CGDNet: Efficient hybrid deep learning model for robust automatic modulation recognition

被引：66

作者：

Njoku, Judith Nkechinyere ^{[1
]}

Morocho-Cayamcela, Manuel Eugenio ^{[2
]}

Lim, Wansu ^{[1
]}

机构：

[1] Department of Aeronautics, Mechanical and Electronic Convergence Engineering, Kumoh National Institute of Technology, Gumi

[2] School of Mathematical and Computational Sciences, Yachay Tech University, San Miguel de Urcuquí Canton

来源：

IEEE Networking Letters | 2021年 / 3卷 / 02期

关键词：

Automatic modulation recognition; convolutional neural networks; deep learning; gated recurrent unit;

D O I：

10.1109/LNET.2021.3057637

中图分类号：

学科分类号：

摘要：

In this letter, we introduce CGDNet, a cost-efficient hybrid neural network composed of a shallow convolutional network, a gated recurrent unit, and a deep neural network, for robust automatic modulation recognition for cognitive radio services of modern communication systems. Our model employs pooling layers, small filter sizes, Gaussian dropout layers, and skip connections which leads to an increase in network capacity, a reinforced process of feature extraction, and prevents the vanishing gradient problem. From our experiments, CGDNet incurs a low computational complexity and reaches the overall n-modulation recognition accuracy of 93.5% and 90.38% on two widely used Deep-Sig datasets. © 2019 IEEE.

引用

页码：47 / 51

页数：4

共 18 条

[1]

Huynh-The T., Hua C., Pham Q., Kim D., MCNet: An efficient CNN architecture for robust automatic modulation classification, IEEE Commun. Lett., 24, 4, pp. 811-815, (2020)

[2]

Hermawan A.P., Ginanjar R.R., Kim D.-S., Lee J.-M., CNNbased automatic modulation classification for beyond 5G communications, IEEE Commun. Lett., 24, 5, pp. 1038-1041, (2020)

[3]

Morocho-Cayamcela M.E., Lee H., Lim W., Machine learning for 5G/B5G mobile and wireless communications: Potential, limitations, and future directions, IEEE Access, 7, pp. 137184-137206, (2019)

[4]

Zheng J., Lv Y., Likelihood-based automatic modulation classification in OFDM with index modulation, IEEE Trans. Veh. Technol., 67, 9, pp. 8192-8204, (2018)

[5]

Huang S., Yao Y., Wei Z., Feng Z., Zhang P., Automatic modulation classification of overlapped sources using multiple cumulants, IEEE Trans. Veh. Technol., 66, 7, pp. 6089-6101, (2017)

[6]

O'Shea T.J., Corgan J., Clancy T.C., Convolutional Radio Modulation Recognition Networks (Communications in Computer and Information Science), 629, pp. 213-226, (2016)

[7]

Nkechinyere N.J., Morocho-Cayamcela M.E., Lim W., Automatic radar waveform recognition using the Wigner-Ville distribution and AlexNet-SVM, Proc. KICS Summer Conf., Pyeongchang, South Korea, pp. 467-470, (2020)

[8]

Popovski P., Et al., Wireless access in ultra-reliable low-latency communication (URLLC), IEEE Trans. Commun., 67, 8, pp. 5783-5801, (2019)

[9]

Daldal N., Yldrm O., Polat K., Deep long short-term memory networks-based automatic recognition of six different digital modulation types under varying noise conditions, Neural Comput. Appl., 2, pp. 1967-1981, (2019)

[10]

Wei S., Qu Q., Su H., Wang M., Shi J., Hao X., Intra-pulse modulation radar signal recognition based on CLDN network, IET Radar Sonar Navig., 14, 6, pp. 803-810, (2020)

← 1 2 →