.png){kind=icon}
.png){kind=icon}
Return
Zero-Shot Modulation Recognition via Knowledge-Informed Waveform Description
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2024.3491013.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In non-cooperative environments, deep learning-based automatic modulation recognition techniques often struggle with the situations with insufficient or even no training data accessible. In this letter, we investigate this problem in the amplitude-phase-modulation recognition task and introduce a knowledge-informed waveform description for zero-shot recognition generalization. Specifically, drawing inspiration from constellation association knowledge, we define a constellation-based semantic attribute set to describe waveform structures and employ graph formulation to model attributes' symmetric dependency for improving representations. Subsequently, we align the waveform and semantic spaces by associating waveform and attribute compositional representations, facilitating the transfer of knowledge from the seen to unseen domain. Our scheme can reason the labels of unseen waveform types with the guidance of the attribute description outputting, beyond merely distinguishing test instances as unseen. Experiments validate the efficacy of the proposed method across few-shot and zero-shot recognition tasks.
Keywords:
Semantics
Modulation
Training
Symmetric matrices
Vectors
Zero shot learning
Symbols
Visualization
Receivers
Laboratories
Automatic modulation recognition
knowledge and data joint-driven learning
zero-shot learning
graph neural networks
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W