|
|
论文:2019,Vol:37,Issue(4):816-823 |
|
|
引用本文： |
|
|
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 |
|
|
BAI Pengyuan, XU Hua, SUN Li. A Recognition Algorithm for Modulation Schemes by Convolution Neural Network and Spectrum Texture[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 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 |
|
| 白芃远, 许华, 孙莉 |
|
| 空军工程大学 信息与导航学院, 陕西 西安 710077 |
| 摘要: |
| 通信信号的调制方式识别是通信侦察、频谱监测的重要工作内容之一，提出一种利用深度学习提取信号时频图纹理信息的分类方法。该方法利用不同调制方式在时频图细节上的微弱差别，并使用卷积神经网络提取图像纹理特征，最终输入SOFTMAX分类器进行分类。结果表明，该方法在大样本条件下，可取得良好的分类效果。与传统基于特征参数的支持向量机分类方法或前馈神经网络方法相比，其提取特征更优、分类效果更好，同时减少了人工设计特征参数的工作量和不确定性。 |
| 关键词:
调制识别
时频图纹理信息
深度学习
卷积神经网络
|
|
| A Recognition Algorithm for Modulation Schemes by Convolution Neural Network and Spectrum Texture |
|
| BAI Pengyuan, XU Hua, SUN Li |
|
| Institute of Information and Navigation, Air Force Engineering University, Xi'an 710077, China |
| Abstract: |
| The recognition of modulation schemes for communication signals is an important part of communication surveillance and spectrum monitoring. An algorithm based on deep learning and spectrum texture is proposed to recognize modulation schemes. Based on imperceptible differences among various spectrums of modulation schemes, the algorithm uses Convolution Neural Network to capture the features of image texture and thus classify the features with a SOFTMAX classifier. The experiment shows the algorithm performs better than traditional algorithm based on feature parameters, while the features captured can better reveal the signal detail and reduces effort on feature parameter design. |
| Key words:
modulation classification
spectrum texture
deep learning
convolution neural network
algorithm
|
|
| 收稿日期: 2018-07-23
修回日期:
|
| DOI: 10.1051/jnwpu/20193740816 |
| 基金项目: 国家自然科学基金（61701531）资助 |
| 通讯作者:
Email： |
| 作者简介: 白芃远(1995-),空军工程大学硕士研究生,研究从事电子对抗研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 白芃远 在本刊中的所有文章 |
| 许华 在本刊中的所有文章 |
| 孙莉 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 陈红,蔡晓霞,徐云,等. 基于多重分形特征的通信调制方式识别研究[J]. 电子与信息学报,2016, 4(38):863-869 CHEN Hong, CAI Xiaoxia, XU Yun, et al. Communication Modulation Recognition Based on Multi-Fractal Dimension Characteristics[J]. Journal of Electronics and Information Technology, 2016, 38(4):863-869(in Chinese)
[2] 杨发权,李赞,李红艳,等. 基于蜂群算法和神经网络的通信调制识别方法[J]. 系统工程与电子技术, 2013, 35(10):2186-2191 YANG Faquan, LI Zan, LI Hongyan, et al. Research of Communication Modulation Recongnition Based on Bee Colony Algorithm and Neural Netowork[J]. Systems Engineering and Electronics, 2013, 35(10):2186-2191(in Chinese)
[3] 李一兵,葛娟,林云. 基于熵特征和支持向量机的调制识别方法[J]. 系统工程与电子技术,2012, 34(8):1691-1695 LI Yibing, Ge Juan, LIN Yun. Modulation Recongition Using Entropy Features and SVM[J]. Systems Engineering and Electronics, 2012, 34(8):1691-1695(in Chinese)
[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. 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] 韩洁,张涛,王欢欢,等. 基于3D-Hibert能量谱和多尺度分形特征的通信辐射源个体识别[J]. 通信学报, 2017, 38(4):99-109 HAN Jie, ZHANG Tao, WANG Huanhuan, et al. Communication Emitter Individual Identification Based on 3D-Hibert Energy Spectrum and Multi-Scale Fractal Features[J]. Journal on Communications, 2017, 38(4):99-109(in Chinese)
[6] NANDI A K, AZZOUZ E E. Algorithms for Automatic Modulation Recognition of Communication Signals[J]. IEEE Trans on Communications, 1998, 46(4):431-436
[7] 付俊强,李蓉,赵成林, 等. 基于贝叶斯序贯推理的自适应调制识别算法[J]. 系统工程与电子技术, 2015, 37(12):2860-2864 FU Junqiang, LI Rong, ZHAO Chenglin, et al. Sequential Bayesian Inference Based Adaptive Modulation Recognition Algorithm[J]. Systems Engineering and Electronics, 2015, 37(12):2860-2864(in Chinese)
[8] 刘明骞,李兵兵,曹超凤, 等. 认知无线电中非高斯噪声下数字调制信号识别方法[J]. 通信学报, 2014, 35(1):82-88 LIU Mingqian, LI Bingbing, CAO Chaofeng, et al. Recognition Method of Digital Modulation Signals over Non-Gaussian Noise in Cognitive Radio[J]. Journal on Communications, 2014, 35(1):82-88(in Chinese)
[9] 陆珊珊,王伟,王国玉. 幅相调制信号的星座图恢复与调制方式识别[J]. 国防科技大学学报,2016, 38(6):130-134 LU Shanshan, WANG Wei, WANG Guoyu. Constellation Recovery and Modulation Recongition for Multiplequadrature Amplitude Modulation Signals[J]. Journal of Mational University of Defense Technology, 2016, 38(6):130-134(in Chinese)
[10] SWAMI A, SADLER B M. Hierarchical Digital Modulation Classification Using Cumulants[J]. IEEE Trans on Communications, 2000, 48(3):416-429
[11] HARALICK R, SHANMNGAM K, DINSTEIN I. Texture Feature for Image Classification[J]. IEEE Trans on Systems, Manand Cybernetics, 1973, 3(6):768-780
[12] 冀中,聂林红. 基于抗噪声局部二值模式的纹理图像分类[J]. 计算机研究与发展,2016,53(5):1128-1135 JI Zhong, NIE Linhong. Texture Image Classification with Noise-Tolerant Local Binary Pattern[J]. Journal of Computer Research and Development, 2016, 53(5):1128-1135(in Chinese)
[13] LEE H, GROSSE R, Ranganath R. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations[C]//International Conference on Machine Learning, 2009
[14] LEE Y J, GRAUMAN K. Learning the Easy Things First:Self-Paced Visual Category Discovery[C]//Conference on Computer Vision and Pattern Recognition, 2011
[15] NIXON M, ALBERTO S. Aguado. Feature Extraction and Image Processing[M]. Amsterdam, Elsevier Academic Press, 2008
[16] KRIZHEVSKY A, SUTSKEVER I, HINTON G. Imagenet Classification with Deep Convolutional Networks[C]//Advances in Neural Information Processing Systems, 2012:1097-1105
[17] GOODFELLOW I, COURVILLE A. On Distinguishability Criteria for Estimating Generative Models[C]//International Conference on Learning Representations, 2014
[18] KINGMA D, REZENDE D, MOHAMED S. Semi-Supervised Learning with Deep Generative Models[C]//Neural Information Processing Systems, 2014
[19] BERTONCINI C, RUDD K, NOUSAIN B. Wavelet Fingerprinting of Radio-Frequency Identification(RFID) Tags[J]. IEEE Trans on Industrial Electronics, 2012, 59(12):4843-4850
[20] 孙延奎. 小波分析及其应用[M]. 北京:机械工业出版社, 2005 SUN Yankui. Wavelet Analysis and Application[M]. Beijing, Mechanical Industry Press, 2005(in Chinese) |
|
|
|
|
|
|
|
