Interference Mitigation using U-Net Autoencoder based system

TL;DR

This paper introduces a U-Net autoencoder framework that effectively mitigates various interference types in communication signals, outperforming traditional methods especially in low to mid SIR conditions.

Contribution

The paper presents a novel U-Net-based autoencoder architecture tailored for interference mitigation in diverse communication scenarios, demonstrating superior performance over conventional techniques.

Findings

Outperforms traditional interference cancellation methods in low- and mid-SIR regimes.

Effectively handles diverse interference types including sinusoidal, chirp, and modulated signals.

Maintains robustness under model mismatch conditions like carrier offset and colored noise.

Abstract

This paper proposes a U-Net-based autoencoder framework for mitigating interference in communication signals corrupted by noise and diverse interference sources. The approach targets scenarios involving both signal-plus-noise and signal-plus-interference-plus-noise mixtures, including sinusoidal interferers, LFM chirps, QPSK interferers with different sampling rates, and modulated interference such as QAM. The U-Net architecture leverages multiscale feature extraction and skip connections to preserve fine-grained temporal structure while suppressing interference components. Performance is evaluated using bit error rate and compared against conventional cancellation methods. Results show that the proposed method consistently outperforms traditional techniques in low- and mid-SIR regimes, while remaining competitive at high SIRs. Additional experiments examine the autoencoder's behavior under model mismatch conditions such as carrier offset and colored noise. The study demonstrates that multiscale neural architectures provide a flexible and effective platform for interference mitigation across a wide range of interference types.