Learning sparse structures for physics-inspired compressed sensing

TL;DR

This paper introduces a novel structured sparsity model using restricted Boltzmann machines for improved estimation of modal wavenumbers in underwater acoustics, enhancing broadband source analysis.

Contribution

It proposes a new deep Bayesian network-based approach for structured sparsity in compressed sensing, tailored for underwater acoustic signal processing.

Findings

Efficient learning of the model on simulated data.

Improved estimation of wavenumbers across frequencies.

Enhanced understanding of underwater propagation environments.

Abstract

In underwater acoustics, shallow water environments act as modal dispersive waveguides when considering low-frequency sources. In this context, propagating signals can be described as a sum of few modal components, each of them propagating according to its own wavenumber. Estimating these wavenumbers is of key interest to understand the propagating environment as well as the emitting source. To solve this problem, we proposed recently a Bayesian approach exploiting a sparsity-inforcing prior. When dealing with broadband sources, this model can be further improved by integrating the particular dependence linking the wavenumbers from one frequency to the other. In this contribution, we propose to resort to a new approach relying on a restricted Boltzmann machine, exploited as a generic structured sparsity-inforcing model. This model, derived from deep Bayesian networks, can indeed be efficiently learned on physically realistic simulated data using well-known and proven algorithms.