mireabulletinRussian Technological JournalRussian Technological Journal2782-32102500-316XRTU MIREA10.32362/2500-316X-2026-14-4-82-95VLPBLVmireabulletin-1617Research ArticleСОВРЕМЕННЫЕ РАДИОТЕХНИЧЕСКИЕ И ТЕЛЕКОММУНИКАЦИОННЫЕ СИСТЕМЫMODERN RADIO ENGINEERING AND TELECOMMUNICATION SYSTEMSГибридная архитектура нейронной сети ResBiLSTM-BiGRU для эффективного подавления шума в радиоканале с цифровыми модулированными сигналамиHybrid neural network architecture ResBiLSTM-BiGRU for efficient noise suppression in radio channels with digitally modulated signalshttps://orcid.org/0000-0002-2810-1204НгуенВ. З.NguyenV. D.

Нгуен Ван Зунг, к.т.н., преподаватель, кафедра теории цепей измерения, Факультет радиотехники и электроники

Ханой, ул. Хоанг Куок Вьет, д. 236

Nguyen Van Dung, Cand. Sci. (Eng.), Lecturer, Department of Circuit Theory Measurement, Faculty of Radio-Electronic Engineering

236, Hoang Quoc Viet, Ha Noi

nguyenvandungvtdt@lqdtu.edu.vnhttps://orcid.org/0009-0006-2093-7150ФанЧ. Х.PhanT. H.

Фан Чонг Хань, к.т.н., преподаватель, кафедра теории цепей измерения, Факультет радиотехники и электроники

Ханой, ул. Хоанг Куок Вьет, д. 236

Phan Trong Hanh, Cand. Sci. (Eng.), Lecturer, Department of Circuit Theory Measurement, Faculty of Radio-Electronic Engineering

236, Hoang Quoc Viet, Ha Noi

maitrongphan@gmail.comВьетнамский государственный технический университет им. Ле Куй ДонаВьетнамLe Quy Don Technical UniversityViet Nam2026080820261448295Copyright © Нгуен В.З., Фан Ч.Х., 20262026Нгуен В.З., Фан Ч.Х.Nguyen V.D., Phan T.H.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.rtj-mirea.ru/jour/article/view/1617Цели

Цели. Целью данной работы является разработка эффективного метода подавления аддитивного гауссовского шума в радиоканале, обеспечивающего высокое качество восстановления цифровых модулированных сигналов при низких значениях отношения сигнал/шум (signal-to-noise ratio, SNR).

Методы

Методы. Для решения поставленной задачи предложена гибридная архитектура, объединяющая рекуррентные нейронные сети типов долгой краткосрочной памяти (long short-term memory, LSTM) и управляемых рекуррентных блоков (gated recurrent unit, GRU). Модель ResBiLSTM-BiGRU обеспечивает более стабильное обучение, повышенное качество восстановления и более точное моделирование временной структуры сигналов. Эффективность модели оценивалась на многомодуляционном наборе данных при различных уровнях входного SNR.

Результаты

Результаты. Экспериментальные исследования показали, что предложенная модель в среднем обеспечивает увеличение выходного SNR на 2–3 дБ по сравнению с релятивистской усредненной генеративно-состязательной сетью (relativistic average generative adversarial networks, RaGAN) и более чем на 10 дБ по сравнению с методом на основе вейвлет-преобразования при одинаковых условиях моделирования. Модель характеризуется меньшими значениями среднеквадратической ошибки и более высокими коэффициентами корреляции во всем диапазоне входных SNR от −10 до 10 дБ. Значения пикового SNR также свидетельствуют о высоком качестве восстановления сигналов, особенно при низких уровнях входного SNR. Анализ архитектурных параметров показал, что наилучшие результаты достигаются при использовании 128 скрытых узлов и глубокой архитектуры ResBiLSTM-BiGRU.

Выводы

Выводы. Полученные результаты подтверждают эффективность и практическую применимость гибридной архитектуры ResBiLSTM-BiGRU для подавления аддитивного гауссовского шума в радиоканале и восстановления цифровых модулированных сигналов, особенно в условиях низкого SNR.

Objectives

Objectives. The work sets out to develop an effective method for suppressing additive Gaussian noise in radio channels to ensure the high-quality reconstruction of digitally modulated signals at low signal-to-noise ratio (SNR) levels. 

Methods

Methods. To address this problem, a hybrid architecture is proposed that combines Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) recurrent neural networks. The ResBiLSTM-BiGRU model enables more stable training and improved reconstruction quality, as well as more accurate modeling of the temporal structure of signals. The performance of the model was evaluated using a multi-modulation dataset with various input SNR levels. 

Results

Results. As confirmed by the experimental results, the proposed model achieves an average improvement of 2–3 dB in output SNR compared with the Relativistic Average Generative Adversarial Network (RaGAN) under identical simulation conditions, as well as a more than a 10-dB improvement as compared with the wavelet-transform-based method. The model is characterized by lower mean squared error values and higher correlation coefficients across the entire input SNR range from –10 to 10 dB. The peak SNR values also indicate high signal reconstruction quality, especially at low input SNR levels. Analysis of architectural parameters shows that the best performance is achieved with 128 hidden units and a deep ResBiLSTM-BiGRU architecture.

Conclusions

Conclusions. The obtained results confirm the effectiveness and practical applicability of the proposed ResBiLSTM-BiGRU hybrid architecture for suppressing additive Gaussian noise in radio channels and reconstructing digitally modulated signals, particularly under low-SNR conditions.

когнитивные радиосетиавтоматическая классификация модуляциисигналы цифровой модуляцииглубокое обучениегибридная сеть ResBiLSTM-BiGRUподавление шумаотношение сигнал/шумсреднеквадратическая ошибкакоэффициент корреляциипиковое отношение сигнал/шумcognitive radio networksautomatic modulation classificationdigitally modulated signalsdeep learninghybrid ResBiLSTM-BiGRU networknoise suppressionsignal-to-noise ratiomean squared errorcorrelation coefficientpeak signal-to-noise ratioReferencesWang W. Evaluation of Adaptive Filtering Algorithms in Signal Denoising: Insights from Simulation and Algorithmic Enhancement. Theoretical and Natural Science . 2025;101(1):61–69. https://doi.org/10.54254/2753-8818/2025.CH22293Wang W. Evaluation of Adaptive Filtering Algorithms in Signal Denoising: Insights from Simulation and Algorithmic Enhancement. Theoretical and Natural Science . 2025;101(1):61–69. https://doi.org/10.54254/2753-8818/2025.CH22293Lei J., Zhou J., Jian Z., Liu H., Zhang L., Feng Y., Wu Z. A Wiener Filter Denoising Based Intelligent Modulation Recognition. In: 2022 IEEE/CIC International Conference on Communications in China ( ICCC ). IEEE. 2022. P. 88–93. https://doi.org/10.1109/ICCC55456.2022.9880789Lei J., Zhou J., Jian Z., Liu H., Zhang L., Feng Y., Wu Z. A Wiener Filter Denoising Based Intelligent Modulation Recognition. In: 2022 IEEE/CIC International Conference on Communications in China ( ICCC ). IEEE. 2022. P. 88–93. https://doi.org/10.1109/ICCC55456.2022.9880789Guo T., Zhang T., Lim E., López-Benítez M., Ma F., Yu L. A Review of Wavelet Analysis and Its Applications: Challenges and Opportunities. IEEE Access . 2022;10:58869–58903. https://doi.org/10.1109/ACCESS.2022.3179517Guo T., Zhang T., Lim E., López-Benítez M., Ma F., Yu L. A Review of Wavelet Analysis and Its Applications: Challenges and Opportunities. IEEE Access . 2022;10:58869–58903. https://doi.org/10.1109/ACCESS.2022.3179517Akkaya S. Wavelet-Based Denoising Strategies for Non-Stationary Signals in Electrical Power Systems: An Optimization Perspective. Electronics . 2025;14(16):3190. https://doi.org/10.3390/electronics14163190Akkaya S. Wavelet-Based Denoising Strategies for Non-Stationary Signals in Electrical Power Systems: An Optimization Perspective. Electronics . 2025;14(16):3190. https://doi.org/10.3390/electronics14163190Facciolo G., Pierazzo N., Morel J.-M. Conservative Scale Recomposition for Multiscale Denoising. (The Devil is in the High Frequency Detail). SIAM J. Imaging Sci . 2017;10(3):1603–1626. https://doi.org/10.1137/17M1111826Facciolo G., Pierazzo N., Morel J.-M. Conservative Scale Recomposition for Multiscale Denoising. (The Devil is in the High Frequency Detail). SIAM J. Imaging Sci . 2017;10(3):1603–1626. https://doi.org/10.1137/17M1111826Wahab M.F., Gritti F., C. O’Haver T. Discrete Fourier transform techniques for noise reduction and digital enhancement of analytical signals. TrAC Trends in Analytical Chemistry. 2021;143(4):116354. https://doi.org/10.1016/j.trac.2021.116354Wahab M.F., Gritti F., C. O’Haver T. Discrete Fourier transform techniques for noise reduction and digital enhancement of analytical signals. TrAC Trends in Analytical Chemistry. 2021;143(4):116354. https://doi.org/10.1016/j.trac.2021.116354Zhao S., Ma L., Xu L., Liu M., Chen X. A Study of Fault Signal Noise Reduction Based on Improved CEEMDAN-SVD. Appl. Sci. 2023;13(19):10713. https://doi.org/10.3390/app131910713Zhao S., Ma L., Xu L., Liu M., Chen X. A Study of Fault Signal Noise Reduction Based on Improved CEEMDAN-SVD. Appl. Sci. 2023;13(19):10713. https://doi.org/10.3390/app131910713Wang H., Yao Y., Zhang G., Pan J., Gao L., Jin H., Wang C. Enhanced Noise Suppression in Partial Discharge Signals via SVD and VMD with Wavelet Thresholding. Modelling and Simulation in Engineering . 2024;2024:5676986. https://doi.org/10.1155/2024/5676986Wang H., Yao Y., Zhang G., Pan J., Gao L., Jin H., Wang C. Enhanced Noise Suppression in Partial Discharge Signals via SVD and VMD with Wavelet Thresholding. Modelling and Simulation in Engineering . 2024;2024:5676986. https://doi.org/10.1155/2024/5676986Almazrouei E., Gianini G., Almoosa N., Damiani E. A Deep Learning Approach to Radio Signal Denoising. In: 2019 IEEE Wireless Communications and Networking Conference Workshop ( WCNCW ). IEEE. 2019. https://doi.org/10.1109/WCNCW.2019.8902756Almazrouei E., Gianini G., Almoosa N., Damiani E. A Deep Learning Approach to Radio Signal Denoising. In: 2019 IEEE Wireless Communications and Networking Conference Workshop ( WCNCW ). IEEE. 2019. https://doi.org/10.1109/WCNCW.2019.8902756Duan R., Chen Z., Zhang H., Wang X., Meng W., Sun G. Dual Residual Denoising Autoencoder with Channel Attention Mechanism for Modulation of Signals. Sensors . 2023;23(2):1023. https://doi.org/10.3390/s23021023Duan R., Chen Z., Zhang H., Wang X., Meng W., Sun G. Dual Residual Denoising Autoencoder with Channel Attention Mechanism for Modulation of Signals. Sensors . 2023;23(2):1023. https://doi.org/10.3390/s23021023He S., Zhu L., Yao C., Wang L., Qin Z. A Novel Approach Based on Generative Adversarial Network for Signal Enhancement in Wireless Communications. Wireless Communications and Mobile Computing . 2022. https://doi.org/10.1155/2022/7050573He S., Zhu L., Yao C., Wang L., Qin Z. A Novel Approach Based on Generative Adversarial Network for Signal Enhancement in Wireless Communications. Wireless Communications and Mobile Computing . 2022. https://doi.org/10.1155/2022/7050573Peng L., Fang S., Fan Y., Wang M., Ma Z. A Method of Noise Reduction for Radio Communication Signal Based on RaGAN. Sensors . 2023;23(1):475. https://doi.org/10.3390/s23010475Peng L., Fang S., Fan Y., Wang M., Ma Z. A Method of Noise Reduction for Radio Communication Signal Based on RaGAN. Sensors . 2023;23(1):475. https://doi.org/10.3390/s23010475Yao H., Zhou Q., Chen Z., Huang L., Xu D., Xuan Q. Denoising of Radio Modulation Signal Based on Deep Learning. In: Xuan Q., Xiang Y., Xu D. (Eds.). Deep Learning Applications . 2023. Ch. 7. P. 125–143. https://doi.org/10.1142/9789811266911_0007Yao H., Zhou Q., Chen Z., Huang L., Xu D., Xuan Q. Denoising of Radio Modulation Signal Based on Deep Learning. In: Xuan Q., Xiang Y., Xu D. (Eds.). Deep Learning Applications . 2023. Ch. 7. P. 125–143. https://doi.org/10.1142/9789811266911_0007Wu T., Chen Z., He D., Qian L., Xu Y., Tao M. CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications. IEEE Trans. on Wireless Commun . 2024;23(9):11168–11183. https://doi.org/10.1109/TWC.2024.3379244Wu T., Chen Z., He D., Qian L., Xu Y., Tao M. CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications. IEEE Trans. on Wireless Commun . 2024;23(9):11168–11183. https://doi.org/10.1109/TWC.2024.3379244Letafati M., Ali S., Latva-Aho M. Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communications. IEEE Trans. on Machine Learning in Communications and Networking . 2025;3:133–146. https://doi.org/10.1109/TMLCN.2024.3522872Letafati M., Ali S., Latva-Aho M. Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communications. IEEE Trans. on Machine Learning in Communications and Networking . 2025;3:133–146. https://doi.org/10.1109/TMLCN.2024.3522872Ji Z., Wang S., Yang K., Zhang Q., Ye P. Transfer Learning Guided Noise Reduction for Automatic Modulation Classification. In: 2025 IEEE 102nd Vehicular Technology Conference ( VTC2025-Fall ). IEEE. 2025. https://doi.org/10.1109/VTC2025-Fall65116.2025.11310099Ji Z., Wang S., Yang K., Zhang Q., Ye P. Transfer Learning Guided Noise Reduction for Automatic Modulation Classification. In: 2025 IEEE 102nd Vehicular Technology Conference ( VTC2025-Fall ). IEEE. 2025. https://doi.org/10.1109/VTC2025-Fall65116.2025.11310099Chung J., Gulcehre C., Cho K.H., Bengio Y. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv preprint. arXiv:1412.3555. 2014. http://arxiv.org/abs/1412.3555Chung J., Gulcehre C., Cho K.H., Bengio Y. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv preprint. arXiv:1412.3555. 2014. http://arxiv.org/abs/1412.3555O’Shea T.J., Roy T., Clancy T.C. Over-the-Air Deep Learning Based Radio Signal Classification. IEEE J. Selected Topics in Signal Process . 2018;12(1):168–179. https://doi.org/10.1109/JSTSP.2018.2797022O’Shea T.J., Roy T., Clancy T.C. Over-the-Air Deep Learning Based Radio Signal Classification. IEEE J. Selected Topics in Signal Process . 2018;12(1):168–179. https://doi.org/10.1109/JSTSP.2018.2797022

The authors declare that there are no conflicts of interest present.