Cybernetics And Systems Analysis logo
Editorial Board Announcements Abstracts Authors Archive
KIBERNETYKA TA SYSTEMNYI ANALIZ
International Theoretical Science Journal
Volume 60 >>> № 5 SEPTEMBER — OCTOBER 2024
-->

DOI 10.34229/KCA2522-9664.24.5.16
UDC 53.088.3+53.088.7
D. Onufriienko1, Yu. Taranenko2, O. Oliinyk3, V. Lopatin4


1 National Technical University “Kharkiv Polytechnic Institute,” Kharkiv, Ukraine

 оnufrienkoresearcher@gmail.com

2 “Likopak” Private Enterprise, Dnipro, Ukraine

 tatanen@ukr.net

3 Dnipro Applied College of Radio Electronics, Dnipro, Ukraine

 oleinik_o@ukr.net

4 M.S. Poliakov Institute of Geotechnical Mechanics, National Academy of Sciences of Ukraine, Dnipro, Ukraine

 vlop@ukr.net

RECOGNITION OF IMAGES OF CONTINUOUS WAVELET SPECTRA OF NOISED
RADIO LOCATION SIGNALS USING A CONVOLUTIONAL NEURAL NETWORK

Abstract. The paper considers the existing methods of image recognition of continuous wavelet spectra of noisy signals with linear and nonlinear frequency modulation using convolutional neural networks. A procedure for preparing spectral images for processing in a neural network is proposed, which ensures a sufficient probability of recognizing a given type of signal out of twenty possible ones. The methodology for solving the problem consists of finding an image preparation algorithm that provides image augmentation by the method of changing continuous wavelets, which ensures the identification of signals under conditions of limited resonance frequency and bandwidth. The algorithm involves changing the frequency of the continuous spectrum by processing the phase grating signal with different continuous wavelets after the additive addition of non-stationary noise. Signals with linear and nonlinear modulation prepared in this way, as well as signal spectra of other regular forms, are used as input data of the convolutional neural network. The procedure of dividing wavelet spectrum images into classes is performed by checking the homogeneity of the class based on the Shannon entropy value. The minimum entropy value indicates the homogeneity of the subset and the absence of “impurities” from images of other classes. The developed model of a neural network with augmentation by continuous wavelet spectra in the conditions of a limited data set has an accuracy of up to 97.95%.

Keywords: augmentation, wavelet spectrum, convolutional neural networks, continuous wavelets, unmanned aerial vehicles.


full text

REFERENCES

  • 1. Fujiyoshi H., Hirakawa T., Yamashita T. Deep learning-based image recognition for autonomous driving. IATSS Research. 2019. Vol. 43, Iss. 4. Р. 244–252. doi.org/10.1016/j.iatssr.2019.11.008.

  • 2. Traore B.B., Kamsu-Foguem B., Tangara F. Deep convolution neural network for image recognition. Ecological Informatics. 2018. Vol. 48. Р. 257–268. doi.org/10.1016/j.ecoinf.2018.10.002.

  • 3. Ramzi Z., Michalewicz K., Starck J.-L., Moreau T., Ciuciu P. Wavelets in the deep learning era. Journal of Mathematical Imaging and Vision. 2023. Vol. 65, N 1. Р. 240–251. doi.org/10.1007/s10851-022-01123-w .

  • 4. Abdel-Khalek S., Algarni M., Mansour R.F., Gupta D., Ilayaraja M. Quantum neural network-based multilabel image classification in high-resolution unmanned aerial vehicle imagery. Soft Computing. 2021. Vol. 27. Р. 1–12. doi.org/10.1007/s00500-021-06460-3.

  • 5. Walenczykowska М., Kawalec A., Krenc K. An application of analytic wavelet transform and convolutional neural network for radar intrapulse modulation recognition. Sensors. 2023. Vol. 23, N 4. 1986. doi.org/10.3390/s23041986.

  • 6. Li H., Zhao J. Analysis of a combined waveform of linear frequency modulation and phase coded modulation. Proc. of the 2016 11th International Symposium on Antennas, Propagation and EM Theory (ISAPE) (18–21 Oct., 2016, Guilin, China). IEEE, 2016. Р. 539–541. doi.org/10.1109/ISAPE.2016.7834008.

  • 7. Taranenko Yu.K., Lopatin V.V., Oliynyk O.Yu. Wavelet filtering by using nonthreshold method and example of model Doppler function. Radioelectronics and Communications Systems. 2021. Vol. 64. Р. 380–389. doi.org/10.3103/S0735272721070049.

  • 8. Taranenko Yu.K., Oliynyk O. Yu. Optimization of the packet wavelet filtering algorithm of signals. Cybernetics and Systems Analysis. 2024. Vol. 60, N 1. Р. 163–174. doi.org/10.1007/s10559-024-00654-x .

  • 9. Chen L., Li S., Bai Q., Yang J., Jiang S., Miao Y. A Review of image classification algorithms based on convolutional neural networks. Remote Sensing. 2021. Vol. 13, N 22. 4712. doi.org/10.3390/rs13224712.

  • 10. Sun Y., Zhang M., Yen G. Evolving deep convolutional neural networks for image classification. IEEE Transactions on Evolutionary Computation. 2020. Vol. 24, N 2. Р. 394–407. doi.org/10.1109/TEVC.2019.2916183.

  • 11. Niranjan R., Rao C.R., Singh A., Real-time identification of exotic modulated radar signals for electronic intelligence systems. 2021 Emerging Trends in Industry 4.0 (ETI 4.0) (19–21 May, 2021, Raigarh, India). 2021. Р. 1–4. doi.org/10.1109/ETI4.051663.2021.9619339.

  • 12. Wang C., Wang J., Zhang X. Automatic radar waveform recognition based on time-frequency analysis and convolutional neural network. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (5–9 March, 2017, New Orleans, LA, USA). 2017. Р. 2437–2441. doi.org/10.1109/ICASSP.2017.7952594.

  • 13. Taranenko Yu.K., Rizun N.O. Wavelet filtering of signals without using model functions. News of higher educational institutions. Radioelectronics. 2022. Vol. 65, N 2. P. 110–125. doi.org/10.20535/S0021347022020042.

  • 14. Solovyov V.I., Rybalsky O.V., Zhuravel V.V., Shablya A.N., Timko E.V. Taking into account the multifactorial nature of voice characteristics in speaker identification problems. International scientific and technical journal “Problems of science and informatics”. 2021. N 5. P. 21–30. doi.org/10.34229/1028-0979-2021-5-2.

  • 15. Zavolodko G., Pavlova D., Kolesnikova Y., Sukmanskyi M. Interstage optimization of data processing of distributed airspace monitoring systems. IT Synergy. 2021. N 1. P. 58–65. doi.org/10.53920/ITS-2021-1-7.

  • 16. da Silva H.T., Alves D.I., Machado R., Passaro A. A Methodology for assessing data augmentation effectiveness for target classification in SAR images. 2024 IEEE Radar Conference (RadarConf24) (06–10 May, 2024, Denver, CO, USA). IEEE, 2024. P. 1–6. doi.org/10.1109/RadarConf2458775.2024.10548664

  • 17. Oliinyk О., Taranenko Yu., Lopatin V. Analysis of discrete wavelet spectra of broadband signals. CMIS-2023 (The Sixth International Workshop on Computer Modeling and Intelligent Systems) (3 May, 2023, Zaporizhzhia, Ukraine). 2023. P. 188–198.

  • 18. Taranenko Yu.K. Methods of discrete wavelet filtering of measurement signals: An algorithm for choosing a method. Measurement Techniques. 2022. Vol. 64. P. 801–808. doi.org/10.1007/s11018-022-02007-6.

  • 19. A guide for using the Wavelet Transform in Machine Learning. A guide for using the Wavelet Transform in Machine Learning — ML Fundamentals. URL: ataspinar.com.

  • 20. Zharkikh A.A., Kvaschenko V.A. Comparison of the accuracy of representation of Gaussian wavelets of different orders. Bulletin of Moscow State Technical University. 2009. Vol. 12, N 2. P. 218–223.

  • 21. Convolutional neural network in Python. URL: www.100byte.ru/python/MNIST_ NN/mnist_nn.html#p1.

  • 22. Continuous wavelet transform (CWT). URL: https://pywavelets.readthedocs.io/en/latest/ref/cwt.html .

  • 23. Onufrienko D., Taranenko Yu., Suchkov G. Improving metrological characteristics of measuring instruments by discrete wavelet noise filtering using the recursion method. Ukrainian Metrological Journal. 2022. N 2. Р. 15–20. doi.org/10.24027/2306-7039.2.2022.263869.

  • 24. Skladchikov I.O. Automated analysis of security thermal imager data based on deep learning. XIII All-Ukrainian Scientific and Practical Conference of Students, Postgraduates and Young Scientists «Looking into the Future of Instrument Building» (13–14 May, 2020, Kyiv, Ukraine). 2020. Р. 315–318.

  • 25. Oliynyk O., Taranenko Y., Losikhin D., Shvachka A. Examining the Kalman filter in the field of noise and interference with the non-Gaussian distribution. Eastern-European Journal of Enterprise Technologies. 2018. Vol. 4, N 4(94). Р. 36–42. doi.org/10.15587/1729-4061.2018.140649.

  • 26. Litvinchuk A.M., Baranovska L.V. Improving face recognition models using similarity learning, learning rate change schedule, and augmentations. International Scientific and Technical Journal "Problems in Control and Informatics". 2021. Vol 6. P. 93–101. doi.org/10.34229/1028-0979-2021-6-9.

  • 27. Chaikovskyi O., Volokita A., Kir'yanov A., Lutskyi G. Data augmentation method using generative competitive networks. Technical sciences and technologies. 2021. Vol. 2(24). P. 83–91. doi.org/10.25140/2411-5363-2021-2(24)-83-91.

  • 28. Joseph F.J.J., Nonsiri S., Monsakul A. Keras and TensorFlow: A hands-on experience. In: Advanced Deep Learning for Engineers and Scientists. EAI/Springer Innovations in Communication and Computing. Prakash K.B., Kannan R., Alexander S., Kanagachidambaresan G.R. (Eds.). Cham: Springer, 2021. P. 85–111. doi.org/10.1007/978-3-030-66519-7_4.

  • 29. Bazi Y., Melgani F. Convolutional SVM networks for object detection in UAV imagery. IEEE Transactions on Geoscience and Remote Sensing. 2018. Vol. 56, N 6. Р. 3107–3118. doi.org/10.1109/TGRS.2018.2790926.

  • 30. Kovbasyuk C.V., Osadchuk R.M., Romanchuk M.P., Naumchak L.M. Algorithm for forming a set of a priori neural network data for processing digital aerial photographs. Problems of creation, testing, application and operation of complex information systems: Collection of scientific works of ZVI. 2022. Iss. 23. P. 77–88. doi.org/10.46972/2076-1546.2022.23.06.




Editorial Board Announcements Abstracts Authors Archive
about scope office editorial board instructions for authors subscriptions contacts
© 2024 Kibernetika.org. All rights reserved.