English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Many deep learning-based computerized respiratory sound analysis methods havepreviously been developed. However, these studies focus on either lung soundonly or tracheal sound only. The effectiveness of using a lung sound analysisalgorithm on tracheal sound and vice versa has never been investigated.Furthermore, no one knows whether using lung and tracheal sounds together intraining a respiratory sound analysis model is beneficial. In this study, wefirst constructed a tracheal sound database, HF_Tracheal_V1, containing 1044815-s tracheal sound recordings, 21741 inhalation labels, 15858 exhalationlabels, and 6414 continuous adventitious sound (CAS) labels. HF_Tracheal_V1 andour previously built lung sound database, HF_Lung_V2, were either combined(mixed set), used one after the other (domain adaptation), or used alone totrain convolutional neural network bidirectional gate recurrent unit models forinhalation, exhalation, and CAS detection in lung and tracheal sounds. Theresults revealed that the models trained using lung sound alone performedpoorly in tracheal sound analysis and vice versa. However, mixed set trainingor domain adaptation improved the performance for 1) inhalation and exhalationdetection in lung sounds and 2) inhalation, exhalation, and CAS detection intracheal sounds compared to positive controls (the models trained using lungsound alone and used in lung sound analysis and vice versa). In particular, themodel trained on the mixed set had great flexibility to serve two purposes,lung and tracheal sound analyses, at the same time.

A Dual-Purpose Deep Learning Model for Auscultated Lung and Tracheal Sound Analysis Based on Mixed Set Training