JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

Modulation recognition network of multi-scale analysis with deep threshold noise elimination

Author(s): Xiang LI, Yibing LI, Chunrui TANG, Yingsong LI
Affiliation(s): College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China; more
Corresponding email(s): chunruitang@126.com
Key Words: Signal noise elimination; Deep adaptive threshold learning network; Multi-scale feature fusion; Modulation recognition

Share this article to： More <<< Previous Paper \|Next Paper >>>

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
Chinese Summary
Academic Network
Reviewer Comment

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

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference