Signal Clustering with Class-independent Segmentation

TL;DR

This paper introduces a novel deep learning approach that encodes radar signals into images and applies image segmentation techniques for class-independent signal clustering, improving source separation in complex signals.

Contribution

It presents the first method to combine image segmentation with deep learning for radar signal clustering, introducing new loss functions for optimized neural network training.

Findings

Outperforms traditional clustering baselines

Capable of end-to-end clustering of radar signals

Effective in separating complex, concurrent signals

Abstract

Radar signals have been dramatically increasing in complexity, limiting the source separation ability of traditional approaches. In this paper we propose a Deep Learning-based clustering method, which encodes concurrent signals into images, and, for the first time, tackles clustering with image segmentation. Novel loss functions are introduced to optimize a Neural Network to separate the input pulses into pure and non-fragmented clusters. Outperforming a variety of baselines, the proposed approach is capable of clustering inputs directly with a Neural Network, in an end-to-end fashion.