Advanced Search
Turn off MathJax
Article Contents
LIN Peiqi, YOU Yuxin, LI Jinqiu, YAN Mubiao, JIANG Xinglong, LI Shuxun, LIU Huijie. Adaptive Neural Network-Based PAC Code Decoding Method for LEO Satellite Communication[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260346
Citation: LIN Peiqi, YOU Yuxin, LI Jinqiu, YAN Mubiao, JIANG Xinglong, LI Shuxun, LIU Huijie. Adaptive Neural Network-Based PAC Code Decoding Method for LEO Satellite Communication[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260346

Adaptive Neural Network-Based PAC Code Decoding Method for LEO Satellite Communication

doi: 10.11999/JEIT260346 cstr: 32379.14.JEIT260346
Funds:  The National Key Research and Development Plan (2021ZD0300100), Shanghai Primary Research and Development Plan (2019sHZDZX01)
  • Received Date: 2026-03-25
  • Accepted Date: 2026-09-15
  • Rev Recd Date: 2026-08-31
  • Available Online: 2026-09-23
  • Polarization-Adjusted Convolutional (PAC) codes combine convolutional precoding with polar coding and improve error-correction performance over polar codes, particularly at short to moderate block lengths. However, conventional neural network-based decoders often struggle to adapt to the complex, time-varying channels encountered in Low Earth Orbit (LEO) satellite communications, which exhibit rapid channel variations and strong attenuation. This study proposes a HyperNetwork-based Adaptive Multi-Layer Perceptron (HNA-MLP) decoding framework for PAC codes. A hypernetwork branch conditioned on Channel State Information (CSI) generates adaptive weights for the main network, which extracts features from the received signal and performs decoding. This design enables the decoder to adjust its parameters to changing channel conditions. The framework is evaluated under different fading conditions, Doppler shift offsets, and levels of rain attenuation. A weighted binary cross-entropy loss is used to optimize the network parameters through backpropagation, with the aim of reducing the Bit Error Rate (BER). Simulation results show that the proposed decoder outperforms other neural network-based decoders and achieves BER performance comparable to or better than Successive Cancellation List (SCL) decoding and Two-Stage Adaptive Cyclic Redundancy Check (CRC)-aided SCL (TA-SCL) decoding across the tested channel conditions, with the clearest gains under high rain attenuation, low Signal-to-Noise Ratio (SNR), and large Doppler shift offsets.  Objective  This study addresses the limited adaptability of conventional fixed-structure neural network decoders in LEO satellite communication channels characterized by rapid variations and strong attenuation. Such decoders struggle to adapt to changing channel conditions in real time, which limits their decoding performance. The objective is to develop a PAC code decoding scheme that combines high adaptability with low decoding latency.  Methods  The proposed HNA-MLP framework employs a CSI-driven weight-generation mechanism and a dual-branch architecture. The main network extracts features for decoding, whereas the hypernetwork branch processes the CSI and dynamically generates adaptive weight matrices for the main network. By providing real-time CSI to the hypernetwork, the decoder adjusts its parameters to accommodate different fading conditions, Doppler shift offsets, and levels of rain attenuation. During training, a weighted binary cross-entropy loss guides backpropagation to optimize the network parameters and improve bit-level decoding accuracy, thereby reducing BER.  Results and Discussions  Simulation results show that, within the tested SNR and Doppler shift offset ranges, the proposed scheme achieves lower BER than other non-adaptive neural network-based decoders and can outperform conventional SCL decoding. The gains over SCL and TA-SCL are most pronounced under medium-to-high rain attenuation, low SNR, and large Doppler shift offsets. Under other tested carrier frequencies, symbol rates, and fading conditions, its BER remains comparable to that of these conventional schemes. These findings indicate that CSI-driven dynamic weight generation enables the decoder to respond to changing channel characteristics and maintain stable performance in highly dynamic environments. The method also avoids complex manual feature recomputation and achieves shorter decoding times than SCL and TA-SCL decoding, supporting its potential for practical engineering applications.  Conclusions  This study proposes an HNA-MLP decoding framework for PAC codes to address the challenges posed by highly dynamic and strongly attenuating LEO satellite communication channels. The framework dynamically adjusts decoder parameters through CSI-driven weight generation. Multi-scenario simulations yield three main findings. (1) Under medium-to-high rain attenuation, low SNR, and large Doppler shift offsets, the proposed decoder achieves significantly lower BER than conventional SCL and TA-SCL decoders. (2) The CSI-driven weight-generation mechanism enables the decoder to adapt to variations in fading conditions, Doppler shift offsets, carrier frequencies, symbol rates, SNRs, and rain attenuation, maintaining stable performance across diverse channel environments. (3) Although the proposed decoder does not outperform some neural network-based decoders in parameter count or inference speed, it exhibits lower overall computational complexity and achieves decoding speedups of approximately 5.37-fold and 2.08-fold over the SCL and TA-SCL schemes, respectively. This study assumes ideal CSI. Future work will account for CSI estimation errors, sensor noise, and hybrid fading in real flight environments. The feasibility of deployment on a Graphics Processing Unit (GPU) platform will also be evaluated to improve the practicality and robustness of the algorithm.
  • loading
  • [1]
    ALVES H, MAHMOOD N H, LÓPEZ O L A, et al. 6G resilience-white paper[R]. 6G Research Visions, No. 15, 2025.
    [2]
    游雨欣, 姜兴龙, 刘会杰, 等. TDD OTFS低轨卫星通信系统的LLM信道预测方法[J]. 电子与信息学报, 2025, 47(8): 2535–2548. doi: 10.11999/JEIT250105.

    YOU Yuxin, JIANG Xinglong, LIU Huijie, et al. LLM channel prediction method for TDD OTFS low-earth-orbit satellite communication systems[J]. Journal of Electronics & Information Technology, 2025, 47(8): 2535–2548. doi: 10.11999/JEIT250105.
    [3]
    ARIKAN E. Channel polarization: A method for constructing capacity-achieving codes for symmetric binary-input memoryless channels[J]. IEEE Transactions on Information Theory, 2009, 55(7): 3051–3073. doi: 10.1109/TIT.2009.2021379.
    [4]
    ROWSHAN M, BURG A, and VITERBO E. Polarization-adjusted convolutional (PAC) codes: Sequential decoding vs list decoding[J]. IEEE Transactions on Vehicular Technology, 2021, 70(2): 1434–1447. doi: 10.1109/TVT.2021.3052550.
    [5]
    ZHANG Shunwai and LIU Hong. RIS-assisted DF relay system based on PAC codes for short packet communication[J]. IEEE Communications Letters, 2026, 30: 263–267. doi: 10.1109/LCOMM.2025.3636940.
    [6]
    FANO R. A heuristic discussion of probabilistic decoding[J]. IEEE Transactions on Information Theory, 1963, 9(2): 64–74. doi: 10.1109/TIT.1963.1057827.
    [7]
    LEROUX C, RAYMOND A J, SARKIS G, et al. A semi-parallel successive-cancellation decoder for polar codes[J]. IEEE Transactions on Signal Processing, 2013, 61(2): 289–299. doi: 10.1109/TSP.2012.2223693.
    [8]
    TAL I and VARDY A. List decoding of polar codes[C]. 2011 IEEE International Symposium on Information Theory Proceedings, St. Petersburg, Russia, 2011: 1–5. doi: 10.1109/ISIT.2011.6033904.
    [9]
    BENGIO Y. Learning deep architectures for AI[J]. Foundations and Trends® in Machine Learning, 2009, 2(1): 1–127. doi: 10.1561/2200000006.
    [10]
    DAI Jingxin, YIN Hang, LV Yansong, et al. Performance evaluation of PAC decoding with deep neural networks[C]. 2025 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), Dublin, Ireland, 2025: 1–6. doi: 10.1109/BMSB65076.2025.11165584.
    [11]
    HA D, DAI A M, and LE Q V. HyperNetworks[C]. International Conference on Learning Representations (ICLR), Toulon, France, 2017.
    [12]
    ROYCHOWDHURY P, SINGH Y P, and CHANSARKAR R A. Dynamic tunneling technique for efficient training of multilayer perceptrons[J]. IEEE Transactions on Neural Networks, 1999, 10(1): 48–55. doi: 10.1109/72.737492.
    [13]
    PUSHPARAJESH V, SINGH S, and GUPTA R. Satellite communications performance analysis in the presence of atmospheric attenuation and rain fading[C]. 2024 3rd International Conference for Advancement in Technology (ICONAT), GOA, India, 2024: 1–6. doi: 10.1109/ICONAT61936.2024.10774711.
    [14]
    ITU-R. Recommendation ITU-R P. 838–2 Specific attenuation model for rain for use in prediction methods[S]. Geneva: ITU, 1992.
    [15]
    GUPTA H, SRIVASTAVA N, and BORMAN L. Stochastic channel modeling for flat fading in non-terrestrial narrowband systems[C]. 2025 3rd International Conference on Communication, Security, and Artificial Intelligence (ICCSAI), Greater Noida, India, 2025: 1042–1048. doi: 10.1109/ICCSAI64074.2025.11064139.
    [16]
    XU Rongchi, CHEN Hao, LIU Ling, et al. Path metric range and LLR-based design of polar codes and PAC codes for SCL decoding[J]. IEEE Communications Letters, 2025, 29(2): 338–342. doi: 10.1109/LCOMM.2024.3516939.
    [17]
    CHIU M C and SU Yisheng. Design of polar codes and PAC codes for SCL decoding[J]. IEEE Transactions on Communications, 2023, 71(5): 2587–2601. doi: 10.1109/TCOMM.2023.3263225.
    [18]
    SABER H, GE Yiqun, ZHANG Ran, et al. Convolutional polar codes: LLR-based successive cancellation decoder and list decoding performance[C]. 2018 IEEE International Symposium on Information Theory (ISIT), Vail, USA, 2018: 1480–1484. doi: 10.1109/ISIT.2018.8437733.
    [19]
    TRIFONOV P and MILOSLAVSKAYA V. Polar codes with dynamic frozen symbols and their decoding by directed search[C]. 2013 IEEE Information Theory Workshop (ITW), Seville, Spain, 2013: 1–5. doi: 10.1109/ITW.2013.6691213.
    [20]
    ZHU Hongfei, CAO Zhiwei, ZHAO Yuping, et al. Learning to denoise and decode: A novel residual neural network decoder for polar codes[J]. IEEE Transactions on Vehicular Technology, 2020, 69(8): 8725–8738. doi: 10.1109/TVT.2020.3000345.
    [21]
    LIU Yusha and SIMEONE O. HyperRNN: Deep learning-aided downlink CSI acquisition via partial channel reciprocity for FDD massive MIMO[C]. 2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Lucca, Italy, 2021: 31–35. doi: 10.1109/SPAWC51858.2021.9593238.
    [22]
    刘晓敏, 余梦君, 乔振壮, 等. 面向多源遥感数据分类的尺度自适应融合网络[J]. 电子与信息学报, 2024, 46(9): 3693–3702. doi: 10.11999/JEIT240178.

    LIU Xiaomin, YU Mengjun, QIAO Zhenzhuang, et al. Scale adaptive fusion network for multimodal remote sensing data classification[J]. Journal of Electronics & Information Technology, 2024, 46(9): 3693–3702. doi: 10.11999/JEIT240178.
    [23]
    职为梅, 常智, 卢俊华, 等. 面向不平衡图像数据的对抗自编码器过采样算法[J]. 电子与信息学报, 2024, 46(11): 4208–4218. doi: 10.11999/JEIT240330.

    ZHI Weimei, CHANG Zhi, LU Junhua, et al. Adversarial Autoencoders oversampling algorithm for imbalanced image data[J]. Journal of Electronics & Information Technology, 2024, 46(11): 4208–4218. doi: 10.11999/JEIT240330.
    [24]
    XIA Chenyang, FAN Youzhe, and TSUI C Y. A two-staged adaptive successive cancellation list decoding for polar codes[C]. IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, Japan, 2019: 1–5. doi: 10.1109/ISCAS.2019.8702103.
    [25]
    HOCHREITER S and SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735–1780. doi: 10.1162/neco.1997.9.8.1735.
    [26]
    HOANG N D. Automatic impervious surface area detection using image texture analysis and neural computing models with advanced optimizers[J]. Computational Intelligence and Neuroscience, 2021, 2021(1): 8820116. doi: 10.1155/2021/8820116.
    [27]
    SUBRAMANIAN S and GANAPATHIRAMAN V. Zeroth Order GreedyLR: An adaptive learning rate scheduler for deep neural network training[C]. 2023 IEEE 4th International Conference on Pattern Recognition and Machine Learning (PRML), Urumqi, China, 2023: 593–601. doi: 10.1109/PRML59573.2023.10348370.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(9)  / Tables(1)

    Article Metrics

    Article views (345) PDF downloads(21) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return