volume | PIER Journals

Abstract

A network optimization approach based on Neural Architecture Search (NAS) and network pruning is suggested to solve the issue of poor recognition performance of missile-borne radar active jamming under the condition of short sample sizes. The approach realized the ideal network design under severely constrained technical indications by combining the benefits of several methods, including NAS, convolutional light-weighting, and network pruning. The recognition network's convolution kernel size parameters were first optimized using NAS. The number of model parameters were then decreased via convolutional substitution. Finally, the structured pruning algorithm further screened the redundant network based on the technical indicators. The WideResNet28_2 wide residual network's recognition accuracy is only 84.38% when there are only 1000 training samples for each type of signal, according to the simulation results. After optimization, the number of new model parameters was increased 2.55M, 2.26M, and 1.78M, respectively, and their respective recognition accuracy was increased to 85.7%, 85.61%, and 85.37%. According to the simulation results, the technique offers a wide range of possible applications in the optimized design of radar active jamming identification networks for small sample sizes.

1. Li, N. J. and Y. T. Zhang, "A survey of radar ECM and ECCM," IEEE Transactions on Aerospace and Electronic Systems, Vol. 31, No. 3, 1110-1120, 1995.
doi:10.1109/7.395232 Google Scholar

2. Krizhevsky, A., I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in Neural Information Processing Systems, Vol. 25, 2012. Google Scholar

3. Sun, J., G. Xu, W. Ren, et al. "Radar emitter classification based on unidimensional convolutional neural network," Radar, Sonar & Navigation, Vol. 12, No. 8, 862-867, IET, 2018.
doi:10.1049/iet-rsn.2017.0547 Google Scholar

4. Liu, W., Z. Wang, X. Liu, et al. "A survey of deep neural network architectures and their applications," Neurocomputing, Vol. 234, 11-26, Apr. 19, 2017. Google Scholar

5. Yu, J., J. Li, B. Sun, et al. "Barrage jamming detection and classification based on convolutional neural network for synthetic aperture radar," IGARSS 2018 --- 2018 IEEE International Geoscience and Remote Sensing Symposium, 4583-4586, IEEE, 2018. Google Scholar

6. Liu, S. and C. Zhu, "Jamming recognition based on feature fusion and convolutional neural network," Journal of Beijing Institute of Technology, Vol. 31, No. 2, 9, 2022. Google Scholar

7. He, K., X. Zhang, S. Ren, et al. "Deep residual learning for image recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778, 2016. Google Scholar

8. Sun, C., A. Shrivastava, S. Singh, et al. "Revisiting unreasonable effectiveness of data in deep learning era," Proceedings of the IEEE International Conference on Computer Vision, 843-852, 2017. Google Scholar

9. Saptarshi, M. and J. Maiti, "Risk analysis using FMEA: Fuzzy similarity value and possibility theory based approach," Expert Systems with Applications, Vol. 41, No. 7, 3527-3537, 2014.
doi:10.1016/j.eswa.2013.10.058 Google Scholar

10. Versaci, M., G. Angiulli, P. Crucitti, et al. "A Fuzzy similarity-based approach to classify numerically simulated and experimentally detected carbon fiber-reinforced polymer plate defects," Sensors, Vol. 22, 4232, 2022.
doi:10.3390/s22114232 Google Scholar

11. Zadeh, L. A., "A note on similarity-based definitions of possibility and probability," Information Sciences, Vol. 267, 334-336, 2014.
doi:10.1016/j.ins.2014.01.046 Google Scholar

12. Termritthikun, C., Y. Jamtsho, J. Ieamsaard, et al. "EEEA-Net: An early exit evolutionary neural architecture search," Engineering Applications of Artificial Intelligence, Vol. 104, No. 2, 104397, 2021.
doi:10.1016/j.engappai.2021.104397 Google Scholar

13. Yao, X., Y. Shi, G. Huo, et al. "Lightweight model construction based on neural architecture search," Pattern Recognition and Artificial Intelligence, Vol. 34, No. 11, 1038-1048, 2021. Google Scholar

14. Liu, H., K. Simonyan, and Y. Yang, "DARTS: Differentiable architecture search,", arXiv preprint arXiv:1806.09055, 2018. Google Scholar

15. Reed, R. D., "Pruning algorithms --- A survey," IEEE Transactions on Neural Networks, 1993. Google Scholar

16. Li, H., A. Kadav, I. Durdanovic, et al. "Pruning filters for efficient convnets,", arXiv preprint arXiv:1608.08710, 2016. Google Scholar

17. He, Y., X. Zhang, and J. Sun, "Channel pruning for accelerating very deep neural networks," Proceedings of the IEEE International Conference on Computer Vision, 1389-1397, 2017. Google Scholar

18. He, Y., G. Kang, X. Dong, et al. "Soft filter pruning for accelerating deep convolutional neural networks,", arXiv preprint arXiv:1808.06866, 2018. Google Scholar

19. Ma, J., Y. Zhang, Z. Ma, et al. "Research progress of lightweight neural network convolution design," Journal of Frontiers of Computer Science and Technology, Vol. 16, No. 3, 17, 2022. Google Scholar

20. Dumoulin, V. and F. Visin, "A guide to convolution arithmetic for deep learning,", arXiv preprint arXiv:1603.07285, 2016. Google Scholar

21. Szegedy, C., V. Vanhoucke, S. Ioffe, et al. "Rethinking the inception architecture for computer vision," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818-2826, 2016. Google Scholar

22. Wang, X., J.-C. Liu, W. Zhang, et al. "The mathematical principle of intermittent sampling and forwarding interference," Science in China (Series E), Vol. 36, 891-901, 2006. Google Scholar

23. Suo, W., "Research on jamming against pseudo-random code pulse-doppler fuse,", Xidian University, Shaanxi, 2014. Google Scholar

24. Zhou, C., Q. Liu, and C. Hu, "Time-frequency analysis techniques for recognition and suppression of interrupted sampling repeater jamming," Journal of Radars, Vol. 8, 100-106, 2019. Google Scholar

25. Yu, H., X. Yan, R. Jia, et al. "Research on anti-jamming performance of M-sequence pseudo-random code phase modulation pulse doppler fuze," ACTA Armamentarii, Vol. 41, No. 03, 417-425, 2020. Google Scholar

26. Toole, J. M. O. and B. Boashash, "Fast and memory-efficient algorithms for computing quadratic time-frequency distributions," Applied & Computational Harmonic Analysis, Vol. 35, No. 2, 350-358, 2013.
doi:10.1016/j.acha.2013.01.003 Google Scholar

27. Gao, Z., F. Cao, C. He, et al. "MATLAB simulation of performance evaluation model of time-frequency analysis method based on SVM," 2022 8th International Symposium on Sensors, Mechatronics and Automation System, Suzhou, China, 2022. Google Scholar

28. Zhang, X., Modern Signal Processing (Third Edition), Tsinghua University Press, Beijing, 2015.

29. Recht, B., R. Roelofs, L. Schmidt, et al. "Do cifar-10 classifiers generalize to cifar-10?,", arXiv preprint arXiv:1806.00451, 2018. Google Scholar

30. Zagoruyko, S. and N. Komodakis, "Wide residual networks,", arXiv preprint arXiv:1605.07146, 2016. Google Scholar

31. Sohn, K., D. Berthelot, N. Carlini, et al. "Fixmatch: Simplifying semi-supervised learning with consistency and confidence," Advances in Neural Information Processing Systems, Vol. 33, 596-608, 2020. Google Scholar

Dr. Zejun Gao

Professor Fei Cao

Dr. Chuan He

Dr. Xiaowei Feng

Dr. Jianfeng Xu

Dr. Jianqiang Qin