Interference Mitigation using U-Net Autoencoder based system

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.

On the Ability of Deep Learning to Detect Signals with Unknown Parameters

In many signal processing applications, including communications, sonar, radar, and localization, a fundamental problem is the detection of a signal of interest in background noise, known as signal detection [1] [2]. A simple version of this problem is the detection of a signal of interest with unknown parameters in Additive White Gaussian Noise (AWGN). When the parameters defining the signal are not known, an optimal detector (in the Neyman-Pearson sense) does not exist. An upper bound on the performance of any detector is the matched filter, which implies perfect sample by sample knowledge of the signal of interest. In recent years Deep Neural Networks (DNNs) have proven to be very effective at hypothesis testing problems such as object detection and image classification. This paper examines the application of DNN-based approaches to the signal detection problem at the raw I/Q level and compares them to statistically based approaches as well as the Matched Filter. These methods aim to maximize the Probability of Detection Pd while maintaining a constant Probability of False Alarm PF A. Two Machine Learning (ML) algorithms are trained and assessed on this signal detection problem, across three signal of interest models. A model was also trained on a unified dataset and assessed across all signals of interest.

Interference Mitigation Recommender System using U-Net Autoencoders

Building on the previous work on interference mitigation, this paper introduces a modular recommender system that automatically selects the most effective interference mitigation strategy based on the interference characteristics present in the received signal. The system integrates three key stages: an SPS classifier module, a SIR predictor, and a bank of specialized U-Net autoencoders designed for different interference conditions. The classification block identifies the parameters required for cancellation. The recommender then directs the signal to the appropriate mitigation model, optionally incorporating SIR-based decisions for scenarios where successive interference cancellation may be advantageous. Experiments conducted across diverse SIR levels and modulation environments show that the recommender strategy improves robustness and reduces BER compared to using any single mitigation method alone. The results demonstrate the potential of adaptive, model-selective architectures to enhance interference resilience in dynamic communication environments.