A novel radar signal recognition method based on a deep restricted Boltzmann machine

Authors

  • Dongqing Zhou Air Force Engineering University
  • Xing Wang Air Force Engineering University
  • Yuanrong Tian Air Force Engineering University
  • Ruijia Wang Air Force Engineering University

Keywords:

radar signal recognition, deep learning, restricted Boltzman machine, RSRDRBM

Abstract

Radar signal recognition is of great importance in the field of electronic intelligence reconnaissance. To deal with the problem of parameter complexity and agility of multi-function radars in radar signal recognition, a new model called radar signal recognition based on the deep restricted Boltzmann machine (RSRDRBM) is proposed to extract the feature parameters and recognize the radar emitter. This model is composed of multiple restricted Boltzmann machines. A bottom-up hierarchical unsupervised learning is used to obtain the initial parameters, and then the traditional back propagation (BP) algorithm is conducted to fine-tune the network parameters. Softmax algorithm is used to classify the results at last. Simulation and comparison experiments show that the proposed method has the ability of extracting the parameter features and recognizing the radar emitters, and it is characterized with strong robustness as well as highly correct recognition rate.

Downloads

Published

2017-05-22