Signal demodulator based on in‐phase and quadrature interference‐robust feature

Abstract

This letter examines the issue of mitigating strong co-channel interference in communication systems is addressed. Unlike conventional model-based methods, a novel data-driven scheme is proposed. A recurrent neural network is trained to directly demodulate the desired signal under strong co-channel interference. Instead of inputting the original received signal, in-phase and quadrature interference-robust features are extracted through preprocess. The recurrent neural network is then trained offline to implement sequence labelling, with the interferencerobust feature sequences and known code sequences of the desired signal as inputs and ground-truth labels. Meanwhile, a guard zone is introduced when loading the interference-robust feature sequences to enable better contextual information exploitation by the recurrent neural network demodulator. Online tests validated the low bit error rate of the recurrent neural network demodulator, under strong co-channel interference. Moreover, the proposed scheme outperformed existing modelbased and data-driven interference mitigation schemes in terms of the bit error rate, especially in low signal-to-interference ratio region. Inspiringly, the proposed data-driven scheme generalized well to varied unseen test conditions.