Riemannian center of mass and mollifier smoothing
  publication-title: Comm. Pure Appl. Math.
– volume: 42
  start-page: 1
  year: 2017
  end-page: 21
  ident: bib0034
  article-title: DBSCAN Revisited, revisited: why and how you should (still) use DBSCAN
  publication-title: ACM Trans. Database Syst.
– year: 2019
  ident: bib0036
  article-title: Clustering approaches for high-dimensional databases: a review
  publication-title: Wiley Interdiscip. Rev.
– start-page: 410
  year: 2007
  end-page: 420
  ident: bib0037
  article-title: V-measure: a conditional entropy-based external cluster evaluation measure
  publication-title: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)
– start-page: 12036
  year: 2019
  end-page: 12045
  ident: bib0010
  article-title: A neural network based on SPD manifold learning for skeleton-based hand gesture recognition
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 20
  start-page: 717
  year: 2018
  ident: bib0021
  article-title: Representation and characterization of nonstationary processes by dilation operators and induced shape space manifolds
  publication-title: Entropy
– reference: Z. Wang, T. Oates, Imaging time-series to improve classification and imputation, 24th International Joint Conference on Artificial Intelligence (2015).
– volume: 145
  start-page: 194
  year: 2021
  end-page: 199
  ident: bib0005
  article-title: Dynamic relationship identification for abnormality detection on financial time series
  publication-title: Pattern Recognit. Lett.
– volume: vol. 6
  start-page: 6
  year: 2003
  end-page: 29
  ident: bib0041
  article-title: A differential entropy based method for determining the optimal embedding parameters of a signal
  publication-title: 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings. (ICASSP ’03)
– volume: 120
  start-page: 108142
  year: 2021
  ident: bib0015
  article-title: Learnable low-rank latent dictionary for subspace clustering
  publication-title: Pattern Recognit.
– volume: 55
  start-page: 6162
  year: 1997
  end-page: 6170
  ident: bib0040
  article-title: False-nearest-neighbors algorithm and noise-corrupted time series
  publication-title: Phys. Rev. E
– start-page: 573
  year: 2018
  end-page: 577
  ident: bib0011
  article-title: Multivariate time-series analysis via manifold learning
  publication-title: 2018 IEEE Statistical Signal Processing Workshop (SSP)
– volume: 30
  start-page: 5303
  year: 1997
  end-page: 5314
  ident: bib0022
  article-title: Takens embedding theorems for forced and stochastic systems
  publication-title: Nonlinear Anal.
– reference: C. Pealat, G. Bouleux, V. Cheutet, Extracting Most Impacting Emergency Department Patient Flow By Embedding Laboratory-confirmed and Clinical Diagnosis on The Stiefel Manifold, Proceedings of 2019 IEEE EMBS International Conference on Biomedical Health Informatics (BHI) (2019). ISSN: 2641-3590.
– volume: 41
  start-page: 301
  year: 2013
  end-page: 312
  ident: bib0002
  article-title: Oblique projection pre-processing and TLS application for diagnosing rotor bar defects by improving power spectrum estimation
  publication-title: Mech. Syst. Signal Process.
– reference: M. Cuturi, M. Blondel, Soft-DTW: a differentiable loss function for time-series, Proceedings of the 34th International Conference on Machine Learning (2017).
– volume: 42
  start-page: 1537
  year: 2020
  end-page: 1544
  ident: bib0012
  article-title: Subspace clustering via good neighbors
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 42
  start-page: 1537
  issue: 6
  year: 2020
  ident: 10.1016/j.patcog.2021.108423_bib0012
  article-title: Subspace clustering via good neighbors
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2019.2913863
– volume: 8
  issue: 1
  year: 2010
  ident: 10.1016/j.patcog.2021.108423_bib0006
  article-title: Clustering time series data stream - a literature survey
  publication-title: Int. J. Comput. Sci.Inf. Secur.
– volume: 120
  start-page: 108142
  year: 2021
  ident: 10.1016/j.patcog.2021.108423_bib0015
  article-title: Learnable low-rank latent dictionary for subspace clustering
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2021.108142
– volume: 30
  start-page: 5303
  issue: 8
  year: 1997
  ident: 10.1016/j.patcog.2021.108423_bib0022
  article-title: Takens embedding theorems for forced and stochastic systems
  publication-title: Nonlinear Anal.
  doi: 10.1016/S0362-546X(96)00149-6
– volume: vol. 344
  start-page: 68
  year: 1990
  ident: 10.1016/j.patcog.2021.108423_bib0033
– volume: vol. 6
  start-page: 6
  year: 2003
  ident: 10.1016/j.patcog.2021.108423_bib0041
  article-title: A differential entropy based method for determining the optimal embedding parameters of a signal
– volume: 87
  start-page: 4
  year: 2010
  ident: 10.1016/j.patcog.2021.108423_bib0009
  article-title: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-009-0273-6
– ident: 10.1016/j.patcog.2021.108423_bib0013
  doi: 10.1109/ICCV.2007.4409044
– volume: 19
  start-page: 033137
  issue: 3
  year: 2009
  ident: 10.1016/j.patcog.2021.108423_bib0023
  article-title: Complex network from time series based on phase space reconstruction
  publication-title: Chaos
  doi: 10.1063/1.3227736
– start-page: 130
  year: 2014
  ident: 10.1016/j.patcog.2021.108423_sbref0032
  article-title: An introduction to Riemannian geometry
  publication-title: Lecture Notes
– ident: 10.1016/j.patcog.2021.108423_bib0039
– volume: 1
  start-page: 100001
  year: 2020
  ident: 10.1016/j.patcog.2021.108423_bib0016
  article-title: A benchmark study on time series clustering
  publication-title: Mach. Learn. Appl.
– year: 2019
  ident: 10.1016/j.patcog.2021.108423_bib0036
  article-title: Clustering approaches for high-dimensional databases: a review
  publication-title: Wiley Interdiscip. Rev.
– volume: 55
  start-page: 6162
  issue: 5
  year: 1997
  ident: 10.1016/j.patcog.2021.108423_bib0040
  article-title: False-nearest-neighbors algorithm and noise-corrupted time series
  publication-title: Phys. Rev. E
  doi: 10.1103/PhysRevE.55.6162
– volume: 19
  start-page: 1929
  issue: 6
  year: 2015
  ident: 10.1016/j.patcog.2021.108423_bib0003
  article-title: Early index for detection of pediatric emergency department crowding
  publication-title: IEEE J. Biomed. Health Inform.
  doi: 10.1109/JBHI.2014.2350996
– start-page: 17
  year: 1999
  ident: 10.1016/j.patcog.2021.108423_bib0007
  article-title: Clustering time series with hidden Markov models and dynamic time warping
– year: 2008
  ident: 10.1016/j.patcog.2021.108423_bib0001
– start-page: 476
  year: 2017
  ident: 10.1016/j.patcog.2021.108423_bib0017
  article-title: A survey on time series data mining
– ident: 10.1016/j.patcog.2021.108423_bib0031
  doi: 10.1137/16M1074485
– start-page: 12036
  year: 2019
  ident: 10.1016/j.patcog.2021.108423_bib0010
  article-title: A neural network based on SPD manifold learning for skeleton-based hand gesture recognition
– ident: 10.1016/j.patcog.2021.108423_bib0027
– start-page: 410
  year: 2007
  ident: 10.1016/j.patcog.2021.108423_bib0037
  article-title: V-measure: a conditional entropy-based external cluster evaluation measure
– volume: 171
  start-page: 81
  issue: 92
  year: 1992
  ident: 10.1016/j.patcog.2021.108423_bib0030
  article-title: On principal angles between subspaces in Rn
  publication-title: Linear Algebra Appl.
  doi: 10.1016/0024-3795(92)90251-5
– volume: 23
  start-page: 2174
  issue: 5
  year: 2019
  ident: 10.1016/j.patcog.2021.108423_bib0004
  article-title: Improving health care management through persistent homology of time-varying variability of emergency department patient flow
  publication-title: IEEE J. Biomed. Heal. Inform.
  doi: 10.1109/JBHI.2018.2882748
– volume: 20
  start-page: 717
  issue: 9
  year: 2018
  ident: 10.1016/j.patcog.2021.108423_bib0021
  article-title: Representation and characterization of nonstationary processes by dilation operators and induced shape space manifolds
  publication-title: Entropy
  doi: 10.3390/e20090717
– volume: 43
  start-page: 3309
  issue: 10
  year: 2021
  ident: 10.1016/j.patcog.2021.108423_bib0042
  article-title: Adversarial attacks on time series
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.2986319
– volume: 145
  start-page: 194
  year: 2021
  ident: 10.1016/j.patcog.2021.108423_bib0005
  article-title: Dynamic relationship identification for abnormality detection on financial time series
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2021.02.004
– volume: 133
  start-page: 1
  year: 2017
  ident: 10.1016/j.patcog.2021.108423_bib0019
  article-title: Univariate and multivariate time series manifold learning
  publication-title: Knowl. Based Syst.
  doi: 10.1016/j.knosys.2017.05.026
– volume: 95
  start-page: 24
  year: 2019
  ident: 10.1016/j.patcog.2021.108423_bib0018
  article-title: Univariate time series classification using information geometry
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2019.05.040
– volume: 7819
  start-page: 160
  year: 2013
  ident: 10.1016/j.patcog.2021.108423_bib0025
  article-title: Density-based clustering based on hierarchical density estimates
  publication-title: Adv. Data Min.
– start-page: 573
  year: 2018
  ident: 10.1016/j.patcog.2021.108423_bib0011
  article-title: Multivariate time-series analysis via manifold learning
– volume: 33
  start-page: 2273
  issue: 11
  year: 2011
  ident: 10.1016/j.patcog.2021.108423_bib0014
  article-title: Statistical computations on Grassmann and Stiefel manifolds for image and video-based recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2011.52
– volume: 42
  start-page: 1
  issue: 3
  year: 2017
  ident: 10.1016/j.patcog.2021.108423_bib0034
  article-title: DBSCAN Revisited, revisited: why and how you should (still) use DBSCAN
  publication-title: ACM Trans. Database Syst.
  doi: 10.1145/3068335
– year: 1985
  ident: 10.1016/j.patcog.2021.108423_bib0038
  article-title: Comparing partitions
  publication-title: J. Classif.
  doi: 10.1007/BF01908075
– ident: 10.1016/j.patcog.2021.108423_bib0024
– ident: 10.1016/j.patcog.2021.108423_bib0008
  doi: 10.1109/BHI.2019.8834507
– volume: 1
  start-page: 231
  issue: 3
  year: 2011
  ident: 10.1016/j.patcog.2021.108423_bib0035
  article-title: Density-based clustering
  publication-title: WIREs Data Min. Knowl. Discov.
  doi: 10.1002/widm.30
– ident: 10.1016/j.patcog.2021.108423_bib0028
– volume: 30
  start-page: 509
  issue: 5
  year: 1977
  ident: 10.1016/j.patcog.2021.108423_bib0029
  article-title: Riemannian center of mass and mollifier smoothing
  publication-title: Comm. Pure Appl. Math.
  doi: 10.1002/cpa.3160300502
– ident: 10.1016/j.patcog.2021.108423_bib0026
– volume: 41
  start-page: 301
  issue: 1
  year: 2013
  ident: 10.1016/j.patcog.2021.108423_bib0002
  article-title: Oblique projection pre-processing and TLS application for diagnosing rotor bar defects by improving power spectrum estimation
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2013.06.018
– volume: 65
  start-page: 6484
  issue: 10
  year: 2019
  ident: 10.1016/j.patcog.2021.108423_bib0020
  article-title: Information topological characterization of periodically correlated processes by dilation operators
  publication-title: IEEE Trans. Inf. Theory
  doi: 10.1109/TIT.2019.2923217
SSID ssj0017142
Score 2.4473944
Snippet •We use the geometrical information of the time series via Takens embedding.•We analyze the geometrical information obtained by the embedding on the Stiefel,...
Most existing methods for time series clustering rely on distances calculated from the entire raw data using the Euclidean distance or Dynamic Time Warping...
SourceID hal
crossref
elsevier
SourceType Open Access Repository
Enrichment Source
Index Database
Publisher
StartPage 108423
SubjectTerms Clustering
Computer Aided Engineering
Computer Science
Delayed coordinate embedding
Embedding
Engineering Sciences
HDBSCAN
Mechanical engineering
Mechanics
Stiefel manifold
Time series
UMAP
Title Improved time series clustering based on new geometric frameworks
URI https://dx.doi.org/10.1016/j.patcog.2021.108423
https://hal.science/hal-03457460
Volume 124
WOSCitedRecordID wos000782989900012&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-5142
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017142
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdruoe9bN0X7boWMfYWPGTJkaXHULp1ZZTAupE340hyP0id0MSlf37vLMnuKKPbYC8mEZEV7k6n0339CPmouRWS6Qp22oglcOKpRGmrE2MkK8FiL2VWtWAT-cmJmk71JKCirlo4gbyu1e2tXv5XVsMYMBtLZ_-C3d1LYQA-A9PhCWyH5x8x3rsJwI5E2PghLulWQzNvsCMC-gXw3LIYIwCDenjmFleIqWWGVczSWt23Vydt-00seQl5Rn3UfuJj7OW89Jkjc__9fiYNgla7pj3evjQIb9RcdXJ0cO6atY-E_LyoTZwVHBBwd-3zVlqvWKyM6dOQWk0r0kRw5pWX88pV5SIBA-1X7etLqB9ocu9UuPy0hBNpcQYXeZ5iPmTGRX9ydfmE330LSoYFSdhwRm-QTZ6PtBqQzfHXw-lxF1jK08w3kA9_L1ZTtil_D9f6nbWycR797q0dcrpFnocLBB17xr8kT1z9iryI4Bw06OrXZBzlgKIcUC8HtJcD2soBXdQU5IB2ckB7OXhDfnw-PD04SgJeRmKEkuvEggY1s1yhTSlgo2mVKcfQTJkZp5w1NuezzPHSViUTlrkZd5XhmZAV1-nIibdkUC9qt02odYjAJYVEdIRS2jKFzWszU6XMGSbLHSIiXQoTmskjpsm8iFmDl4WnZoHULDw1d0jSzVr6ZiqP_D6PJC-CQegNvQKk5JGZH4BD3SLYQ_1o_K3AMSDIKM8ku0nf_fPrd8mzfie8J4P1deP2yFNzs75YXe8HmbsDu-6RNw
linkProvider Elsevier
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=Improved+time+series+clustering+based+on+new+geometric+frameworks&rft.jtitle=Pattern+recognition&rft.au=P%C3%A9alat%2C+Cl%C3%A9ment&rft.au=Bouleux%2C+Guillaume&rft.au=Cheutet%2C+Vincent&rft.date=2022-04-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.eissn=1873-5142&rft.volume=124&rft_id=info:doi/10.1016%2Fj.patcog.2021.108423&rft.externalDocID=S0031320321005999
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon