DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation

Modulation recognition, as one of the key technologies in the field of wireless communications, holds significant importance in applications such as spectrum resource management, interference suppression, and cognitive radio. While deep learning has substantially improved the performance of Automati...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiankun Ma, Zhenxi Zhang, Linrun Zhang, Yu Li, Haoyue Tan, Xiaoran Shi, Feng Zhou
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4553
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406155133026304
author Jiankun Ma
Zhenxi Zhang
Linrun Zhang
Yu Li
Haoyue Tan
Xiaoran Shi
Feng Zhou
author_facet Jiankun Ma
Zhenxi Zhang
Linrun Zhang
Yu Li
Haoyue Tan
Xiaoran Shi
Feng Zhou
author_sort Jiankun Ma
collection DOAJ
description Modulation recognition, as one of the key technologies in the field of wireless communications, holds significant importance in applications such as spectrum resource management, interference suppression, and cognitive radio. While deep learning has substantially improved the performance of Automatic Modulation Recognition (AMR), it heavily relies on large amounts of labeled data. Given the high annotation costs and privacy concerns, researching semi-supervised AMR methods that leverage readily available unlabeled data for training is of great significance. This study constructs a semi-supervised AMR method based on dual-student. Specifically, we first adopt a dual-branch co-training architecture to fully exploit unlabeled data and effectively learn deep feature representations. Then, we develop a dynamic stability evaluation module using strong and weak augmentation strategies to improve the accuracy of generated pseudo-labels. Finally, based on the dual-student semi-supervised framework and pseudo-label stability evaluation, we propose a stability-guided consistency regularization constraint method and conduct semi-supervised AMR model training. The experimental results demonstrate that the proposed DualBranch-AMR method significantly outperforms traditional supervised baseline approaches on benchmark datasets. With only 5% labeled data, it achieves a recognition accuracy of 55.84%, reaching over 90% of the performance of fully supervised training. This validates the superiority of the proposed method under semi-supervised conditions.
format Article
id doaj-art-8dcd7577aec3454089ea7bf648a06f01
institution Kabale University
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-8dcd7577aec3454089ea7bf648a06f012025-08-20T03:36:30ZengMDPI AGSensors1424-82202025-07-012515455310.3390/s25154553DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability EvaluationJiankun Ma0Zhenxi Zhang1Linrun Zhang2Yu Li3Haoyue Tan4Xiaoran Shi5Feng Zhou6The Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, Xi’an 710126, ChinaThe Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, Xi’an 710126, ChinaThe Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, Xi’an 710126, ChinaThe Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, Xi’an 710126, ChinaThe Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, Xi’an 710126, ChinaThe Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, Xi’an 710126, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi’an 710126, ChinaModulation recognition, as one of the key technologies in the field of wireless communications, holds significant importance in applications such as spectrum resource management, interference suppression, and cognitive radio. While deep learning has substantially improved the performance of Automatic Modulation Recognition (AMR), it heavily relies on large amounts of labeled data. Given the high annotation costs and privacy concerns, researching semi-supervised AMR methods that leverage readily available unlabeled data for training is of great significance. This study constructs a semi-supervised AMR method based on dual-student. Specifically, we first adopt a dual-branch co-training architecture to fully exploit unlabeled data and effectively learn deep feature representations. Then, we develop a dynamic stability evaluation module using strong and weak augmentation strategies to improve the accuracy of generated pseudo-labels. Finally, based on the dual-student semi-supervised framework and pseudo-label stability evaluation, we propose a stability-guided consistency regularization constraint method and conduct semi-supervised AMR model training. The experimental results demonstrate that the proposed DualBranch-AMR method significantly outperforms traditional supervised baseline approaches on benchmark datasets. With only 5% labeled data, it achieves a recognition accuracy of 55.84%, reaching over 90% of the performance of fully supervised training. This validates the superiority of the proposed method under semi-supervised conditions.https://www.mdpi.com/1424-8220/25/15/4553automatic modulation recognitionsemi-superviseddual-student modeldynamic stabilityconsistency constraints
spellingShingle Jiankun Ma
Zhenxi Zhang
Linrun Zhang
Yu Li
Haoyue Tan
Xiaoran Shi
Feng Zhou
DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation
Sensors
automatic modulation recognition
semi-supervised
dual-student model
dynamic stability
consistency constraints
title DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation
title_full DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation
title_fullStr DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation
title_full_unstemmed DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation
title_short DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation
title_sort dualbranch amr a semi supervised amr method based on dual student consistency regularization with dynamic stability evaluation
topic automatic modulation recognition
semi-supervised
dual-student model
dynamic stability
consistency constraints
url https://www.mdpi.com/1424-8220/25/15/4553
work_keys_str_mv AT jiankunma dualbranchamrasemisupervisedamrmethodbasedondualstudentconsistencyregularizationwithdynamicstabilityevaluation
AT zhenxizhang dualbranchamrasemisupervisedamrmethodbasedondualstudentconsistencyregularizationwithdynamicstabilityevaluation
AT linrunzhang dualbranchamrasemisupervisedamrmethodbasedondualstudentconsistencyregularizationwithdynamicstabilityevaluation
AT yuli dualbranchamrasemisupervisedamrmethodbasedondualstudentconsistencyregularizationwithdynamicstabilityevaluation
AT haoyuetan dualbranchamrasemisupervisedamrmethodbasedondualstudentconsistencyregularizationwithdynamicstabilityevaluation
AT xiaoranshi dualbranchamrasemisupervisedamrmethodbasedondualstudentconsistencyregularizationwithdynamicstabilityevaluation
AT fengzhou dualbranchamrasemisupervisedamrmethodbasedondualstudentconsistencyregularizationwithdynamicstabilityevaluation