ZTE Communications ›› 2022, Vol. 20 ›› Issue (S1): 44-56.DOI: 10.12142/ZTECOM.2022S1007

• Research Paper • Previous Articles     Next Articles

Multi-Task Learning with Dynamic Splitting for Open-Set Wireless Signal Recognition

XU Yujie1, ZHAO Qingchen1, XU Xiaodong1(), QIN Xiaowei1, CHEN Jianqiang2   

  1. 1.University of Science and Technology of China, Hefei 230026, China
    2.ZTE Corporation, Shenzhen 518057, China
  • Received:2021-07-05 Online:2022-01-25 Published:2022-03-01
  • About author:XU Yujie received the B. Eng. and M. Eng. degree in electronic and information engineering from University of Science and Technology of China (USTC), China in 2017 and 2021. His research interest is deep learning for wireless signal identification.|ZHAO Qingchen received the B.Eng. degree in electronic information engineering from Anhui University of Finance and Economics, China in 2018. He is currently pursuing his M. Eng. degree in Department of Electronic Engineering and Information Science, University of Science and Technology of China (USTC), China. His research interest is smart transmission.|XU Xiaodong (xdxu@ustc.edu.cn) received the B.Eng. and Ph.D. degrees in electronic and information engineering from University of Science and Technology of China (USTC) in 2000 and 2007, respectively. From 2000 to 2001, he served as a research assistant at the R&D center, Konka Telecommunications Technology. Since 2007, he has been a faculty member with the Department of Electronic Engineering and Information Science, USTC. He is currently working with the CAS Key Laboratory of Wireless-Optical Communications, USTC. His research interests include the areas of wireless communications, signal processing, wireless artificial intelligence and information-theoretic security.|QIN Xiaowei received the B.S. and Ph.D. degrees from the Department of Electrical Engineering and Information Science, University of Science and Technology of China (USTC), China in 2000 and 2008, respectively. Since 2014, he has been a member of staff in Key Laboratory of Wireless-Optical Communications of Chinese Academy of Sciences at USTC. His research interests include optimization theory, service modeling in future heterogeneous networks, and wireless artificial intelligence in mobile communication networks.|CHEN Jianqiang received the M. Eng. degree from Nanjing University of Technology, China in electromagnetic field and microwave technology. At present, he works at the intelligent home terminal product line of ZTE Corporation and has many years of experience in the communication industry. His research direction is Wi-Fi key technologies and their applications, in which he has more than 10 patents.
  • Supported by:
    the Natural Science Foundation of Anhui Province(2008085MF213);ZTE Industry-University-Institute Cooperation Funds(20190822003)


Open-set recognition (OSR) is a realistic problem in wireless signal recognition, which means that during the inference phase there may appear unknown classes not seen in the training phase. The method of intra-class splitting (ICS) that splits samples of known classes to imitate unknown classes has achieved great performance. However, this approach relies too much on the predefined splitting ratio and may face huge performance degradation in new environment. In this paper, we train a multi-task learning (MTL) network based on the characteristics of wireless signals to improve the performance in new scenes. Besides, we provide a dynamic method to decide the splitting ratio per class to get more precise outer samples. To be specific, we make perturbations to the sample from the center of one class toward its adversarial direction and the change point of confidence scores during this process is used as the splitting threshold. We conduct several experiments on one wireless signal dataset collected at 2.4 GHz ISM band by LimeSDR and one open modulation recognition dataset, and the analytical results demonstrate the effectiveness of the proposed method.

Key words: open-set recognition, dynamic method, adversarial direction, multi-task learning, wireless signal