Convolutional Radio Modulation Recognition Networks
This addresses the problem of accurate radio signal classification for communication systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled radio modulation classification by adapting convolutional neural networks to complex temporal radio signals, showing significant performance improvements over expert features, especially at low signal-to-noise ratios.
We study the adaptation of convolutional neural networks to the complex temporal radio signal domain. We compare the efficacy of radio modulation classification using naively learned features against using expert features which are widely used in the field today and we show significant performance improvements. We show that blind temporal learning on large and densely encoded time series using deep convolutional neural networks is viable and a strong candidate approach for this task especially at low signal to noise ratio.