Classification of IQ-Modulated Signals Based on Reservoir Computing With Narrowband Optoelectronic Oscillators

We numerically perform the classification of IQ-modulated radiofrequency signals using reservoir computing based on narrowband optoelectronic oscillators (OEOs) driven by a continuous-wave semiconductor laser. In general, the OEOs used for reservoir computing are wideband and are processing analog signals in the baseband. However, their hardware architecture is inherently inadequate to directly process radiotelecom or radar signals, which are modulated carriers. On the other hand, the high-Q OEOs that have been developed for ultra-low phase noise microwave generation have the adequate hardware architecture to process such multi-GHz modulated signals, but they have never been investigated as possible reservoir computing platforms. In this article, we show that these high-Q OEOs are indeed suitable for reservoir computing with modulated carriers. Our dataset (DeepSig RadioML) is composed with 11 analog and digital formats of IQ-modulated radio signals (BPSK, QAM64, WBFM, etc.), and the task of the high-Q OEO reservoir computer is to recognize and classify them. Our numerical simulations show that with a simpler architecture, a smaller training set, fewer nodes and fewer layers than their neural network counterparts, high-Q OEO-based reservoir computers perform this classification task with an accuracy better than the state-of-the-art, for a wide range of parameters. We also investigate in detail the effects of reducing the size of the training sets on the classification performance.

Automated summary

In this study, it was shown that high-Q OEOs are suitable for reservoir computing tasks involving modulated carriers, achieving better accuracy than the current state-of-the-art. These high-Q OEO-based reservoir computers perform the classification of IQ-modulated radio signals with simpler architecture, smaller training sets, fewer nodes, and layers compared to neural network counterparts. The effects of reducing the size of training sets on classification performance were also investigated in detail.