| 基于集成时频通道注意力的倒残差神经网络干扰识别 |
| |
| 引用本文： | 靳增源,张晓瀛,谭思源,张学庆,魏急波. 基于集成时频通道注意力的倒残差神经网络干扰识别[J]. 信号处理, 2023, 39(2): 343-355. DOI: 10.16798/j.issn.1003-0530.2023.02.015 |
| |
| 作者姓名： | 靳增源 张晓瀛 谭思源 张学庆 魏急波 |
| |
| 作者单位： | 1.国防科技大学电子科学学院, 湖南 长沙 410073 |
| |
| 基金项目： | 国家自然科学基金资助项目61931020湖南省自然科学基金面上项目2022JJ30047 |
| |
| 摘 要： | 准确识别干扰类型是实施高效抗干扰举措的先决条件。针对低干噪比（Jamming-to-Noise Ratio,JNR）的条件下干扰识别准确率低的问题，本文将信号短时傅里叶变换（Short Time Fourier Transform,STFT）后的时频图像作为卷积神经网络训练输入，提出一种以倒残差结构为主体的神经网络架构，并引入联合时频通道注意力机制模块，同时从时频图像提取时频域和通道域的综合干扰特征，充分利用多维度的干扰特征信息来准确识别干扰类型。仿真结果表明，在JNR=-8 dB时，本文所提算法能够实现对8种类型干扰100%的准确识别，在JNR=-10 dB时所有类型的干扰信号识别准确率都能达到98.3%以上，在JNR=-14 dB准确率也依然可以达到90%以上。同时分析了所提算法的网络复杂度，结果表明所提方案在时间和空间复杂度上得到了较好的折中，验证了模型的性能优越性。
|
| 关 键 词： | 干扰识别 深度神经网络 倒残差结构 注意力机制 |
| 收稿时间： | 2022-07-25 |
Jamming Identification Based on Inverse Residual Neural Network with Integrated Time-frequency Channel Attention |
| |
| Affiliation: | 1.College of Electronic Science，National University of Defense Technology，Changsha，Hunan 410073，China2.Xi’an Electronic Engineering Research Institute，Xi’an，Shaanxi 710100，China3.College of Information and Communication，National University of Defense Technology，Wuhan，Hubei 430010，China |
| |
| Abstract: | ? ?Accurate identification of jamming types was a prerequisite for implementing efficient anti-jamming initiatives. Aiming at the problem of low accuracy of jamming recognition under the condition of low Jamming-to-Noise Ratio（JNR）， this paper took the time-frequency images of the signal after Short-Time Fourier transform（STFT） as the training input of the convolutional neural network， proposed a neural network architecture with inverted residual structure as the main body， and introduced an attention mechanism module of joint time-frequency channel， which accurately identified the jamming type by simultaneously extracting the integrated jamming features in time-frequency and channel domains from the time-frequency images and making full use of multi-dimensional jamming feature information. The simulation results indicate that the proposed algorithm can precisely discriminate eight types of jamming signals when JNR is ?8 dB. The recognition accuracy of eight types of jamming signals can reach more than 98.3% when JNR is ?10 dB and can still reach more than 90% when JNR is ?14 dB. The network complexity of the proposed algorithm was also analyzed. The outcomes indicate that the proposed scheme obtains a better compromise in time and space complexity， which verifies the superior performance of the model. |
| |
| Keywords: | |
|
| 点击此处可从《信号处理》浏览原始摘要信息 |
|
点击此处可从《信号处理》下载免费的PDF全文 |
