Conference site ยป Proceedings

Deep and Ensemble Learning to Win the Army RCO AI Signal Classification Challenge

Andres Vila
The Aerospace Corporation

Donna Branchevsky
The Aerospace Corporation

Kyle Logue
The Aerospace Corporation

Sebastian Olsen
The Aerospace Corporation

Esteban Valles
The Aerospace Corporation

Darren Semmen
The Aerospace Corporation

Alex Utter
The Aerospace Corporation

Eugene Grayver
The Aerospace Corporation

Abstract

Automatic modulation classification is a challenging problem with multiple applications including cognitive radio and signals intelligence. Most of the existing efforts to solve this problem are only applicable when the signal to noise ratio (SNR) is high and/or long observations of the signal are available. Recent work has focused on applying shallow and deep machine learning (ML) to this problem. In this paper, we present an exploration of such deep learning and ensemble learning techniques that was used to win the Army Rapid Capability Office (RCO) 2018 Signal Classification Challenge. An expert feature extraction and shallow learning approach is discussed in a simultaneous publication. We evaluated multiple state-of-the-art deep learning network architectures and adapted them to work in the RF signal domain instead of the image/computer-vision domain. The best deep learning methods were merged with the best expert feature extraction and shallow learning methods using ensemble learning. Finally, the ensemble classifier was calibrated to obtain marginal gains. The methods discussed are capable of correctly classifying waveforms at -10 dB SNR with over 63\% accuracy and signals at +10 dB SNR with over 95\% accuracy from an Army RCO provided training set.

Keywords

modulation classification, neural networks, deep learning, machine learning, ensemble learning, wireless communications, signals intelligence, probability calibration

DOI

10.25080/Majora-7ddc1dd1-003

Bibtex entry

Full text PDF