.png){kind=icon}
.png){kind=icon}
Return
Enhanced Specific Emitter Identification With Limited Data Through Dual Implicit Regularization
.png){kind=icon}
PRE
AI
DOI：10.1109/JIOT.2024.3395441.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Specific emitter identification (SEI) is a critical technology for physical layer authentication in wireless communications and the Internet of Things. Leveraging the inherent and hard-to-forge characteristics of radio frequency fingerprinting (RFF), SEI has gained significant attention. Recent advancements in deep learning have propelled SEI methods to new heights of identification performance. However, these methods are often constrained by their reliance on large data sets, posing challenges in real-world scenarios with limited samples. Addressing this issue, this article proposes an enhanced SEI approach tailored for limited sample environments, employing double implicit regularization (DIR). Our proposed method, DIR-multiscale residual attention network (MRAN), utilizes a MRAN to extract features effectively from limited samples. The DIR strategy enhances model generalizability by incorporating sample-wise implicit regularization (SIR) and Label-wise Implicit Regularization (LIR), which, respectively, facilitate sample expansion and label smoothing. We evaluated DIR-MRAN on two real-world data sets, achieving an impressive 95.34% accuracy on the power amplifier data set and outperforming comparative methods by 26.4% on the ADS-B data set.
Keywords:
Feature extraction
Internet of Things
Convolutional neural networks
Training
Wireless communication
Physical layer
Object recognition
Double implicit regularization (DIR)
limited samples
multiscale residual attention network (MRAN)
specific emitter identification (SEI)
Journal
IF:
8.9
Papers:
1.4W
Citations:
7.8W