APL: Integrated Discriminative Features and Robust Boundary for Modulation Open-Set Recognition
- 18 December 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (4) , 5724-5740
Abstract
As the electromagnetic environment becomes increasingly complex, traditional Automatic Modulation Recognition (AMR) methods cannot handle unknown modulation types that may arise under real-world conditions. Therefore, Automatic Modulation Open-Set Recognition (AMOSR) has gained significant attention as a technique that could identify unknown classes, playing a crucial role in enhancing the reliability of cognitive radio systems. Existing AMOSR approaches have primarily concentrated on either extracting discriminative features or establishing robust decision boundaries to enhance the AMOSR performance. To overcome existing limitation, we propose an Adversarial Prototype Learning (APL) algorithm to jointly optimize the features and boundaries through iterative refinement of prototype learning and adversarial learning. The prototype learning exploits the semantic similarity with the designed distribution distance-based cross entropy loss, aiming to obtain compact feature distributions while enhancing inter-class separability. The adversarial learning fully leverages the generated counterfactual images to constrain the unknown feature space, thus conducive to robust decision boundaries between known and unknown classes. The joint optimization yields mutual enhancements to boost AMOSR performance, as discriminative features facilitate boundary formulation, while well-defined boundaries further consolidate feature concentration. Comprehensive experiments on simulated and real-world signals demonstrate the effectiveness and robustness of APL compared to state-of-the-art AMOSR methods across various signal conditions.Keywords
Funding Information
- National Natural Science Foundation of China (62301031)
This publication has 59 references indexed in Scilit:
- VAE and Feature Fusion Based Open-Set Point Generation Network for Open-Set Radar Models Recognition2023
- Modulated Signal Open-Set Identification of Complex Convolutional Neural Networks Combined with Incremental Learning2023
- Open-Set Recognition of LPI Radar Signals Based on Deep Class Probability Output Network2022
- Modulation Classifier: A Few-Shot Learning Semi-Supervised Method Based on Multimodal Information and Domain Adversarial NetworkIEEE Communications Letters, 2022
- Open Set Recognition of Communication Signal Modulation Based on Deep LearningIEEE Communications Letters, 2022
- A Transformer Based Approach for Open Set Specific Emitter Identification2021
- Machine Learning Based Automatic Modulation Recognition for Wireless Communications: A Comprehensive SurveyIEEE Access, 2021
- Unknown Radar Waveform Recognition Based on Transferred Deep LearningIEEE Access, 2020
- Open Set Learning with Counterfactual Images2018
- Energy distanceWIREs Computational Statistics, 2015