Deep Learning for Classifying Chaotic Signals Transformed by Advanced Techniques
Keywords:
analytic chaotic sequences, Chebyshev polynomials, ResNet34, signal classification, deep learningAbstract
The rapid evolution of stealthy signals has introduced significant challenges in signal classification, necessitating advanced methodologies for accurate identification and characterization. This study investigates the classification of chaotic signals transformed into Analytic Chaotic Sequences. We utilized a ResNet34 architecture, adapted for one-dimensional signal data, to assess how varying network depths influence classification performance. The dataset comprised sequences with frequency- dependent variations, and the model’s robustness was evaluated under varying noise levels. Results indicate that while the full ResNet34 model maintains high accuracy at elevated signal-to-noise ratios, its performance deteriorates with increased noise. In contrast, models with reduced depths (1, 2, and 3 layers) exhibit improved adaptability and noise resilience. Notably, the 2-layer and 3-layer ResNet34 variants show greater robustness in noisy conditions, suggesting practical benefits for real-world applications. This research highlights the importance of network depth and frequency adaptation in chaotic signal classification, emphasizing that simplified models can provide efficient performance and competitive accuracy, particularly in environments with fluctuating noise levels. Future work will optimize the ResNet34 architecture and expand the dataset to enhance generalization and robustness.
References
N. Rowe and D. Saha, “DetecSHUN: Detection of signals hidden under the noise,” in Proc. of the 2024 ACM Workshop on Wireless Security and Machine Learning, 2024, pp. 38–43. https://doi.org/10.1145/3649403.3656488.
L. Ashiku and C. Dagli, “Network intrusion detection system using deep learning,” Procedia Computer Science, vol. 185, pp. 239–247, 2021. https://doi.org/10.1016/j.procs.2021.05.025.
G. A. Al-Suhail, F. R. Tahir, M. H. Abd, V.-T. Pham, and L. Fortuna, “Modelling of long-wave chaotic radar system for anti-stealth applications,” Communications in Nonlinear Science and Numerical Simulation, vol. 57, pp. 80–96, 2018. https://doi.org/10.1016/j.cnsns.2017.09.008.
V. Dubey, “Analysis of chaotic communication over traditional communication,” International Journal of Innovative Research in Computer and Communication Engineering, vol. 3, pp. 3967–3975, 2015. https://doi.org/10.15680/ijircce.2015.0305033.
M. A. Aziz-Alaoui, “A survey of chaotic synchronization and secure communication,” in Proc. of the 12th IEEE Int. Conf. on Electronics, Circuits and Systems, 2005, pp. 1–4. https://doi.org/10.1109/ICECS.2005.4633618.
N. Smaoui, A. Karouma, and M. Zribi, “Secure communications based on the synchronization of the hyperchaotic Chen and the unified chaotic systems,” Communications in Nonlinear Science and Numerical Simulation, vol. 16, no. 8, pp. 3279–3293, 2011. https://doi.org/10.1016/j.cnsns.2010.10.023.
S. Kacar, S. Uzun, and B. Aricioglu, “Deep learning-based classification of chaotic systems over phase portraits,” Turkish Journal of Electrical Engineering and Computer Sciences, vol. 31, pp. 17–38, 2023. https://doi.org/10.55730/1300-0632.3969.
H. Kantz and T. Schreiber, Nonlinear Time Series Analysis. Cambridge University Press, 2004. https://doi.org/10.1017/CBO9780511755798.
M. Andriychuk, Chaos Theory. Rijeka: IntechOpen, 2024. https://doi.org/10.5772/intechopen.104024.
P. Yu. Kostenko, K. S. Vasiuta, and S. N. Symonenko, “Nonparametric BDS detector of chaotic signals against the background of white noise,” Radioelectronics and Communication Systems, vol. 54, pp. 19–25, 2011. https://doi.org/10.3103/S0735272711010031.
B. Lebaron, “A fast algorithm for the BDS statistic,” Studies in Nonlinear Dynamics and Econometrics, vol. 2, 1997. https://doi.org/10.2202/1558- 3708.1029.
A. I. Tsopa, D. G. Ganshin, A. A. Dudka, and A. N. Bitchenko, “Analysis of the structural secrecy of multifrequency signals of broadband communication systems,” Radiotekhnika, no. 184, pp. 127–134, 2016 (in Ukrainian).
J. L. Yao, M. X. He, Y. J. Ma, et al., “Design of integrated radar and communication system based on solvable chaotic signal,” Scientific Reports, vol. 14, p. 31663, 2024. https://doi.org/10.1038/s41598-024-80956-4.
K. Vasiuta, U. Zbezhkhovska, V. Slobodyanyuk, I. Zakharchenko, O. Kashchyshyn, M. Dubinskyi, Y. Riabukha, and O. Koval, “The method of increasing the stealthiness of information transmission systems based on modulating with OFDM of chaotic subcarriers,” Radioelectronic and Computer Systems, no. 3, pp. 79–93, 2021. https://doi.org/10.32620/reks.2021.3.07 (in Ukrainian).
M. Nandish, J. Kumar, H. G. Mohan, M. S. Krishnamurthy, "GraphConvDeep: A deep learning approach for enhancing binary code similarity detection using graph embeddings,” International Journal of Computer Network and Information Security (IJCNIS), vol. 17, no. 3, pp. 72-88, 2025. https://doi.org/10.5815/ijcnis.2025.03.05.
B. Jovic, “Chaotic signals and their use in secure communications,” in Chaotic Signals in Digital Communications. Springer, 2011. https://doi.org/10.1007/978-3-642-21849-1_2.
M. Small, Applied Nonlinear Time Series Analysis: Applications in Physics, Physiology and Finance. World Scientific, 2005. https://doi.org/10.1142/5722.
H. A. Elsayed and S. E. El-Khamy, “Classification of chaotic codes using fuzzy clustering techniques and higher-order statistics features,” in Proc. URSI Atlantic Radio Science Conference (URSI AT-RASC), Gran Canaria, Spain, 2015, pp. 1–6. https://doi.org/10.1109/URSI-AT- RASC.2015.7302985.
C. Couvreur, C. Flamme, and M. Pirlot, “Statistical classification of chaotic signals,” in Proc. of the IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), vol. 4, 1998, pp. 2149–2152. https://doi.org/10.1109/ICASSP.1998.681571.
A. Ohno, Y. Uwate, and Y. Nishio, “Chaotic data classification by using attractors including time information,” in Proc. of the IEEE Workshop on Non- linear Circuit Networks, 2021, pp. 69–72.
Y. Zhang and X. Chen, “Triad state space construction for chaotic signal classification with deep learning,” CoRR, vol. abs/2003.11931, 2020. https://arxiv.org/abs/2003.11931.
J. Nam and J. Kang, “Classification of chaotic signals of the recurrence matrix using a convolutional neural network and verification through the Lyapunov exponent,” Applied Sciences, vol. 11, no. 1, p. 77, 2021. https://doi.org/10.3390/app11010077.
N. Boullé, V. Dallas, Y. Nakatsukasa, and D. Samaddar, “Classification of chaotic time series with deep learning,” Physica D: Nonlinear Phenomena, 2019. https://doi.org/10.48550/arXiv.1908.06848.
P. Yu. Kostenko, K. S. Vasiuta, and S. N. Symonenko, “Improving communication security by complicating chaotic process at- tractor using linear transform with Mandelbrot kernel,” Radioelectronics and Communication Systems, vol. 53, pp. 636–643, 2010. https://doi.org/10.3103/S0735272710120022.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. of the IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. https://doi.org/10.48550/arXiv.1512.03385.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016. ISBN: 978-0262035613.
L. McInnes, J. Healy, N. Saul, and L. Großberger, “UMAP: Uniform mani- fold approximation and projection,” Journal of Open Source Software, vol. 3, no. 29, p. 861, 2018. https://doi.org/10.21105/joss.00861.
F. O. Catak, M. Kuzlu, U. Cali, “Comparative analysis of attention mechanisms for automatic modulation classification in radio frequency signals,” arXiv preprint arXiv:2508.09996, 2025.
R. H. Mohammed, A. M. El-Saieed, “Chaotic billiards optimized hybrid transformer and XGBoost model for robust and sustainable time series forecasting,” Scientific Reports, vol. 15, no. 1, 10641, 2025. https://doi.org/10.1038/s41598-025-10641-7.
L. Xiong, L. Su, X. Wang and C. Pan, “Dynamic adaptive graph convolutional transformer with broad learning system for multi-dimensional chaotic time series prediction”, Applied Soft Computing, vol. 157, 111516, 2024. https://doi.org/10.1016/j.asoc.2024.111516.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
