Deep Learning for Spectral Filling in Radio Frequency Applications

TL;DR

This paper introduces deep learning techniques to enhance RF spectral efficiency by embedding additional information within existing signals, effectively increasing capacity without bandwidth expansion and maintaining undetectability.

Contribution

It presents novel neural network-based methods for spectral filling that learn to encode extra messages around fixed modulation schemes, improving RF channel capacity.

Findings

Increased channel capacity without bandwidth increase

Generated signals closely resemble original modulations

Extra messages remain undetectable to third parties

Abstract

Due to the Internet of Things (IoT) proliferation, Radio Frequency (RF) channels are increasingly congested with new kinds of devices, which carry unique and diverse communication needs. This poses complex challenges in modern digital communications, and calls for the development of technological innovations that (i) optimize capacity (bitrate) in limited bandwidth environments, (ii) integrate cooperatively with already-deployed RF protocols, and (iii) are adaptive to the ever-changing demands in modern digital communications. In this paper we present methods for applying deep neural networks for spectral filling. Given an RF channel transmitting digital messages with a pre-established modulation scheme, we automatically learn novel modulation schemes for sending extra information, in the form of additional messages, "around" the fixed-modulation signals (i.e., without interfering with them). In so doing, we effectively increase channel capacity without increasing bandwidth. We further demonstrate the ability to generate signals that closely resemble the original modulations, such that the presence of extra messages is undetectable to third-party listeners. We present three computational experiments demonstrating the efficacy of our methods, and conclude by discussing the implications of our results for modern RF applications.