Deep Learning for Spectrum Sensing

TL;DR

This paper introduces a deep learning-based spectrum sensing method for cognitive radio that outperforms traditional energy detectors, especially under noise uncertainty, and includes a cooperative detection system for enhanced performance.

Contribution

The paper presents the first deep learning-based signal detector for spectrum sensing that requires no prior channel or noise knowledge, and proposes a cooperative system for improved detection.

Findings

Deep learning detector achieves state-of-the-art performance.

The method is robust to noise uncertainty.

Cooperative detection significantly improves sensing accuracy.

Abstract

In cognitive radio systems, the ability to accurately detect primary user's signal is essential to secondary user in order to utilize idle licensed spectrum. Conventional energy detector is a good choice for blind signal detection, while it suffers from the well-known SNR-wall due to noise uncertainty. In this letter, we firstly propose a deep learning based signal detector which exploits the underlying structural information of the modulated signals, and is shown to achieve the state of the art detection performance, requiring no prior knowledge about channel state information or background noise. In addition, the impacts of modulation scheme and sample length on performance are investigated. Finally, a deep learning based cooperative detection system is proposed, which is shown to provide substantial performance gain over conventional cooperative sensing methods.