Deep Learning Based Detection for Spectrally Efficient FDM Systems

TL;DR

This paper explores the use of residual convolutional neural networks to develop efficient detectors for spectrally efficient FDM systems, demonstrating their superiority through extensive experimentation.

Contribution

It introduces a CNN-based detection approach specifically tailored for SEFDM systems, highlighting the effectiveness of residual CNN architectures.

Findings

Residual CNNs outperform traditional detectors in SEFDM

Deep learning models improve spectral efficiency detection accuracy

Extensive experiments validate the proposed approach

Abstract

In this study we present how to approach the problem of building efficient detectors for spectrally efficient frequency division multiplexing (SEFDM) systems. The superiority of residual convolution neural networks (CNNs) for these types of problems is demonstrated through experimentation with many different types of architectures.