[an error occurred while processing this directive]

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (2): 354-359.doi: 10.23919/JSEE.2022.000037

• • 上一篇    下一篇

  

  • 收稿日期:2020-12-22 出版日期:2022-05-06 发布日期:2022-05-06

A novel approach for unlabeled samples in radiation source identification

Haifen YANG*(), Hao ZHANG(), Houjun WANG(), Zhengyang GUO()   

  1. 1 School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
  • Received:2020-12-22 Online:2022-05-06 Published:2022-05-06
  • Contact: Haifen YANG E-mail:yanghf@uestc.edu.cn;zhanghao_sice@163.com;201922010217@std.uestc.edu.cn;1162101974@qq.com
  • About author:|YANG Haifen was born in 1977. She received her Ph.D. degree in 2008 from the Department of Communication and Information Engineering, University of Electronic and Science Technology of China (UESTC), Chengdu. She is now an associate professor in UESTC. Her research interests include signal processing in wireless communications. E-mail: yanghf@uestc.edu.cn||ZHANG Hao was born in 1993. He received his B.S. degree from the University of Electronic Science and Technology of China (UESTC), Chengdu, China, in 2017. He is now studying as a postgraduate at UESTC. His research interest is specific emitter identification. E-mail: zhanghao_sice@163.com||WANG Houjun was born in 1996. He received his B.S. degree from the University of Electronic Science and Technology of China (UESTC), Chengdu, China, in 2019. He is now studying as a postgraduate at UESTC. His research interest is specific emitter identification. E-mail: 201922010217@std.uestc.edu.cn||GUO Zhengyang was born in 1996. He received his B.S. degree from the Southwest University in Chongqing, China, in 2019. He is now studying as a postgraduate at the University of Electronic Science and Technology of China. His research interest is specific emitter identification. E-mail: 1162101974@qq.com
  • Supported by:
    This work was supported by the National Key R&D Program of China (2018YFB2101300).

Abstract:

Radiation source identification plays an important role in non-cooperative communication scene and numerous methods have been proposed in this field. Deep learning has gained popularity in a variety of computer vision tasks. Recently, it has also been successfully applied for radiation source identification. However, training deep neural networks for classification requires a large number of labeled samples, and in non-cooperative applications, it is unrealistic. This paper proposes a method for the unlabeled samples of unknown radiation source. It uses semi-supervised learning to detect unlabeled samples and label new samples automatically. It avoids retraining the neural network with parameter-transfer learning. The results show that compared with the traditional algorithms, the proposed algorithm can offer better accuracy.

Key words: radiation source identification, deep learning, semi-supervised learning