Machine learning empowered Modulation detection for OFDM-based signals

TL;DR

This paper introduces a blind machine learning approach using ResNet to detect modulation types and locate cyclic prefixes in OFDM signals, accounting for environmental imperfections and without prior signal knowledge.

Contribution

It presents a novel blind modulation detection method for OFDM signals that leverages deep learning to handle realistic environmental factors and does not require prior signal parameters.

Findings

Achieves over 80% accuracy at 10 dB SNR

Reaches 95% accuracy at 25 dB SNR

Effective across various modulation schemes and subcarrier counts

Abstract

We propose a blind ML-based modulation detection for OFDM-based technologies. Unlike previous works that assume an ideal environment with precise knowledge of subcarrier count and cyclic prefix location, we consider blind modulation detection while accounting for realistic environmental parameters and imperfections. Our approach employs a ResNet network to simultaneously detect the modulation type and accurately locate the cyclic prefix. Specifically, after eliminating the environmental impact from the signal and accurately extracting the OFDM symbols, we convert these symbols into scatter plots. Due to their unique shapes, these scatter plots are then classified using ResNet. As a result, our proposed modulation classification method can be applied to any OFDM-based technology without prior knowledge of the transmitted signal. We evaluate its performance across various modulation schemes and subcarrier numbers. Simulation results show that our method achieves a modulation detection accuracy exceeding $80\%$ at an SNR of $10$ dB and $95\%$ at an SNR of $25$ dB.