RF Signal Transformation and Classification using Deep Neural Networks

TL;DR

This paper introduces a convolutional transform for RF data to enable deep neural network classification, proposes a simple CNN architecture for raw RF I/Q data, and presents a new RF dataset RF1024 for future research, demonstrating improved performance on existing datasets.

Contribution

It presents a novel RF data transformation technique, a simple CNN architecture for raw RF data, and introduces the RF1024 dataset to advance RF signal classification research.

Findings

Improved classification accuracy on RadioML2016 dataset.

Effective raw RF I/Q data classification with the proposed CNN.

RF1024 dataset facilitates future RF signal processing research.

Abstract

Deep neural networks (DNNs) designed for computer vision and natural language processing tasks cannot be directly applied to the radio frequency (RF) datasets. To address this challenge, we propose to convert the raw RF data to data types that are suitable for off-the-shelf DNNs by introducing a convolutional transform technique. In addition, we propose a simple 5-layer convolutional neural network architecture (CONV-5) that can operate with raw RF I/Q data without any transformation. Further, we put forward an RF dataset, referred to as RF1024, to facilitate future RF research. RF1024 consists of 8 different RF modulation classes with each class having 1000/200 training/test samples. Each sample of the RF1024 dataset contains 1024 complex I/Q values. Lastly, the experiments are performed on the RadioML2016 and RF1024 datasets to demonstrate the improved classification performance.