Source detection via multi-label classification

TL;DR

This paper introduces deep learning-based multi-label classification methods, CNNDetector and RadioNet, for improved radio source detection in challenging conditions, outperforming traditional algorithms especially with correlated signals and low SINR.

Contribution

It reformulates source detection as a multi-class classification problem using CNNs, including novel preprocessing and benchmarking against conventional methods.

Findings

RadioNet resolves the number of uncorrelated sources with correlated paths.

Deep learning models outperform traditional algorithms in low SINR conditions.

Extensive evaluations demonstrate the efficacy of the proposed methods.

Abstract

Radio source detection through conventional algorithms has been unreliable when trying to solve for large number of sources in the presence of low SINR and less number of snapshots. We address this by reformulating source detection as a multi-class classification problem solved using deep learning frameworks. Incoming waveforms are sampled using a centrosymmetric linear array with omni-directional elements and the normalized upper triangle of the autocorrelation matrix is extracted as the input feature to a modified convolutional neural network with uni-dimensional filters, trained to detect the sources in the presence of both uncorrelated and correlated signals. Two detection algorithms are introduced and referred to as CNNDetector and RadioNet, and subsequently benchmarked against the conventional source detection algorithms. By including preprocessing in forward backward spatial smoothing, RadioNet can also resolve the number of uncorrelated sources in the presence of correlated paths. Finally, the algorithms are stress tested under challenging operational conditions and extensive evaluations are presented showing the efficacy and contributions of the introduced predictive models.