Lightweight signal recognition based on hybrid model in wireless networks

被引:0
作者
Tang, Mingjun [1 ,2 ]
Gao, Rui [2 ]
Guo, Lan [2 ]
机构
[1] Yangzhou Univ, Sch Informat Engn, Yangzhou 225000, Peoples R China
[2] Yangzhou Univ, Sch Informat Engn, Yangzhou 225000, Peoples R China
基金
中国国家自然科学基金;
关键词
Signal recognition; Wireless networks; Deep learning; Hybrid neural network; AUTOMATIC MODULATION CLASSIFICATION; DEEP LEARNING-MODEL; EFFICIENT; FEATURES;
D O I
10.1007/s11235-024-01204-8
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Signal recognition is a key technology in wireless networks, with broad applications in both military and civilian fields. Accurately recognizing the modulation scheme of an incoming unknown signal can significantly enhance the performance of communication systems. As global digitization and intelligence advance, the rapid development of wireless communication imposes higher standards for signal recognition: (1) Accurate and efficient recognition of various modulation modes, and (2) Lightweight recognition compatible with intelligent hardware. To meet these demands, we have designed a hybrid signal recognition model based on a convolutional neural network and a gated recurrent unit (CnGr). By integrating spatial and temporal modules, we enhance the multi-dimensional extraction of the original signal, significantly improving recognition accuracy. Additionally, we propose a lightweight signal recognition method that combines pruning and depthwise separable convolution. This approach effectively reduces the network size while maintaining recognition accuracy, facilitating deployment and implementation on edge devices. Extensive experiments demonstrate that our proposed method significantly improves recognition accuracy and reduces the model size without compromising performance.
引用
收藏
页码:707 / 721
页数:15
相关论文
共 34 条
[1]   Automatic Modulation Classification Using Moments and Likelihood Maximization [J].
Abu-Romoh, Mohannad ;
Aboutaleb, Ahmed ;
Rezki, Zouheir .
IEEE COMMUNICATIONS LETTERS, 2018, 22 (05) :938-941
[2]  
[Anonymous], 2017, IEEE INT S DYNAMIC S
[3]   A Hybrid ICA-SVM Approach to Continuous Phase Modulation Recognition [J].
Boutte, David ;
Santhanam, Balu .
IEEE SIGNAL PROCESSING LETTERS, 2009, 16 (05) :402-405
[4]   Spatial-Temporal Hybrid Feature Extraction Network for Few-Shot Automatic Modulation Classification [J].
Che, Jibin ;
Wang, Li ;
Bai, Xueru ;
Liu, Chunheng ;
Zhou, Feng .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (12) :13387-13392
[5]  
Cho K., 2014, P SSST 2014 8 WORKSH, DOI [10.3115/v1/w14-4012, DOI 10.3115/V1/W14-4012]
[6]  
Chollet Francois, 2017, PROC CVPR IEEE, P1251, DOI [DOI 10.1109/CVPR.2017.195, 10.1109/CVPR.2017.195]
[7]   Survey of automatic modulation classification techniques: classical approaches and new trends [J].
Dobre, O. A. ;
Abdi, A. ;
Bar-Ness, Y. ;
Su, W. .
IET COMMUNICATIONS, 2007, 1 (02) :137-156
[8]   Decentralized Automatic Modulation Classification Method Based on Lightweight Neural Network [J].
Dong, Biao ;
Xu, Guozhen ;
Fu, Xue ;
Dong, Heng ;
Gui, Guan ;
Gacanin, Haris ;
Adachi, Fumiyuki .
2022 IEEE 33RD ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS (IEEE PIMRC), 2022, :259-264
[9]   A Lightweight Decentralized-Learning-Based Automatic Modulation Classification Method for Resource-Constrained Edge Devices [J].
Dong, Biao ;
Liu, Yuchao ;
Gui, Guan ;
Fu, Xue ;
Dong, Heng ;
Adebisi, Bamidele ;
Gacanin, Haris ;
Sari, Hikmet .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (24) :24708-24720
[10]  
Gale T., 2019, COMPUT SCI