摘要
针对传统辐射源信号识别方法在低信噪比条件下提取特征困难且识别率低的问题,提出了一种基于短时傅里叶(STFT)变换和栈式降噪自编码器(sDAE)的识别系统。首先对雷达辐射源信号进行短时傅里叶变化,然后对时频图像进行一系列预处理,将处理后的图像输入到栈式降噪自编码器中,将提取的特征输入到softmax分类器中,完成分类识别。通过仿真表明:该系统在SNR=-10 dB的时候,识别率能够达到80%以上,在低信噪比的情况下,识别效果明显优于传统识别方法。
Aimed at the problems that by the traditional recognition method the recognition rate is low and the feature extraction is difficult under condition of low signal to noise ratio,an automatic classification and recognition system based on short time Fourier transform(STFT)and stacked de-noising Auto-Encoder(sDAE)is proposed.Firstly,the radar emitter signal is changed by the short time Fourier transform,then a series of preprocessing is carried out to the time frequency image.The processed image is input into the stacked denoising auto-encoder,and the extracted features are input into the soft-max classifier to complete the classification recognition.The simulation shows that the recognition rate can reach more than 80%when the system is in SNR=-10 dB.In the case of low SNR,the recognition rate is obviously better than that by the traditional recognition method.
作者
叶文强
俞志富
张奎
王虎帮
YE Wenqiang;YU Zhifu;ZHANG Kui;WANG Hubang(Unit 63768,Xi’an 710600,China;College of Electronic Countermeasure,National University of Defense Technology,Hefei 230037,China)
出处
《空军工程大学学报(自然科学版)》
CSCD
北大核心
2019年第6期47-53,共7页
Journal of Air Force Engineering University(Natural Science Edition)
基金
安徽省自然科学基金(1808085QF182)
关键词
雷达辐射源
短时傅里叶
图像预处理
栈式降噪自编码器
分类器
radar emitter
short time Fourier transform(STFT)
image processing
stacked de-noising auto-encoder(sDAE)
classifier