An ambient denoising method based on multi-channel non-negative matrix factorization for wheezing detection

TL;DR

This paper introduces a multi-channel non-negative matrix factorization method with parallel computing and SVD initialization for effective wheezing detection in noisy auscultation recordings, achieving improved accuracy and speed.

Contribution

It presents a novel NMF-based denoising and wheezing detection system with orthogonal constraints, SVD initialization, and parallel processing for real-time application.

Findings

Significant improvement over existing algorithms in noisy conditions

Achieves fast execution suitable for real-world use

Effective source separation and denoising demonstrated

Abstract

In this paper, a parallel computing method is proposed to perform the background denoising and wheezing detection from a multi-channel recording captured during the auscultation process. The proposed system is based on a non-negative matrix factorization (NMF) approach and a detection strategy. Moreover, the initialization of the proposed model is based on singular value decomposition to avoid dependence on the initial values of the NMF parameters. Additionally, novel update rules to simultaneously address the multichannel denoising while preserving an orthogonal constraint to maximize source separation have been designed. The proposed system has been evaluated for the task of wheezing detection showing a significant improvement over state-of-the-art algorithms when noisy sound sources are present. Moreover, parallel and high-performance techniques have been used to speedup the execution of the proposed system, showing that it is possible to achieve fast execution times, which enables its implementation in real-world scenarios.