融合DAE-LSTM的认知物联网智能频谱感知算法

doi:10.3778/j.issn.1002-8331.2210-0295

摘要/Abstract

摘要： 第五代（fifth-generation，5G）移动通信技术的兴起，推动了物联网（Internet of things，IoT）的发展。然而，随着物联网数据传输量的爆发式增长，频谱资源短缺问题越来越严重。频谱感知技术极大的提高了物联网频谱利用率。但是，物联网移动通信环境的复杂性高以及信号易畸变的特性，对现有的频谱感知算法提出了重大挑战。因此，提出了一种融合去噪自编码器（denoising autoencoder，DAE）和改进长短时记忆（long short term memory，LSTM）神经网络的智能频谱感知算法。DAE通过编码和解码过程挖掘移动信号的底层结构特征，改进的LSTM频谱感知分类器模型结合过去时刻信息特征对时序信号序列进行分类。与支持向量机（support vector machine，SVM）、循环神经网络（recurrent neural network，RNN）、LeNet5、学习矢量量化（learning vector quantization，LVQ）和Elman算法相比，该算法的感知性能提高了45%。

关键词: 认知物联网, 智能频谱感知, 去噪自编码器, 长短时记忆网络

Abstract: The rise of the fifth-generation (5G) mobile communication, the development of Internet of things (IoT) is promoted. However, with the explosive growth of IoT data transmission volume, the shortage of spectrum resources is becoming more and more severe. Spectrum sensing technology greatly improves the spectrum utilization of the Internet of things. However, the IoT mobile communication environment has the characteristics of high complexity and easy signal distortion, which poses a major challenge to the existing spectrum sensing. Thus, this paper proposes an intelligent spectrum sensing algorithm that fused with denoising autoencoder (DAE) and improved long short term memory (LSTM) neural network. DAE excavates the internal structural features of mobile signals through encoding and decoding. The improved LSTM spectrum sensing classifier model is designed to classify time series signal sequences combined with past moment information features. Finally, the proposed algorithm achieves 45% higher sensing accuracy than support vector machine (SVM), Elman, LeNet5, learning vector quantization (LVQ) and recurrent neural network (RNN) algorithms.

Key words: cognitive Internet of things (IoT) networks, intelligent spectrum sensing, denoising autoencoder (DAE), long short term memory (LSTM)

段闫闫, 徐凌伟. 融合DAE-LSTM的认知物联网智能频谱感知算法[J]. 计算机工程与应用, 2024, 60(5): 299-306.

DUAN Yanyan, XU Lingwei. DAE-LSTM-Fused Intelligent Spectrum Sensing Algorithm for Cognitive Internet of Things[J]. Computer Engineering and Applications, 2024, 60(5): 299-306.

参考文献

[1] LI X W, LI J J, LIU Y W, et al. Residual Transceiver Hardware Impairments on Cooperative NOMA Networks[J]. IEEE Transactions on Wireless Communications, 2020, 19(1): 680-695.
[2] 尹钟舒, 洛向刚, 杨成, 等. 物联网 (IoT): 国内现状和国家标准综述[J]. 网络安全技术与应用, 2022(9): 108-111.
YI Z S, LUO X G, YANG C, et al. Internet of Things (IoT): summary of domestic status quo and national standards[J]. Network Security Technology & Application, 2022(9): 108-111.
[3] LI X W, ZHAO M L, ZENG M, et al. Hardware impaired ambient backscatter NOMA system: reliability and security[J]. IEEE Transactions on Communications, 2021, 69(4): 2723-2736.
[4] 徐凌伟, 林文. 移动多用户通信系统的中断概率性能研究[J]. 聊城大学学报(自然科学版). 2020, 33(2): 43-49.
XU L W, LIN W. Outage probability performance analysis of mobile multi-user communication system[J]. Journal of Liaocheng University (Natural Science), 2020, 33(2): 43-49.
[5] DEEMAH H T, WALAA H. An overview and future directions on physical-layer security for cognitive radio networks[J]. IEEE Network, 2021, 35(3): 205-211.
[6] CENGIS H, MAHESH K M. Communication-free inter-operator interference management in shared spectrum small cell networks[J]. IEEE Transactions on Cognitive Communications and Networking, 2019, 5(3): 661-677.
[7] LUO X S, ZHAO W J, LI H, et al. Fusion test statistics based mixture detector for spectrum sensing[J]. IEEE Transactions on Vehicular Technology, 2022, 71(3): 3315-3319.
[8] KONMAL J, ANAND J, SHANKAR P. Performance of underlay cooperative hybrid OMA/NOMA scheme with user selection[C]//2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, 2020: 1-6.
[9] ANAND J, KAMAL A, SHANKAR P. A Coordinated direct AF/DF relay-aided NOMA framework for low outage[J]. IEEE Transactions on Communications, 2022, 70(3): 1559-1579.
[10] ANAND J, KAMAL A, SHANKAR P. Performance of a new framework for coordinated direct AF relay-aided downlink NOMA[C]//2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), 2021: 477-482.
[11] TSANG-YI W, FENG-TSUN C, CHI-KAI H. Collaborative sampling and binary local output generation for distributed blind cooperative spectrum sensing[J]. IEEE Transactions on Communications, 2021, 69(8): 5471-5486.
[12] 马燕茹, 金明. 一种基于谱分量相关性的频谱感知方法及实验评估[J]. 无线通信技术, 2021, 30(4): 6-9.
MA Y R, JIN M. A spectral sensing method based on spectral component correlation and experimental evaluation[J]. Wireless Communication Technology, 2021, 30(4): 6-9.
[13] MAHDI N, HAMID B, NAZIH KHADDAJ M, et al. A wideband 5G cyclostationary spectrum sensing method by kernel least mean square algorithm for cognitive radio networks[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2021, 68(7): 2700-2704.
[14] HAYTHEM BANY S, MUATH BANI I, AHMAD AL A, et al. Energy-efficient cross-layer spectrum sharing in CR green IoT networks[J]. IEEE Transactions on Green Communications and Networking, 2021, 5(3): 1091-1100.
[15] AMIR M, MARYAM S, HALIM Y. Spectrum sensing for symmetric α-stable noise model with convolutional neural networks[J]. IEEE Transactions on Communications, 2021, 69(8): 5121-5135.
[16] ZHAO W J, ALI S S, JIN M L, et al. Extreme eigenvalues-based detectors for spectrum sensing in cognitive radio networks[J]. IEEE Transactions on Communications, 2022, 70(1): 538-551.
[17] MUARD A, SUNDOUS K. Performance of machine learning-based techniques for spectrum sensing in mobile cognitive radio networks[J]. IEEE Access, 2022, 10: 1410-1418.
[18] WALEED E, MOHAMED I. Multiband spectrum sensing and resource allocation for IoT in cognitive 5G networks[J]. IEEE Internet of Things Journal, 2018, 5(1): 150-163.
[19] MEI R R, WANG Z G. Deep learning-based wideband spectrum sensing: a low computational complexity approach[J]. IEEE Communications Letters, 2023, 27(10): 2633-2637.
[20] DHAVAL K P, SAGAR K, ZHIGUO D, et al. Impact of primary user activity statistics in cognitive vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2022, 71(3): 2859-2873.
[21] KAWTAR Z, EL MEHDI A, MARWA C. Filtered multicarrier waveforms classification: a deep learning-based approach[J]. IEEE Access, 2021, 9: 69426-69438.
[22] 盖建新, 薛宪峰, 南瑞祥, 等. 基于残差密集网络的频谱感知方法[J]. 通信学报, 2021, 42(12): 182-191.
GAI J X, XUE X F, NAN R X, et al. Spectrum sensing method based on residual dense network[J]. Journal on Communications, 2021, 42(12): 182-191.
[23] XU L W, XIN P Z, XING W L, et al. Mobile collaborative secrecy performance prediction for artificial IoT networks[J]. IEEE Transactions on Industrial Informatics, 2022, 18(8): 5403-5411.
[24] 徐凌伟, 权天祺. 基于BP神经网络的移动安全性能预测[J]. 聊城大学学报 (自然科学版), 2020, 33(3): 34-40.
XU L W, QUAN T Q. Mobile secrecy performance prediction based on BP neural network[J]. Journal of Liaocheng University (Natural Science), 2020, 33(3): 34-40.
[25] RAMI A H, WITOLD P, ABDULLAH B. Logic-oriented autoencoders and granular logic autoencoders: developing interpretable data representation[J]. IEEE Transactions on Fuzzy Systems, 2022, 30(3): 869-877.