Study of Radar Target Range Profile Recognition Algorithm Based on Optimized Neural Network

  • Xiaokang Guo
  • Tao Jian
  • Yunlong Dong
  • Xiaolong ChenEmail author
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 251)


Neural network as an important aspect of artificial intelligence has received extensive research and long-term development. Radar target range profile recognition is a commonly used method in radar target recognition, in this paper, it is combined with neural network. The LVQ (Learning Vector Quantization) neural network has excellent classification and identification capabilities. This paper applies it to radar target one-dimensional range image recognition and achieves good results. This paper studies the problem of LVQ neural network sensitive to initial connection weights, and uses PSO (Particle Swarm Optimization) algorithm to optimize it of recognition classification. The experimental results show that the study of radar target range profile recognition algorithm based on optimized neural network can overcome the sensitivity of the LVQ neural network to the initial weight and improve its recognition ability.


1-D range profile recognition LVQ (Learning Vector Quantization) PSO (Particle Swarm Optimization) 


  1. 1.
    Liu, H., Du, L., Yuan, L., Bao, Z.: Research progress in radar high resolution range image target recognition. J. Electron. Inf. Technol. 27(8), 1328–1334 (2005)Google Scholar
  2. 2.
    Xu, B., Chen, W., Liu, H., et al.: High-resolution radar range image target recognition based on attentional circulate neural network model. J. Electron. Inf. Technol. 38(12), 2988–2995 (2016)Google Scholar
  3. 3.
    Zhou, Y.: Research on radar target recognition based on high resolution range profile. University of Electronic Science and Technology (2016)Google Scholar
  4. 4.
    Zhao, F., Zhang, J., Liu, J.: Radar target recognition based on kernel optimal transformation and clustering center. Control Decis. 23(7), 735–740 (2008)Google Scholar
  5. 5.
    Chen, W., Yang, P., Liu, C., et al.: Application of BP neural network in radar target recognition. Electron. Sci. Technol. 23(12), 18–19 (2010)Google Scholar
  6. 6.
    Song, J., Zou, X., Yin, Y., et al.: Research on face orientation recognition based on neural network. Ind. Control Comput. 30(4), 111–112 (2017)Google Scholar
  7. 7.
    Chen, Z., Feng, T.J., Houkes, Z.: Texture segmentation based on wavelet and Kohonen network for remotely sensed images. In: IEEE SMC 1999 Conference Proceedings IEEE International Conference on Systems, Man, and Cybernetics, vol. 6, pp. 816–821. IEEE (1999)Google Scholar
  8. 8.
    Xia, F., Luo, Z., Zhang, H., et al.: Application of hybrid neural network in transformer fault diagnosis. J. Electron. Meas. Instrum. 31(1), 118–124 (2017)Google Scholar
  9. 9.
    Munlin, M., Anantathanavit, M.: Hybrid radius particle swarm optimization. In: Region 10 Conference, pp. 1–5. IEEE (2017)Google Scholar
  10. 10.
    Yuan, L., Liu, H., Bao, Z.: Radar HRRP automatic target recognition based on central moment feature. Chin. J. Electron. 32(12), 2078–2081 (2004)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  • Xiaokang Guo
    • 1
  • Tao Jian
    • 1
  • Yunlong Dong
    • 1
  • Xiaolong Chen
    • 1
    Email author
  1. 1.Research Institute of Information FusionNaval Aviation UniversityYantaiChina

Personalised recommendations