Affiliation(s):
College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China;
moreAffiliation(s): College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China; Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin Engineering University, Harbin 150001, China; China Coal Technology Engineering Group Chongqing Research Institute, Chongqing 400037, China; State Key Lab. of Methane Disaster Monitoring & Emergency Technology, Chongqing 400039, China;
less
Xiang LI, Yibing LI, Chunrui TANG, Yingsong LI. Modulation recognition network of multi-scale analysis with deep threshold noise elimination[J]. Frontiers of Information Technology & Electronic Engineering , 1998, -1(11): .
@article{title="Modulation recognition network of multi-scale analysis with deep threshold noise elimination", author="Xiang LI, Yibing LI, Chunrui TANG, Yingsong LI", journal="Frontiers of Information Technology & Electronic Engineering", volume="-1", number="-1", pages="", year="1998", publisher="Zhejiang University Press & Springer", doi="10.1631/FITEE.2200253" }
%0 Journal Article %T Modulation recognition network of multi-scale analysis with deep threshold noise elimination %A Xiang LI %A Yibing LI %A Chunrui TANG %A Yingsong LI %J Frontiers of Information Technology & Electronic Engineering %V -1 %N -1 %P %@ 1869-1951 %D 1998 %I Zhejiang University Press & Springer
TY - JOUR T1 - Modulation recognition network of multi-scale analysis with deep threshold noise elimination A1 - Xiang LI A1 - Yibing LI A1 - Chunrui TANG A1 - Yingsong LI J0 - Frontiers of Information Technology & Electronic Engineering VL - -1 IS - -1 SP - EP - %@ 1869-1951 Y1 - 1998 PB - Zhejiang University Press & Springer ER -
Abstract: To improve the accuracy of modulated signal recognition in variable environments and reduce the impact of factors such as lack of priori knowledge on recognition results, researchers have gradually adopted deep learning techniques to replace traditional modulated signal processing techniques. To address the problem of low recognition accuracy of the modulated signal at low signal-to-noise ratios, we have designed a novel network based on multi-scale analysis of deep threshold noise elimination to recognize the actual collected modulated signals under the action of a symmetric cross-entropy function of label smoothing. The network consists of a denoising encoder with deep adaptive threshold learning and a decoder with multi-scale feature fusion. The two modules are skip-connected to work together to improve the robustness of the overall network. Experimental results show that this method has better recognition at low signal-to-noise ratios than previous methods. The network demonstrates a flexible self-learning capability for noise thresholds and the effectiveness of the designed feature fusion module for multi-scale feature acquisition for various modulated types.
Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article
Reference
Open peer comments: Debate/Discuss/Question/Opinion
Open peer comments: Debate/Discuss/Question/Opinion
<1>