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/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

i Respiratory sounds (RSs) auscultation using stethoscope is often the first noninvasive resource available to physicians for the detection and analysis of respiratory ailments. Motivated by the subjectivity of human auditory system, computerized auscultation combined with signal processing techniques have boosted the diagnostic capabilities of RS. This PhD thesis concentrates on the advanced signals processing methods for RS analysis from several aspects including: RS denoising by means of heart sounds (HSs) cancellation (Part I), respiratory phase detection (Part II), as well as RS analysis and feature extraction methods for RS classification (Part III). Part I solves the problem of HS cancellation through a two-steps scheme consisting of HS localization and HS removal from different types of single-channel RS recordings. HS contaminated segments have been localized by introducing a wavelet based localization scheme. A detection function based on multiscale decomposition is calculated and HS segments in the noisy RS signal are localized based on the cumulative sums of likelihood ratios capturing the dynamic behaviour of the signal. HS removal from RS is then addressed by proposing a novel semi-blind single-channel source extraction algorithm which incorporates the filter banks and template based matching using FIR filters. It has shown that the proposed methods are successful attempts to solve the clinical application challenge faced by the existing HS cancellation methods in terms of respiratory ailments. In Part II, the problem of noninvasive automatic respiratory rate monitoring by acoustical means is addressed first. Respiratory phase segmentation is then formulated as an optimization problem and the boundaries of the respiratory phase segments are ATTENTION: The Singapore Copyright Act applies to the use of this document. Nanyang Technological University Library

Advanced signal processing methods for analysis of respiratory sounds