We integrate machine learning approaches with nonlinear time series analysis, specifically utilizing recurrence measures to classify various dynamical states emerging from time series. We implement three machine learning algorithms: Logistic Regression, Random Forest, and Support Vector Machine for this study. The input features are derived from the recurrence quantification of nonlinear time series and characteristic measures of the corresponding recurrence networks. For training and testing, we generate synthetic data from standard nonlinear dynamical systems and evaluate the efficiency and performance of the machine learning algorithms in classifying time series into periodic, chaotic, hyperchaotic, or noisy categories. Additionally, we explore the significance of input features in the classification scheme and find that the features quantifying the density of recurrence points are the most relevant. Furthermore, we illustrate how the trained algorithms can successfully predict the dynamical states of two variable stars, SX Her and AC Her, from the data of their light curves. We also indicate how the algorithms can be trained to classify data from discrete systems.
REFERENCES
1.
J. A.
Bastos
and J.
Caiado
, “Recurrence quantification analysis of global stock markets
,” Physica A
390
(7
), 1315
–1325
(2011
). 2.
C.
Kyrtsou
and C. E.
Vorlow
, Complex Dynamics in Macroeconomics: A Novel Approach
(Springer
, 2005
).3.
Z.
Zhao
, S.
Li
, J.
Gao
, and Y.
Wang
, “Identifying spatial patterns and dynamics of climate change using recurrence quantification analysis: A case study of Qinghai-Tibet plateau
,” Int. J. Bifurcat. Chaos
21
, 1127
–1139
(2011
). 4.
I.
Gruszczyńska
, R.
Mosdorf
, P.
Sobaniec
, M.
Żochowska Sobaniec
, and M.
Borowska
, “Epilepsy identification based on EEG signal using RQA method
,” Adv. Med. Sci.
64
(1
), 58
–64
(2019
). 5.
M.
Stangalini
, G.
Li Causi
, F.
Pedichini
, S.
Antoniucci
, M.
Mattioli
, J.
Christou
, G.
Consolini
, D.
Hope
, S. M.
Jefferies
, R.
Piazzesi
, and V.
Testa
, “Recurrence quantification analysis as a post-processing technique in adaptive optics high-contrast imaging
,” Astrophys. J.
868
(1
), 6
(2018
). 6.
S.
Namboodiri
, C.
Verma
, P. K.
Dhar
, A.
Giuliani
, and A. S.
Nair
, “Application of recurrence quantification analysis (RQA) in biosequence pattern recognition,” in Proceedings, Part I 1. Advances in Computing and Communications: First International Conference, ACC 2011, Kochi, India, 22–24 July 2011 (Springer, 2011), pp. 284–293.7.
M. A.
Lopes
, J.
Zhang
, D.
Krzemiński
, K.
Hamandi
, Q.
Chen
, L.
Livi
, and N.
Masuda
, “Recurrence quantification analysis of dynamic brain networks
,” Eur. J. Neurosci.
53
(4
), 1040
–1059
(2021
). 8.
W. A.
Hussein
, N. M. G.
Al-Saidi
, and H.
Natiq
, “A new 2D Hénon-logistic map for producing hyperchaotic behavior,” in 2018 Third Scientific Conference of Electrical Engineering (SCEE) (IEEE, 2018), pp. 265–269.9.
W.
Zhang
, G.
Feng
, and Q.
Liu
, “The application of recurrence quantification analysis in detection of abrupt climate change
,” Discrete Dyn. Nat. Soc.
2016
, 1
–7
(2016
).10.
G.
Ambika
, S. V.
George
, and R.
Misra
, “Classification of close binary stars using recurrence networks
,” Chaos
29
(11), 113112
(2019
).11.
J.
Belaire-Franch
, D.
Contreras
, and L.
Tordera-Lledó
, “Assessing nonlinear structures in real exchange rates using recurrence plot strategies
,” Phys. D
171
(4
), 249
–264
(2002
). 12.
C.
Meena
, S.
Kumari
, A.
Sharma
, and S.
Sinha
, “Effect of heterogeneity in a model of El Niño southern oscillations
,” Chaos Soliton. Fract.
104
, 668
–679
(2017
). 13.
C.
Meena
, E.
Surovyatkina
, and S.
Sinha
, Coexistence of attractors in a coupled nonlinear delayed system modelling El Niño southern oscillations, Chaotic Dynamics (2017), pp. 171–186.14.
D.
Baleanu
, S.
Sadat Sajjadi
, J. H.
Asad
, A.
Jajarmi
, and E.
Estiri
, “Hyperchaotic behaviors, optimal control, and synchronization of a nonautonomous cardiac conduction system
,” Adv. Differ. Equations
2021
, 1
–24
(2021
).15.
C.
Meena
, P.
Deep Rungta
, and S.
Sinha
, “Threshold-activated transport stabilizes chaotic populations to steady states
,” PLoS One
12
(8
), e0183251
(2017
). 16.
N.
Marwan
, M.
Carmen Romano
, M.
Thiel
, and J.
Kurths
, “Recurrence plots for the analysis of complex systems
,” Phys. Rep.
438
(5–6
), 237
–329
(2007
). 17.
A.
Khosla
, P.
Khandnor
, and T.
Chand
, “A novel method for EEG based automated eyes state classification using recurrence plots and machine learning approach
,” Concurr. Comput.: Pract. Exp.
34
(13
), e6912
(2022
). 18.
G.
Guglielmo
, T. J.
Wiltshire
, and M. M.
Louwerse
, “Training machine learning models to detect group differences in neurophysiological data using recurrence quantification analysis based features,” in International Conference on Agents and Artificial Intelligence (ICAART) (3) (Springer-VerlagBerlin, 2022), pp. 428–435.19.
P.
Gawade
, S.
Nandi
, C.
Meena
, and R.
Rup Sarkar
, “Artificial intelligence and machine learning techniques using omics data for cancer diagnosis and treatment,” in Systems Biomedicine Approaches in Cancer Research (Springer, 2022), pp. 23–50.20.
D. D.
Lopes
, B. R.
da Cunha
, A. F.
Martins
, S.
Gonçalves
, E. K.
Lenzi
, Q. S.
Hanley
, M.
Perc
, and H. V.
Ribeiro
, “Machine learning partners in criminal networks
,” Sci. Rep.
12
(1
), 15746
(2022
). 21.
A. A. B.
Pessa
, R. S.
Zola
, M.
Perc
, and H. V.
Ribeiro
, “Determining liquid crystal properties with ordinal networks and machine learning
,” Chaos Soliton. Fract.
154
, 111607
(2022
). 22.
H. V.
Ribeiro
, D. D.
Lopes
, A. A. B.
Pessa
, A. F.
Martins
, B. R.
da Cunha
, S.
Gonçalves
, E. K.
Lenzi
, Q. S.
Hanley
, and M.
Perc
, “Deep learning criminal networks
,” Chaos Soliton. Fract.
172
, 113579
(2023
). 23.
Y.-X.
Yang
, Z.-K.
Gao
, X.-M.
Wang
, Y.-L.
Li
, J.-W.
Han
, N.
Marwan
, and J.
Kurths
, “A recurrence quantification analysis-based channel-frequency convolutional neural network for emotion recognition from EEG
,” Chaos
28
(8
), 085724
(2018
). 24.
J.
Mitra
, P.
Mundra
, B. D.
Kulkarni
, and V. K.
Jayaraman
, “Using recurrence quantification analysis descriptors for protein sequence classification with support vector machines
,” J. Biomol. Struct. Dyn.
25
(3
), 289
–297
(2007
). 25.
M.
Mohebbi
and H.
Ghassemian
, “Prediction of paroxysmal atrial fibrillation using recurrence plot-based features of the RR-interval signal
,” Physiol. Meas.
32
(8
), 1147
(2011
). 26.
B. J.
Ricketts
, J. F.
Steiner
, C.
Garraffo
, R. A.
Remillard
, and D.
Huppenkothen
, “Mapping the x-ray variability of GRS 1915
105 with machine learning
,” Mon. Not. R. Astron. Soc.
523
(2
), 1946
–1966
(2023
). 27.
R.
Barrio
, Á.
Lozano
, A.
Mayora-Cebollero
, C.
Mayora-Cebollero
, A.
Miguel
, A.
Ortega
, S.
Serrano
, and R.
Vigara
, “Deep learning for chaos detection
,” Chaos
33
(7
), 073146
(2023
). 28.
D.
Patel
, D.
Canaday
, M.
Girvan
, A.
Pomerance
, and E.
Ott
, “Using machine learning to predict statistical properties of non-stationary dynamical processes: System climate, regime transitions, and the effect of stochasticity
,” Chaos
31
(3
), 033149
(2021
). 29.
J.
Adassuriya
, N.
Jayasinghe
, and K. P. S. C.
Jayaratne
, “Identifying variable stars from Kepler data using machine learning,” Euro. J. Appl. Phys.
3
(4
), 32
–37
(2021
).30.
F.
Köster
, D.
Patel
, A.
Wikner
, L.
Jaurigue
, and K.
Lüdge
, “Data-informed reservoir computing for efficient time-series prediction
,” Chaos
33
(7
), 073109
(2023
). 31.
Z.-M.
Zhai
, M.
Moradi
, L.-W.
Kong
, B.
Glaz
, M.
Haile
, and Y.-C.
Lai
, “Model-free tracking control of complex dynamical trajectories with machine learning
,” Nat. Commun.
14
(1
), 5698
(2023
). 32.
J.
Pathak
, B.
Hunt
, M.
Girvan
, Z.
Lu
, and E.
Ott
, “Model-free prediction of large spatiotemporally chaotic systems from data: A reservoir computing approach
,” Phys. Rev. Lett.
120
(2
), 024102
(2018
). 33.
N.
Marwan
and K.
Hauke Kraemer
, “Trends in recurrence analysis of dynamical systems
,” Eur. Phys. J.: Spec. Top.
232
(1
), 5
–27
(2023
). 34.
M.
Alam
and P.
Ahmed
, “Several chaotic analysis of Lorenz system
,” Eur. Sci. J.
13
, 438
–455
(2017
).35.
K. M.
Ibrahim
, R. K.
Jamal
, and F. H.
Ali
, “Chaotic behaviour of the Rossler model and its analysis by using bifurcations of limit cycles and chaotic attractors,” J. Phys. Conf. Ser.
1003, 012099 (2018).36.
C.
Meena
, P.
Deep Rungta
, and S.
Sinha
, “Resilience of networks of multi-stable chaotic systems to targeted attacks
,” Eur. Phys. J. B
93
, 1
–9
(2020
). 37.
Z.
Chen
, Y.
Yang
, G.
Qi
, and Z.
Yuan
, “A novel hyperchaos system only with one equilibrium
,” Phys. Lett. A
360
(6
), 696
–701
(2007
). 38.
N.
Stankevich
, A.
Kazakov
, and S.
Gonchenko
, “Scenarios of hyperchaos occurrence in 4D Rössler system
,” Chaos
30
(12
), 123129
(2020
). 39.
Y.
Li
, X.
Liu
, G.
Chen
, and X.
Liao
, “A new hyperchaotic Lorenz-type system: Generation, analysis, and implementation
,” Int. J. Circuit Theory Appl.
39
(8
), 865
–879
(2011
). 40.
L.
Noakes
, “The Takens embedding theorem
,” Int. J. Bifurcat. Chaos
1
(04
), 867
–872
(1991
). 41.
G.
Ambika
and K. P.
Harikrishnan
, “Methods of nonlinear time series analysis and applications: A review,” in Energy, Environment, and Sustainability (Springer, 2019).42.
L.
Peppoloni
, E. L.
Lawrence
, E.
Ruffaldi
, and F. J.
Valero-Cuevas
, “Characterization of the disruption of neural control strategies for dynamic fingertip forces from attractor reconstruction
,” PLoS One
12
, e0172025
(2017
). 43.
A.
Krakovská
, K.
Mezeiová
, and H.
Budáčová
, “Use of false nearest neighbours for selecting variables and embedding parameters for state space reconstruction
,” J. Complex Syst.
2015
, 932750
(2015
).44.
J.-P.
Eckmann
, S.
Oliffson Kamphorst
, and D.
Ruelle
, “Recurrence plots of dynamical systems
,” World Sci. Ser. Nonlinear Sci., Ser. A
16
, 441
–446
(1995
).45.
B. G.
Straiotto
, N.
Marwan
, D. C.
James
, and P. J.
Seeley
, “Recurrence analysis discriminates martial art movement patterns
,” Eur. Phys. J. Spec. Top.
232
(1
), 151
–159
(2023
). 46.
N.
Marwan
, “How to avoid potential pitfalls in recurrence plot based data analysis
,” Int. J. Bifurcat. Chaos
21
(04
), 1003
–1017
(2011
). 47.
B.
Ambrożkiewicz
, N.
Meier
, Y.
Guo
, G.
Litak
, and A.
Georgiadis
, “Recurrence-based diagnostics of rotary systems,” IOP Conf. Ser. Mater. Sci. Eng.
710, 012014 (2019).48.
J.
Donges
, J.
Heitzig
, B.
Beronov
, M.
Wiedermann
, J.
Runge
, Q.
Feng
, L.
Tupikina
, V.
Stolbova
, R.
Donner
, H.
Dijkstra
, and J.
Kurths
, “Unified functional network and nonlinear time series analysis for complex systems science: The pyunicorn package
,” Chaos
25
, 113101
(2015
). 49.
Y.
Chen
, S.
Su
, and H.
Yang
, “Convolutional neural network analysis of recurrence plots for anomaly detection
,” Int. J. Bifurcat. Chaos
30
(01
), 2050002
(2020
). 50.
A.
Rysak
, M.
Sedlmayr
, and M.
Gregorczyk
, “Revealing fractionality in the Rössler system by recurrence quantification analysis
,” Eur. Phys. J. Spec. Top.
232
(1
), 83
–98
(2023
). 51.
G.
Mao
and N.
Zhang
, “Analysis of average shortest-path length of scale-free network
,” J. Appl. Math.
2013
, 865643
(2013
). 52.
M. E. J.
Newman
, “The structure and function of complex networks
,” SIAM Rev.
45
(2
), 167
–256
(2003
). 53.
A.
Ben-Yishai
and O.
Ordentlich
, “Constructing multiclass classifiers using binary classifiers under log-loss,” in 2021 IEEE International Symposium on Information Theory (ISIT) (IEEE, 2021), pp. 2435–2440.54.
D.
Richard Cutler
, T. C.
Edwards Jr
, K. H.
Beard
, A.
Cutler
, K. T.
Hess
, J.
Gibson
, and J. J.
Lawler
, “Random forests for classification in ecology
,” Ecology
88
(11
), 2783
–2792
(2007
). 55.
N.
Mohd Ali
, R.
Besar
, and N.
Azlina Ab Aziz
, “A case study of microarray breast cancer classification using machine learning algorithms with grid search cross validation
,” Bull. Electr. Eng. Inf.
12
(2
), 1047
–1054
(2023
). 56.
I.
Shadeed Al-Mejibli
, J. K.
Alwan
, and H.
Abd Dhafar
, “The effect of gamma value on support vector machine performance with different kernels
,” Int. J. Electr. Comput. Eng.
10
(5
), 5497
(2020
).57.
J.
Wainer
and P.
Fonseca
, “How to tune the RBF SVM hyperparameters?: An empirical evaluation of 18 search algorithms,” Artif. Intell. Rev.
54
(6
), 4771
–4797
(2021
).58.
G.
Rabby
and P.
Berka
, “Multi-class classification of COVID-19 documents using machine learning algorithms
,” J. Intell. Inf. Syst.
60
, 571
–591
(2022
). 59.
H.
Jürgen Korsch
, H.-J.
Jodl
, and T.
Hartmann
, “The duffing oscillator,” in Chaos: A Program Collection for the PC (Springer, 2008), pp. 157–184.60.
R.
Jacob
, K. P.
Harikrishnan
, R.
Misra
, and G.
Ambika
, “Characterization of chaotic attractors under noise: A recurrence network perspective
,” Commun. Nonlinear Sci. Numer. Simul.
41
, 32
–47
(2016
). 61.
J.
Robert Buchler
, Z.
Kolláth
, and R.
Cadmus
, “Chaos in the music of the spheres,” AIP Conf. Proc.
622, 61–73 (2002).62.
Z.
Kolláth
, J. R.
Buchler
, T.
Serre
, and J.
Mattei
, “Analysis of the irregular pulsations of AC Herculis
,” Astron. Astrophys.
329
, 147
–154
(1998
).63.
S.
Chen
, S.
Feng
, W.
Fu
, and Y.
Zhang
, “Logistic map: Stability and entrance to chaos,” J. Phys. Conf. Ser.
2014, 012009 (2021).64.
Z.
Galias
, “Are numerical studies of long term dynamics conclusive: The case of the Hénon map,” J. Phys. Conf. Ser.
692, 012001 (2016).65.
N.
Marwan
, N.
Wessel
, U.
Meyerfeldt
, A.
Schirdewan
, and J.
Kurths
, “Recurrence-plot-based measures of complexity and their application to heart-rate-variability data
,” Phys. Rev. E
66
(2
), 026702
(2002
). 66.
B.
Kliková
and A.
Raidl
, “Reconstruction of phase space of dynamical systems using method of time delay,” in Proceedings of the 20th Annual Conference of Doctoral Students-WDS (Matfyzpress, 2011), pp. 83–87.67.
N.
Marwan
, J. F.
Donges
, Y.
Zou
, R. V.
Donner
, and J.
Kurths
, “Complex network approach for recurrence analysis of time series
,” Phys. Lett. A
373
(46
), 4246
–4254
(2009
). © 2024 Author(s). Published under an exclusive license by AIP Publishing.
2024
Author(s)
You do not currently have access to this content.
