Scalable End-to-End RF Classification: A Case Study on Undersized Dataset Regularization by Convolutional-MST

TL;DR

This paper introduces a scalable deep learning method for RF classification that achieves high accuracy with minimal training data, addressing data scarcity and scalability issues in RF sensing applications.

Contribution

The paper proposes a novel multistage training approach for RF classification that significantly improves accuracy with fewer samples, demonstrating scalability to multiple classes.

Findings

Achieves over 99% accuracy with only 11 samples per class.

Outperforms standard DL approaches by up to 35% in accuracy.

Effective for classifying up to 17 diverse RF signal classes.

Abstract

Unlike areas such as computer vision and speech recognition where convolutional and recurrent neural networks-based approaches have proven effective to the nature of the respective areas of application, deep learning (DL) still lacks a general approach suitable for the unique nature and challenges of RF systems such as radar, signals intelligence, electronic warfare, and communications. Existing approaches face problems in robustness, consistency, efficiency, repeatability and scalability. One of the main challenges in RF sensing such as radar target identification is the difficulty and cost of obtaining data. Hundreds to thousands of samples per class are typically used when training for classifying signals into 2 to 12 classes with reported accuracy ranging from 87% to 99%, where accuracy generally decreases with more classes added. In this paper, we present a new DL approach based on multistage training and demonstrate it on RF sensing signal classification. We consistently achieve over 99% accuracy for up to 17 diverse classes using only 11 samples per class for training, yielding up to 35% improvement in accuracy over standard DL approaches.