Research on Signal Modulation Classification under Low SNR Based on ResNext Network

Binghang Zou; Hanzhi Yan; Faquan Wang; Yucheng Zhou; Xiaodong Zeng

doi:10.3390/electronics11172662

journal article Open Access Aug 25, 2022

Research on Signal Modulation Classification under Low SNR Based on ResNext Network

Binghang Zou

Hanzhi Yan Faquan Wang Yucheng Zhou

Xiaodong Zeng

Electronics Vol. 11 No. 17 pp. 2662 · MDPI AG

View at Publisher Save 10.3390/electronics11172662

Abstract

To address the shortcomings of existing methods such as low recognition accuracy and poor anti-interference performance under low signal-to-noise ratios, this paper proposes the RFSE-ResNeXt (Residual-fusion squeeze–excitation aggregated residual for networks, RFSE-ResNeXt) network. In this paper, we improve the residual structure of the network based on the ResNeXt network and then introduce the compressed excitation structure to improve the generalization ability of the network. The improvement of the residual structure of the network leads to a good improvement in the overall recognition accuracy of the network; meanwhile, the compressed excitation structure improves the confusion phenomenon when the network faces complex signals with low signal-to-noise ratios. The experimental results show that the proposed network improves the recognition accuracy by 4% on average at a very low SNR of -10dB and reduces the misclassification of AM-DSB into CPFSK by about 27%.

Topics

No keywords indexed for this article. Browse by subject →

References

23

[1]

Wang "Analysis of radar emitter signal sorting and recognition Model structure" Pro-Cedia Comput. Sci. (2019) 10.1016/j.procs.2019.06.076

[2]

Wang, C., Wang, J., and Zhang, X.D. (2017, January 5–9). Automatic radar waveform recognition based on time-frequency analysis and convolutional neural network. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, LA, USA. 10.1109/icassp.2017.7952594

[3]

Wang, Y., Zhang, S., Zhang, Y., Wan, P., Li, J., and Li, N. (2019). Acooperative spectrum sensing method based on Empirical modede composition and information geometry in complex electrom agnetic environment. Comolexity, 2019. 10.1155/2019/5470974

[4]

Zhang, M., Diao, M., Gao, L., and Liu, L. (2017). Neural networks for radar waveform recognition. Symmetry, 9. 10.3390/sym9050075

[5]

Chen "LPI radar waveform recognition based on multi-branch MWC compressed sampling receiver" IEEE Access (2018) 10.1109/access.2018.2845102

[6]

Zhou "Automatic radar waveform recognition based on deep convolutional denoising autoencoders" Circuits Syst. Signal Process. (2018) 10.1007/s00034-018-0757-0

[7]

Zou, B., Zeng, X., and Wang, F. (2022). Research on Modulation Signal Recognition Based on CLDNN Network. Electronics, 11. 10.3390/electronics11091379

[8]

O’Shea, T.J., Corgan, J., and Clancy, T.C. (2016, January 2–5). Convolutional radio mod-ulation recognition networks. Proceedings of the International Conference on Engineering Applications of Neural Networks, Aberdeen, UK. 10.1007/978-3-319-44188-7_16

[9]

West, N.E., and O’Shea, T.J. (2017). Deep architectures for modulation recognition. arXiv. 10.1109/dyspan.2017.7920754

[10]

O’Shea, T., and West, N. (2016, January 12–16). Radio machine learning dataset generation with gnu radio. Proceedings of the GNU Radio Conference, Boulder, CO, USA.

[11]

Szegedy "Inception-v4, inception-resnet and the impact of residual connections on learning" AAAI (2017)

[12]

Over-the-Air Deep Learning Based Radio Signal Classification

Timothy James O'Shea, Tamoghna Roy, T. Charles Clancy

IEEE Journal of Selected Topics in Signal Processi... 2018 10.1109/jstsp.2018.2797022

[13]

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.90

[14]

Aggregated Residual Transformations for Deep Neural Networks

Saining Xie, Ross Girshick, Piotr Dollar et al.

2017 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2017.634

[15]

Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., and Wey, T. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.

[16]

Squeeze-and-Excitation Networks

Jie Hu, Li Shen, Gang Sun

2018 IEEE/CVF Conference on Computer Vision and Pa... 10.1109/cvpr.2018.00745

[17]

Nair, V., and Hinton, G.E. (2010). Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair. International Conference on International Conference on Machine Learning, Omnipress.

[18]

Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA. JMLR Workshop and Conference Proceedings.

[19]

Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). Exploring the Limits of Weakly Supervised Pretraining. Computer Vision-ECCV, Springer. Lecture Notes in Computer Science. 10.1007/978-3-030-01228-1

[20]

Lee, J., Kim, D., and Ham, B. (2021). Network Quantization with Element-wise Gradient Scaling. arXiv. 10.1109/cvpr46437.2021.00638

[21]

Loffe, S., and Szegedy, C. (2015, January 6–11). Batch normalization: Accelerating deep network trainingby reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France.

[22]

O’Shea, T.J. (2022, January 08). Available online: https://www.Deepsig.io/datasets.

[23]

Qin "Radar emitter signal recognition based on dilated residual network" Actaelectonica Sin. (2020)

Metrics

11

Citations

23

References

Details

Published: Aug 25, 2022
Vol/Issue: 11(17)
Pages: 2662
License: View

Authors

B

Binghang Zou

School of Electrical Engineering, Sichuan University, Chengdu 610065, China

H

Hanzhi Yan

College of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710600, China

F

Faquan Wang

School of Electrical Engineering, Sichuan University, Chengdu 610065, China

Y

Yucheng Zhou

Glasgow College, University of Electronic Science and Technology of China, Chengdu 610056, China

X

Xiaodong Zeng

School of Electrical Engineering, Sichuan University, Chengdu 610065, China

Cite This Article

Binghang Zou, Hanzhi Yan, Faquan Wang, et al. (2022). Research on Signal Modulation Classification under Low SNR Based on ResNext Network. Electronics, 11(17), 2662. https://doi.org/10.3390/electronics11172662

Research on Signal Modulation Classification under Low SNR Based on ResNext Network

You May Also Like