A Novel Approach to Radiometric Identification
This work provides a strong specific gain in radiometric identification for device classification, which could be relevant for security or device management applications.
This paper demonstrates highly accurate radiometric identification using the CAPoNeF feature engineering method. By applying basic ML classification algorithms to experimental SDR data, the authors achieved 99% accuracy, even when the feature space was reduced to just three dimensions.
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.