论文:2020,Vol:38,Issue(5):1074-1083
引用本文:
史蕴豪, 许华, 刘英辉. 一种基于伪标签半监督学习的小样本调制识别算法[J]. 西北工业大学学报
SHI Yunhao, XU Hua, LIU Yinghui. A Few-Shot Modulation Recognition Method Based on Pseudo-Label Semi-Supervised Learning[J]. Northwestern polytechnical university

一种基于伪标签半监督学习的小样本调制识别算法
史蕴豪, 许华, 刘英辉
空军工程大学 信息与导航学院, 陕西 西安 710077
摘要:
针对有标签样本较少条件下的通信信号调制识别问题,提出了一种基于伪标签半监督学习技术的小样本调制方式分类算法,通过优选人工特征集、设计高性能分类器以及基于输出概率的伪标签数据选择方法,构建高效的伪标签标注系统,然后通过该伪标签标注系统与基于深度学习的信号分类方法配合,实现在少量有标签样本和大量无标签样本条件下的调制方式分类。仿真结果表明,对6种数字信号进行调制识别,在信噪比大于5 dB时,伪标签算法可将模型识别性能提高5%~10%,该算法设计简单,具有较大应用价值。
关键词:    调制识别    伪标签    半监督学习   
A Few-Shot Modulation Recognition Method Based on Pseudo-Label Semi-Supervised Learning
SHI Yunhao, XU Hua, LIU Yinghui
Institute of Information & Navigation, Air Force Engineering University, Xi'an 710077, China
Abstract:
In order to solve the problem of insufficient labeled samples in modulation recognition, this paper proposes a few-shot modulation recognition algorithm based on pseudo-label semi-supervised learning (pseudo-label algorithm). First of all, high quality artificial feature, excellent classifier and data-labeling method are used to build efficient pseudo label system, and then the pseudo label system is combined with signal classification method based on the deep learning to realize the modulation classification under the condition of a small number of labeled samples and a large number of unlabeled samples. The simulation results show that the pseudo-label algorithm can improve the model recognition performance by 5%-10% when the six kinds of digital signals are classified and identified and its SNR is greater than 5 dB. At the same time, the algorithm has a simple network design and is of great application value.
Key words:    modulation recognition    pseudo-label algorithm    semi-supervised learning    simulation   
收稿日期: 2019-12-31     修回日期:
DOI: 10.1051/jnwpu/20203851074
基金项目: 国家自然科学基金(61601500)资助
通讯作者:     Email:
作者简介: 史蕴豪(1996-),空军工程大学硕士研究生,主要从事智能通信对抗、信号处理研究。
相关功能
PDF(2928KB) Free
打印本文
把本文推荐给朋友
作者相关文章
史蕴豪  在本刊中的所有文章
许华  在本刊中的所有文章
刘英辉  在本刊中的所有文章

参考文献:
[1] PANAGIOTOU P, ANASTASOPOULOS A, POLYDOROS A. Likelihood Ratio Tests for Modulation Classification[C]//MILCOM 2000 Proceedings of 21st Century Military Communications, Architectures and Technologies for Information Superiority, 2000:670-674
[2] POLYDOROS A, KIM K. On the Detection and Classification of Quadrature Digital Modulations in Broad-Band Noise[J]. IEEE Trans on Communications, 1990, 38(8):1199-1211
[3] ABDI A, DOBRE O A, CHOUDHRY R, et al. Modulation Classification in Fading Channels Using Antenna Arrays[C]//IEEE Military Communications Conference, 2004:211-217
[4] 赵雄文,郭春霞,李景春. 基于高阶累积量和循环谱的信号调制方式混合识别算法[J]. 电子与信息学报,2016,38(3):674-680 ZHAO Xiongwen, GUO Chunxia, LI Jingchun, et al. Mixed Recognition Algorithm for Signal Modulation Schemes by High-Order Cumulants and Cyclic Spectrum[J]. Journal of Electronics & Information Technology, 2016,38(3):674-680(in Chinese)
[5] 刘亚冲,唐智灵. 基于Softmax回归的通信辐射源特征分类识别方法[J]. 计算机工程,2018,44(2):98-102 LIU Yachong, TANG Zhiling. Classification and Identification Method of Communication Radiation Source Feature Based on Softmax Regression[J]. Computer Engineering, 2018, 44(2):98-102(in Chinese)
[6] ZHANG Z, LI Y B, JIN S S, et al. Modulation Signal Recognition Based on Information Entropy and Ensemble Learning[J]. Entropy, 2018, 20(3):198-198
[7] WANG H, GUO L L, DOU Z, et al. A New Method of Cognitive Signal Recognition Based on Hybrid Information Entropy and D-S Evidence Theory[J]. Mobile Networks and Applications, 2018, 23(4):677-685
[8] O'SHEA T J, CORGAN J, CLANCY T C. Convolutional Radio Modulation Recognition Networks[C]//International Conference on Engineering Applications of Neural Networks, 2016:213-226
[9] O'SHEA T J, ROY T, CLANCY T C. Over-the-Air Deep Learning Based Radio Signal Classification[J]. IEEE Journal of Selected Topics in Signal Process, 2018, 12(1):168-179
[10] JEONG S, LEE U, KIM S C. Spectrogram-Based Automatic Modulation Recognition Using Convolution Neural Network[C]//2018 Tenth International Conference on Ubiquitous and Future Networks, 2018:843-845
[11] MENG Fan, CHEN Peng, WU Lenan. Automatic Modulation Classification:A Deep Learning Enabled Approach[J]. IEEE Trans on Vehicular Technology, 2018, 67(11):10760-10772
[12] 白芃远,许华,孙莉. 基于卷积神经网络与时频图纹理信息的信号调制方式分类方法[J]. 西北工业大学学报,2019,37(4):816-823 BAI Pengyuan, XU Hua, SUN Li. A Recognition Algorithm for Modulation Schemes by Convolution Neural Network and Sopectrum Texture[J]. Journal of Northwestern Polytechnical University, 2019, 37(4):816-823(in Chinese)
[13] ZHANG Z, WANG C, GAN C, et al. Automatic Modulation Classification Using Convolutional Neural Network with Features Fusion of SPVWD and BJD[J].IEEE Trans on Signal and Information Processing over Networks, 2019, 5(3):469-478
[14] 龙明盛. 迁移学习问题与方法研究[D]. 北京:清华大学,2014 LONG Mingsheng. Transfer Learning:Problems and Methods[D]. Beijing:Tsinghua University, 2014(in Chinese)
[15] MAULIK U, CHAKRABORTY D. A Self-Trained Ensemble with Semi-Supervised SVM:an Application to Pixel Classification of Remote Sensing Imagery[J]. Pattern Recognition,2011,44(3):615-623
[16] PAWAR S, BHATTACHARYYA P, PALSHIKAR G K. Semi-Supervised Relation Extraction Using EM Algorithm[C]//10th Int Conf on Natural Language Processing, 2013
[17] 陈波. 半监督迁移学习算法研究[D]. 西安:西北大学,2015 CHEN Bo. Research on Semi-Supevised Transfer Learning[D]. Xi'an:Northwest University, 2015(in Chinese)
[18] 李跃,郭兴吉,赵欣. 基于高阶累积量的调制方式识别研究[J]. 西南科技大学学报,2018,33(3):64-68 LI Yue, GUO Xingji, ZHAO Xin. Study on Modulation Recognition Based on Higher-Order Cumulants[J]. Journal of Southwest University of Science and Technology, 2018, 33(3):64-68(in Chinese)
[19] 谭晓衡,褚国星,张雪静, 等. 基于高阶累积量和小波变换的调制识别算法[J]. 系统工程与电子技术, 2018(1):171-177 TAN Xiaoheng, CHU Gouxing, ZHANG Xuejing, et al. Modulation Recognition Algorithm Based on High-Ordercumulants and Wavelet Transform[J]. Engineering and Electronic, 2018(1):171-177(in Chinese)
[20] 李晨,杨俊安,刘辉. 基于信息熵和GA-ELM的调制识别算法[J]. 系统工程与电子技术, 2020, 42(1):223-229 LI Chen, YANG Junan, LIU Hui. Modulation Recognition Algorithm Based on Information Entropy and GA-ELM[J]. Engineering and Electronic, 2020, 42(1):223-229(in Chinese)
[21] ZHEN Z, YIBING L, SHANSHAN J, et al. Modulation Signal Recognition Based on Information Entropy and Ensemble Learning[J]. Entropy, 2018, 20(3):198
[22] ALI A, FAN Y. Automatic Modulation Classification Using Deep Learning Based on Sparse Autoencoders with Non-Negativity Constraints[J]. IEEE Signal Processing Letter, 2017, 24(11):1626-1630