薛宪峰,
吴静谊,
南瑞祥
哈尔滨理工大学测控技术与仪器黑龙江省高校重点实验室 哈尔滨 150080
基金项目:国家自然科学基金(61501150)，黑龙江省自然科学基金(QC2014C074)，黑龙江省省属本科高校基本科研业务费科研项目(2018-KYYWF-1656)
详细信息
作者简介:盖建新：男，1980年生，博士，副教授，研究方向为频谱感知、机器学习、亚奈奎斯特采样理论、压缩感知等
薛宪峰：男，1996年生，硕士生，研究方向为深度学习
吴静谊：女，1996年生，硕士生，研究方向为压缩感知
南瑞祥：男，1996年生，硕士生，研究方向为通信信号处理
通讯作者:盖建新 jxgai@hrbust.edu.cn
中图分类号:TN911计量
文章访问数:466
HTML全文浏览量:113
PDF下载量:135
被引次数:0
出版历程
收稿日期:2020-11-30
修回日期:2021-03-12
网络出版日期:2021-03-25
刊出日期:2021-10-18
Cooperative Spectrum Sensing Method Based on Deep Convolutional Neural Network
Jianxin GAI,,Xianfeng XUE,
Jingyi WU,
Ruixiang NAN
The Higher Educational Key Laboratory for Measuring & Control Technology and Instrumentations of Heilongjiang Province, Harbin University of Science and Technology, Harbin 150080, China
Funds:The National Natural Science Foundation of China (61501150), The Natural Science Foundation of Heilongjiang Province (QC2014C074), The Fundamental Research Funds for the Universities in Heilongjiang Province (2018-KYYWF-1656)
摘要
摘要:针对传统卷积神经网络(CNN)频谱感知方法提取特征能力受限于网络结构简单，增加网络结构又容易出现梯度消失等问题，该文通过在传统卷积神经网络中添加捷径连接，实现输入层恒等映射更深的网络，提出一种基于深度卷积神经网络(DCNN)的协作频谱感知方法。该方法将频谱感知问题转化为图像二分类问题，对正交相移键控(QPSK)信号的协方差矩阵进行归一化灰度处理，并作为深度卷积神经网络的输入，通过残差学习训练深度卷积神经网络模型，提取2维灰度图像的深层特征，将测试数据输入到训练好的模型中，完成基于图像分类的频谱感知。实验结果表明：与传统的频谱感知方法相比，在低信噪比(SNR)下、多用户协作感知时，所提方法具有更高的检测概率和更低的虚警概率。
关键词:协作频谱感知/
深度卷积神经网络/
残差学习/
协方差矩阵
Abstract:The traditional spectrum sensing method of Convolutional Neural Network (CNN) has a simple network structure which limits the ability of feature extraction. To solve the problem of gradient disappearance, a cooperative spectrum sensing method based on Deep Convolutional Neural Network (DCNN) is proposed in this paper, in which shortcut connections are added to the CNN to realize the deeper network of input level identity radiation. This method transforms the spectrum sensing problem into the image binary classification problem, and performs normalized gray level processing on the covariance matrix of Quadrature Phase Shift Keying (QPSK) signal as the input of DCNN, which trains DCNN model through residual learning and extracts the deep image features of the two-dimensional grayscale image. The testing data is input into the trained model and spectrum sensing based on image classification is completed. The experimental results show that the proposed method has higher detection probability and lower false alarm probability than the traditional spectrum sensing method when the Signal to Noise Ratio (SNR) is low and multiple users collaborate in sensing.
Key words:Cooperative spectrum sensing/
Deep Convolutional Neural Network (DCNN)/
Residual learning/
Covariance matrix
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=554991d4-e22c-41de-a3de-fc0ec88f5494
