Abstract
We present a framework for multivariate nonlinear time series forecasting that utilizes phase space image representations and deep learning. Recurrence plots (RP) are a phase space visualization tool used for the analysis of dynamical systems. This approach takes advantage of recurrence plots that are used as input image representations for a class of deep learning algorithms called convolutional neural networks. We show that by leveraging recurrence plots with optimal embedding parameters, appropriate representations of underlying dynamics are obtained by the proposed autoregressive deep learning model to produce forecasts.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
J.P. Eckmann, S. Oliffson Kamphorst, D. Ruelle, Recurrence plots of dynamical systems. Europhys. Lett. 4(9), 973–977 (1987). https://doi.org/10.1209/0295-5075/4/9/004
M.C. Casdagli, Recurrence plots revisited. Phys. D 108(1–2), 12–44 (1997). https://doi.org/10.1016/S0167-2789(97)82003-9
M. Thiel, M.C. Romano, J. Kurths, How much information is contained in a recurrence plot? Phys. Lett. A 330(2004), 343–349 (2004). https://doi.org/10.1016/j.physleta.2004.07.050
W. Liebert, H.G. Schuster, Proper choice of the time delay for the analysis of chaotic time series. Phys. Lett. A 142(2, 3), 107–111 (1989). https://doi.org/10.1016/0375-9601(89)90169-2
A.M. Fraser, H.G. Swinney, Independent coordinates for strange attractors from mutual information. Phys. Rev. A 33(2), 1134 (1986). https://doi.org/10.1103/PhysRevA.33.1134
M.B. Kennel, R. Brown, H.D.I. Abarbanel, Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys. Rev. A 45, 3403 (1992). https://doi.org/10.1103/PhysRevA.45.3403
J.S. Iwanski, E. Bradley, Recurrence plots of experimental data: to embed or not to embed. Chaos 8, 861–871 (1998). https://doi.org/10.1063/1.166372
J. Gao, H. Cai, On the structures and quantification of recurrence plots. Phys. Lett. A 270(1–2), 75–87 (2000). https://doi.org/10.1016/S0375-9601(00)00304-2
T. Gautama, D.P. Mandic, M.M. Van Hulle, A differential entropy based method for determining the optimal embedding parameters of a signal, in 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003, Proceedings, (ICASSP ’03) (Hong Kong, 2003), pp. VI–29. https://doi.org/10.1109/ICASSP.2003.1201610
N. Marwan, J. Kurths, P. Saparin, Generalised recurrence plot analysis for spatial data. Phys. Lett. A 360(2007), 545–551 (2007). https://doi.org/10.1209/0295-5075/4/9/004
A. Sipers, P. Borm, R. Peeters, On the unique reconstruction of a signal from its unthresholded recurrence plot. Phys. Lett. A 375(2011), 2309–2321 (2011). https://doi.org/10.1016/j.physleta.2011.04.040
O.A.B. Penatti, M.F.S. Santos, Human activity recognition from mobile inertial sensors using recurrence plots (2017). ArXiv. Availablehttps://arxiv.org/pdf/2004.13408.pdf. Accessed 31 Aug 2020
N. Marwan, A historical review of recurrence plots. Eur. Phys. J. Spec. Top. 164(2008), 3–12 (2008). https://doi.org/10.1209/0295-5075/4/9/004
B. Lim, S. Zohren, Time series forecasting with deep learning: a survey (2020). ArXiv. Available, https://arxiv.org/pdf/2004.13408.pdf. Accessed 24 Aug 2020
J.M. Sotoca, J.S. Sánchez, R.A. Mollineda, A review of data complexity measures and their applicability to pattern classification problems, in Actas del III Taller Nacional de MinerÃade Datos y Aprendizaje (TAMIDA, 2005), pp. 77–83
L. Li, Y.S. Abu-Mostafa, Data complexity in machine learning. Caltech Computer Science Technical Reports (2006). https://doi.org/10.7907/Z9319SW2
W.A. Brock, J.A. Scheinkman, W.D. Dechert, B. LeBaron, A test for independence based on the correlation dimension. Econ. Rev. 15(3), 197–235 (1996)
J. Belaire-Franch, D. Contreras, How to compute the BDS test: a software comparison. J. Appl. Econ. 17, 691–699 (2002). https://doi.org/10.1002/jae.679
E. Zivot, Nonlinear time series models (n.d.). https://faculty.washington.edu/ezivot/econ584/notes/nonlinear.pdf. Accessed 24 Aug 2020
R.J. Hyndman, G. Athanasopoulos, ARIMA Models, in Forecasting: Principles and Practice, 2nd edn. (OTexts, Melbourne, Australia, 2018), pp. 221–274
S.S. Rao, A course in time series analysis (2020). https://www.stat.tamu.edu/~suhasini/teaching673/time_series.pdf. Accessed 29 Aug 2020
B. Pesaran, Spectral analysis for neural signals (2020). https://neurophysics.ucsd.edu/courses/physics_173_273/SfN_Short_Course_c1.pdf. Accessed 29 Aug 2020
Z. Wang, T. Oates, Visual interpretation of hand gestures for human computer interaction: a review, in Paper presented at the Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. (Buenos Aires, Argentina, 2015). 25–31 July 2015
N. Hatami, Y. Gavet, J. Debayle, Paper presented at the Tenth International Conference on Machine Visio (Vienna, Austria, 2017). 13–15 Nov 2017
Y. Hsueh, V.R. Ittangihala, W. Wu et al., Condition monitor system for rotation machine by CNN with recurrence plot. Energies 12, 3221 (2019). https://doi.org/10.3390/en12173221
Z. Zhao, Y. Zhang, Z. Comert, Y. Deng, Computer-aided diagnosis system of fetal hypoxia incorporating recurrence plot with convolutional neural network. Front. Physiol. (2019). https://doi.org/10.3389/fphys.2019.00255
E. Garcia-Ceja, M.Z. Uddin, J. Torresen, Classification of recurrence plot’ distance matrices with a convolutional neural network for activity recognition. Procedia Comput. Sci. 130, 157–163 (2018). https://doi.org/10.1016/j.procs.2018.04.025
S.A.A. Ojeda, G.A. Solano, E.C. Peramo, Multivariate time series imaging for short-term precipitation forecasting using convolutional neural networks, in 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (2020). https://doi.org/10.1109/icaiic48513.2020.9065238
R.J. Hyndman, Y. Khandakar, Automatic time series forecasting: the forecast package for R. J. Stat. Softw. (2008). https://doi.org/10.18637/jss.v027.i03
L. Cao, Practical method for determining the minimum embedding dimension of a scalar time series. Phys. D: Nonlinear Phenom. 110, 43–50 (1997). https://doi.org/10.1016/s0167-2789(97)00118-8
E. Keogh, K. Chakrabarti, M. Pazzani, S. Mehrotra, Dimensionality reduction for fast similarity search in large time series databases. Knowl. Inf. Syst. 3, 263–286 (2001). https://doi.org/10.1007/pl00011669
N. Marwan, How to avoid potential pitfalls in recurrence plot based data analysis. Int. J. Bifurc. Chaos 21, 1003–1017 (2011). https://doi.org/10.1142/s0218127411029008
A. Zhang, Z. Lipton, M. Li, et al., Convolutional neural networks, in Convolutional Neural Networks—Dive into Deep Learning 0.14.3 documentation (n.d.). http://d2l.ai/chapter_convolutional-neural-networks/index.html. Accessed 31 Aug 2020
I. Goodfellow, Y. Bengio, A. Courville, Convolutional Networks, in Deep Learning. (The MIT Press, Cambridge, MA, 2017), pp. 330–371
S. Ioffe, C. Szegedy, Batch normalization: accelerating deep network training by reducing internal covariate shift 37, 448–456 (2015)
N. Srivastava, G. Hinton, A. Krizhevsky, Dropout: a simple way to prevent neural networks from overfitting 15(56), 1929–1958 (2014)
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https://doi.org/10.1109/cvpr.2016.90
L. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015). https://doi.org/10.1109/cvpr.2015.7298965
I.F. Hassan, B. Lucas, G. Forestier, C. Pelletier, et al., InceptionTime: finding alexnet for time series classification (2019). arXiv:1909.04939
C.W. Tan, C. Bergmeir, F. Petitjean, G.I. Webb, Time series regression (2020). arXiv:2006.12672
J. Borkowski, Blocked designs (2014). http://www.math.montana.edu/jobo/thainp/ksampa.pdf. Accessed 31 Aug 2020
J. Demsar, Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7(Jan), 1–30 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Ojeda, S.A.A., Peramo, E.C., Solano, G.A. (2022). Application of Deep Learning in Recurrence Plots for Multivariate Nonlinear Time Series Forecasting. In: Tsihrintzis, G.A., Virvou, M., Jain, L.C. (eds) Advances in Machine Learning/Deep Learning-based Technologies. Learning and Analytics in Intelligent Systems, vol 23. Springer, Cham. https://doi.org/10.1007/978-3-030-76794-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-76794-5_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76793-8
Online ISBN: 978-3-030-76794-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)