基于对信号功率谱拟合特征提取的信号识别方法

doi:10.13190/j.jbupt.2017-183

北京邮电大学学报 ›› 2018, Vol. 41 ›› Issue (2): 114-118.doi: 10.13190/j.jbupt.2017-183

基于对信号功率谱拟合特征提取的信号识别方法

田昊旻^1,2, 尹良^1,2, 马跃³, 李书芳^1,2

1. 北京邮电大学先进信息网络北京实验室, 北京 100876;
2. 北京邮电大学网络体系构建与融合北京市重点实验室, 北京 100876;
3. 北京邮电大学计算机科学与技术学院, 北京 100876

收稿日期:2017-09-12 出版日期:2018-04-28 发布日期:2018-03-17
作者简介:田昊旻(1993-),男,硕士生,E-mail:haomintian1@163.com;李书芳(1963-),女,教授,博士生导师.
基金资助:
国家自然科学基金项目（61427801）

Signal Recognition Based on Signal Power Spectrum Fitting Feature Extraction

TIAN Hao-min^1,2, YIN Liang^1,2, MA Yue³, LI Shu-fang^1,2

1. Beijing Key Laboratory of Network System Architecture and Convergence, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. Computer Network Research Center, Beijing University of Posts and Telecommunications, Beijing 100876, China;
3. School of Computer Science and Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2017-09-12 Online:2018-04-28 Published:2018-03-17

摘要/Abstract

摘要： 针对通信信号业务种类识别问题，提出利用机器学习领域的线性回归算法和多项式拟合模型提取信号功率谱的多项式拟合因子作为信号的统一特征来构建训练集，并在深度学习平台keras上构建了全连接的神经网络分类器模型.相比传统的方法，新方法具有对无线电信号统一表征而无需对业务逐个提取个性化特征的优点.选取实际无线电监测数据中的码分多址（CDMA）上行、CDMA下行、增强型全球移动通信系统（EGSM）上行、EGSM下行、无线局域网（WLAN）以及长期演进（LTE）6种信号的功率谱数据作为数据集，通过验证得到了97%的分类准确率，并证明了该方法的可行性.

关键词: 信号识别, 深度学习, 特征提取, 多项式回归

Abstract: Aiming at the problem of communication signal service type identification, the author proposes a polynomial fitting factor that extracts the power spectrum of the signal using the linear regression algorithm and the polynomial fitting model in machine learning field as a unified feature of the signal to construct the training set. A multi-layer fully connected neural network classifier model was built on depth learning platform. Compared with the traditional ones, this method has advantages of unifying the radio signal without the need of individual service to extract the personalized features. The power spectrum data of code division multiple access(CDMA) uplink, CDMA downlink, extended global system for mobile(EGSM) uplink, EGSM downlink, wireless local area networks (WLAN) and long time evolution (LTE) signals in the actual radio monitoring data are selected as data set, and 97% classification accuracy is verified. that this method is proven feasible.

Key words: signal recognition, deep learning, future extraction, polynomial regression

中图分类号:

TN911.6

田昊旻, 尹良, 马跃, 李书芳. 基于对信号功率谱拟合特征提取的信号识别方法[J]. 北京邮电大学学报, 2018, 41(2): 114-118.

TIAN Hao-min, YIN Liang, MA Yue, LI Shu-fang. Signal Recognition Based on Signal Power Spectrum Fitting Feature Extraction[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2018, 41(2): 114-118.

参考文献

[1] 吴月娴, 葛临东, 许志勇. 常用数字调制信号识别的一种新方法[J]. 电子学报, 2007, 35(4):782-785. Wu Yuexian, Ge Lindong, Xu Zhiyong. A new method for identifying commonly used digital modulation signals[J]. Acta Electronic Journal, 2007, 35(4):782-785.
[2] 朱雷, 程汉文, 吴乐南. 利用循环谱和参数统计的数字调制信号识别[J]. 应用科学学报, 2009, 27(2):137-143. Zhu Lei, Cheng Hanwen, Wu Lenan. Recognition of digital modulation signals using cyclic spectrum and parametric statistics[J]. Journal of Applied Sciences, 2009, 27(2):137-143.
[3] 张晓, 王金龙, 吴启晖. 认知无线电中一种基于循环谱的能量检测算法[J]. 电路与系统学报, 2010, 15(3):75-80. Zhang Xiao, Wang Jinlong, Wu Qihui. An energy detection algorithm based on cyclic spectrum in cognitive radio[J]. Journal of Circuits and Systems, 2010, 15(3):75-80.
[4] 崔丽, 王金龙, 吴启晖, 等. 认知无线电中基于信息简约的最大似然协同频谱感知算法[J]. 电子与信息学报, 2009, 31(9):2177-2182. Cui Li, Wang Jinlong, Wu Qihui, et al. The maximum likelihood cooperative spectral sensing algorithm based on information simplicity incognitive radio[J]. Journal of Electronics & Information Technology, 2009, 31(9):2177-2182.
[5] 辛建芳, 张立毅, 魏瑾, 等. 基于高阶累积量的数字调制信号识别[C]//中国通信学会学术年会. 中国通信学会第五届学术年会论文集. 南京:中国通信学会, 2008:462-466. Xin Jianfang, Zhang Liyi, Wei Jin, et al. Digitalmodulation signal recognition based on high order cumulant[C]//Annual Conference of China Communications Society. The 5^th Academic Conference Proceedings of China Communications Scoiety. Nanjing:China Communications Association, 2008:462-466.
[6] O'Shea T J, Corgan J, Clancy T C. Convolutional radio modulation recognition networks[C]//International Conference on Engineering Applications of Neural Networks.[S.l.]:Springer International Publishing, 2016:213-226.
[7] O'Shea T J, Corgan J, Clancy T C. Unsupervised representation learning of structured radio communication signals[C]//First International Workshop on Sensing, Processing and Learning for Intelligent Machines. Aalborg, Denmark:IEEE, 2016:1-5.
[8] O'Shea T J, West N, Vondal M, et al. Semi-supervised radio signal identification[C]//International Conference on Advanced Communication Technology. Bougp yeoug, South Korea:IEEE, 2017:33-38.
[9] O'Shea T J, Hoydis J. An introduction to machine learning communications systems[EB/OL]. 2017. http://arxiv.org/abs/1702.00832.
[10] West N E, O'Shea T J. Deep architectures for modulation recognition[C]//IEEE International Symposium on Dynamic Spectrum Access Networks.[S.l.]:IEEE, 2017:1-6.
[11] Anzai Y. Pattern recognition and machine learning[M]. Singapore:Springer, 2006:225-247.

[1]	刘阳, 滕颖蕾, 牛涛, 郅佳琳. 基于深度强化学习的滤波器剪枝方案[J]. 北京邮电大学学报, 2023, 46(3): 31-36.
[2]	靳梦凡, 黄智濒, 储志强. 复杂环境下多模态指导的点云补全方法[J]. 北京邮电大学学报, 2023, 46(3): 103-108.
[3]	荣震宇刘建毅. 基于Transformer和MLP的眼底血管分割算法[J]. 北京邮电大学学报, 2023, 46(1): 26-31.
[4]	宋宇博高嘉振. 改进YOLOv3算法的交通多目标检测方法[J]. 北京邮电大学学报, 2022, 45(5): 103-108.
[5]	张小乾谈振王潇梁芹万黎明. 基于正交投影学习的图像特征提取算法[J]. 北京邮电大学学报, 2022, 45(5): 85-90,128.
[6]	刘金桐, 杨国兴, 刘晓鸿, 王光宇. 针对心电图分类模型的平滑攻击算法[J]. 北京邮电大学学报, 2022, 45(4): 44-50.
[7]	黄柳婷, 刘可欣, 牛凯, 常春, 贺志强. 基于深度学习的哮喘患者CT影像黏液栓自动识别[J]. 北京邮电大学学报, 2022, 45(4): 58-63.
[8]	柳长源, 虎浩媛, 毕晓君. 双线性融合网络的驾驶员分心行为识别[J]. 北京邮电大学学报, 2022, 45(2): 79-84.
[9]	赵海英, 朱会, 侯小刚. 基于改进EMA单元的传统服饰图像语义分割[J]. 北京邮电大学学报, 2022, 45(1): 69-74.
[10]	张滨宇, 赵衍运, 杜昀昊, 万俊峰, 佟知航. 一种基于深度学习的PCB图像字符检测方法[J]. 北京邮电大学学报, 2022, 45(1): 108-114.
[11]	贾珺, 冯春燕, 夏海轮, 张天魁, 李成钢. 基于样本均衡与特征交互的通信网络故障预测方法[J]. 北京邮电大学学报, 2021, 44(6): 59-66.
[12]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.
[13]	王艺霏, 莫爽, 吴文睿, 范少华, 肖丁. 基于内外卷积网络的网络入侵检测[J]. 北京邮电大学学报, 2021, 44(5): 94-100.
[14]	汤永利, 李星宇, 赵宗渠, 李运峰. 面向Android支付破解应用的检测方法[J]. 北京邮电大学学报, 2021, 44(4): 95-101.
[15]	高慧, 张继威, 来扬, 王文东. 深度学习的人体图像半自动标注系统[J]. 北京邮电大学学报, 2021, 44(1): 104-109.

基于对信号功率谱拟合特征提取的信号识别方法

Signal Recognition Based on Signal Power Spectrum Fitting Feature Extraction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价