Bioacoustic signal analysis through complex network features

The paper proposes a graph-theoretical approach to auscultation, bringing out the potential of graph features in classifying the bioacoustics signals. The complex network analysis of the bioacoustics signals -vesicular (VE) and bronchial (BR) breath sound -of 48 healthy persons are carried out for understanding the airflow dynamics during respiration. The VE and BR are classified by the machine learning techniques extracting the graph features - the number of edges (E), graph density (D), transitivity (T), degree centrality (D-cg) and eigenvector centrality (E-cg). The higher value of E, D, and T in BR indicates the temporally correlated airflow through the wider tracheobronchial tract resulting in sustained high-intense low-frequencies. The frequency spread and high-frequencies in VE, arising due to the less correlated airflow through the narrow segmental bronchi and lobar, appears as a lower value for E, D, and T. The lower values of D-cg and E-cg justify the inferences from the spectral and other graph parameters. The study proposes a methodology in remote auscultation that can be employed in the current scenario of COVID-19.

Automated summary

This paper proposes a graph-theoretical approach to auscultation, using graph features in classifying bioacoustics signals. The airflow dynamics during respiration were studied through complex network analysis of 48 healthy individuals' vesicular (VE) and bronchial (BR) breath sounds. Machine learning techniques were used to classify VE and BR by extracting graph features, such as the number of edges, graph density, transitivity, degree centrality, and eigenvector centrality. The results showed that higher values of certain graph features in BR indicated temporally correlated airflow through wider tracheobronchial tracts, resulting in sustained high-intense low-frequencies. On the other hand, lower values of these graph features in VE suggested less correlated airflow through narrow bronchi and lobes, leading to a higher frequency spread and high-frequencies. The study also proposed a methodology for remote auscultation that is applicable in the current scenario of COVID-19.