Source Separation of the Second Heart Sound via Alternating Optimization

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2021

Autores

Renna, F (Autor) FCUP; Plumbley, MD (Autor) Outra; Coimbra, M (Autor) FCUP

Ata de Conferência Internacional

Título: 2021 COMPUTING IN CARDIOLOGY (CINC)

Páginas: 1-4

Conference on Computing in Cardiology (CinC)

Brno, CZECH REPUBLIC, SEP 12-15, 2021

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 1 Citação

Outras Informações

ID Authenticus: P-00V-ZNP

DOI: 10.22489/cinc.2021.052

Abstract (EN): A novel algorithm to separate S2 heart sounds into their aortic and pulmonary components is proposed. This approach is based on the assumption that, in different heartbeats of a given recording, aortic and pulmonary components maintain the same waveform but with different relative delays, which are induced by the variation of the thoracic pressure at different respiration phases. The proposed algorithm then retrieves the aortic and pulmonary components as the solution of an optimization problem which is approximated via alternating optimization. The proposed approach is shown to provide reconstructions of aortic and pulmonary components with normalized root mean-squared error consistently below 10% in various operational regimes.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 4