A Novel Approach to Radiometric Identification

TL;DR

This paper introduces CAPoNeF, a feature engineering method enabling highly accurate radiometric device identification with machine learning, achieving 99% accuracy even with reduced feature dimensions.

Contribution

The paper presents a new feature engineering approach, CAPoNeF, and demonstrates its effectiveness in radiometric identification with high accuracy using standard ML classifiers.

Findings

Random Forest achieved 99% accuracy.

Feature reduction to 3 dimensions still maintains 99% classification accuracy.

Features analyzed with correlation metrics to identify relevance.

Abstract

This paper demonstrates that highly accurate radiometric identification is possible using CAPoNeF feature engineering method. We tested basic ML classification algorithms on experimental data gathered by SDR. The statistical and correlational properties of suggested features were analyzed first with the help of Point Biserial and Pearson Correlation Coefficients and then using P-values. The most relevant features were highlighted. Random Forest provided 99% accuracy. We give LIME description of model behavior. It turns out that even if the dimension of the feature space is reduced to 3, it is still possible to classify devices with 99% accuracy.