Specific Emitter Identification Based on Multi-Scale Multi-Dimensional Approximate Entropy

Addressing the computational demands and data requirements associated with deep learning techniques, this study presents a novel Specific Emitter Identification (SEI) strategy, based on Multi-Scale Multi-Dimensional Approximate Entropy (MSMD-AE). We focus on the steady-state segment of received sign...

Full description

Saved in:
Bibliographic Details
Published inIEEE signal processing letters Vol. 31; pp. 850 - 854
Main Authors Zahid, Muhammad Usama, Nisar, Muhammad Danish, Shah, Maqsood Hussain, Hussain, Syed Aamer
Format Journal Article
LanguageEnglish
Published New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Emitters
Entropy
Feature extraction
Fractal dimension
Fractal geometry
multi dimension approximate entropy
multi scale approximate entropy
Signal processing algorithms
Signal to noise ratio
specific emitter identification
Steady-state
Training
Vectors
Very high frequencies
Online AccessGet full text

Cover

More Information
Summary:Addressing the computational demands and data requirements associated with deep learning techniques, this study presents a novel Specific Emitter Identification (SEI) strategy, based on Multi-Scale Multi-Dimensional Approximate Entropy (MSMD-AE). We focus on the steady-state segment of received signals, obtained through Katz Fractal Dimension (KFD). The performance of proposed method is thoroughly evaluated across a range of SNR variations for two distinct scenarios, involving real-world Very High-Frequency (VHF) radios and open-source cell phone datasets. A comprehensive comparison with the most relevant literature exhibits the superior performance of proposed MSMD-AE method.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2024.3375264