NEURAL NETWORK-ASSISTED CONTINUOUS EMBEDDING OF UNIVARIATE DATA STREAMS FOR TIME SERIES ANALYSIS
DOI:
https://doi.org/10.34185/1562-9945-2-151-2024-08Keywords:
time series analysis, time series embedding, dimensionality reductionAbstract
Univariate time series analysis is a universal problem that arises in various science and engineering fields and the approaches and methods developed around this problem are diverse and numerous. These methods, however, often require the univariate data stream to be transformed into a sequence of higher-dimensional vectors (embeddings). In this article, we explore the existing embedding methods, examine their capabilities to perform in real-time, and propose a new approach that couples the classical methods with the neural network-based ones to yield results that are better in both accuracy and computational performance. Specifically, the Broomhead-King-inspired embedding algorithm implemented in a form of an autoencoder neural network is employed to produce unique and smooth representation of the input data fragments in the latent space.
References
Broomhead D.S. and King G. P. (1986). Extracting qualitative dynamics from experimental data. Physica D: Nonlinear Phenomena, Volume 20 (2-3), Pages 217-236. https://doi.org/10.1016/0167-2789(86)90031-X.
Cao, L. (1997). Practical method for determining the minimum embedding dimension of a scalar time series. Physica D: Nonlinear Phenomena, Volume 110 (1-2), 43-50, https://doi.org/10.1016/S0167-2789(97)00118-8.
Chakraborty, B. (2014).A Proposal for Classification of Multisensor Time Series Data based on Time Delay Embedding. International Journal on Smart Sensing and Intelligent Systems,7(5) 1-5. https://doi.org/10.21307/ijssis-2019-120
Datseris, G. (2018). DynamicalSystems.jl: A Julia software library for chaos and nonlinear dynamics. Journal of Open Source Software, 3(23), Pages 598, https://doi.org/10.21105/joss.00598
Frank, J., Mannor, S., & Precup, D. (2010). Activity and Gait Recognition with Time-Delay Embeddings. Proceedings of the AAAI Conference on Artificial Intelligence, 24(1), Pages 1581-1586. https://doi.org/10.1609/aaai.v24i1.7724
Geist K., Parlitz U., and Lauterborn W., (1990). Comparison of Different Methods for Computing Lyapunov Exponents, Progress of Theoretical Physics, Volume 83 (5), Pages 875–893, https://doi.org/10.1143/PTP.83.875
Gupta, V. and Mittal, M. (2019). QRS Complex Detection Using STFT, Chaos Analysis, and PCA in Standard and Real-Time ECG Databases. J. Inst. Eng. India Ser. B 100, 489–497. https://doi.org/10.1007/s40031-019-00398-9
Hegger R. and Kantz H. (1999). Improved false nearest neighbor method to detect determinism in time series data. Phys. Rev. E, Volume 60, Pages 4970-4973, https://doi.org/10.1103/PhysRevE.60.4970
Kennel M. B., Brown R., and Abarbanel H. D. I. (1992). Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys. Rev. A, Volume 45, Pages 3403–3411, https://doi.org/10.1103/PhysRevA.45.3403.
Kıymık M. K., Güler İ., Dizibüyük A., and Akın M. (2005). Comparison of STFT and wavelet transform methods in determining epileptic seizure activity in EEG signals for real-time application, Computers in Biology and Medicine, Volume 35, Issue 7, 603-616, ISSN 0010-4825,
https://doi.org/10.1016/j.compbiomed.2004.05.001.
Koshel, E. (2020). Local jacobian estimation for delay embedded time series data. In XVIIІ International scientific and practical conference, Dnipro (pp. 152-153).
Koshel Y. V. and Belozyorov V. Y. (2023). Univariate Time Series Analysis with Hyper Neural ODE. Journal of Optimization, Differential Equations and Their Applications (JODEA), 31(2), 50-66.
Krakovská A., Mezeiová K., and Budáčová H. (2015). Use of False Nearest Neighbours for Selecting Variables and Embedding Parameters for State Space Reconstruction. Journal of Complex Systems, Volume 2015,
https://doi.org/10.1155/2015/932750.
Nalmpantis, C., Vrakas, D. (2019). Signal2Vec: Time Series Embedding Representation, Engineering Applications of Neural Networks. EANN 2019. Communications in Computer and Information Science, vol 1000. https://doi.org/10.1007/978-3-030-20257-6_7
Pecora L. M., Moniz L., Nichols J., and Carroll T. L. (2007). A unified approach to attractor reconstruction. Chaos, Volume 17 (1). https://doi.org/10.1063/1.2430294
Takens, F. (1981). Detecting strange attractors in turbulence. In: Rand, D., Young, LS. (eds) Dynamical Systems and Turbulence, Warwick 1980. Lecture Notes in Mathematics, vol 898. Springer, Berlin, Heidelberg.
https://doi.org/10.1007/BFb0091924
Tüske, Z., Golik, P., Schlüter, R., & Drepper , F. R. (2011). Non-stationary feature extraction for automatic speech recognition, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, 5204-5207, doi: 10.1109/ICASSP.2011.5947530.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 System technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
