Wireless signal modulation identification method based on RF I/Q data distribution

Electromagnetic spectrum detection is the basis of the next generation wireless communication technology. Wireless signal identification is an important part of electromagnetic spectrum detection and management activities. This paper proposes to extract the distribution features of different modulat...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2021-11, Vol.11 (1), p.21383-21383, Article 21383
Main Authors: Wang, Lihui, Chen, Zhenjia, Zhang, Yonghui
Format: Article
Language:English
Subjects:
631/114/1314
631/114/2398
Algorithms
Classification
Humanities and Social Sciences
Identification
Methods
multidisciplinary
Neural networks
Noise
Science
Science (multidisciplinary)
Software
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Electromagnetic spectrum detection is the basis of the next generation wireless communication technology. Wireless signal identification is an important part of electromagnetic spectrum detection and management activities. This paper proposes to extract the distribution features of different modulated signals from the signal I/Q data. A two-dimensional gradient matrix is used to describe the characteristics of the signal classification. The minimum gradient cumulative distance (GCD) estimate between the sample and the model is used as the decision criterion for the signal classification. According to the result of the confusion matrix, the weight of the model is adjusted. Experiments show that the recognition rate of the modulated signal mentioned in this paper can reach 82.75%. The I/Q data sample was extracted under actual engineering conditions involving random noise, and the recognition rate dropped to approximately 79%. Based on the initial model gradient matrix, a reasonable algorithm is set to adjust the weight of the model, which can effectively improve the recognition rate of the modulated signal.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-021-00723-7