Classification of Radio Signals Using Truncated Gaussian Discriminant Analysis of Convolutional Neural Network-Derived Features

TL;DR

This paper introduces a novel Gaussian mixture model approach for RF signal classification using CNN-derived features, enabling efficient new class addition and SNR estimation without retraining the neural network.

Contribution

It presents a maximum likelihood classification method based on truncated Gaussian mixtures of CNN features, reducing parameters for new classes and enabling SNR estimation from the same features.

Findings

Comparable classification performance to full CNN training

Significant reduction in parameters for new class addition

Effective SNR estimation correlates with classification confidence

Abstract

To improve the utility and scalability of distributed radio frequency (RF) sensor and communication networks, reduce the need for convolutional neural network (CNN) retraining, and efficiently share learned information about signals, we examined a supervised bootstrapping approach for RF modulation classification. We show that CNN-bootstrapped features of new and existing modulation classes can be considered as mixtures of truncated Gaussian distributions, allowing for maximumlikelihood-based classification of new classes without retraining the network. In this work, the authors observed classification performance using maximum likelihood estimation of CNNbootstrapped features to be comparable to that of a CNN trained on all classes, even for those classes on which the bootstrapping CNN was not trained. This performance was achieved while reducing the number of parameters needed for new class definition from over 8 million to only 200. Furthermore, some physical features of interest, not directly labeled during training, e.g. signal-to-noise ratio (SNR), can be learned or estimated from these same CNN-derived features. Finally, we show that SNR estimation accuracy is highest when classification accuracy is lowest and therefore can be used to calibrate a confidence in the classification.