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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper presents a deep learning system applied for detecting anomaliesfrom respiratory sound recordings. Initially, our system begins with audiofeature extraction using Gammatone and Continuous Wavelet transformation. Thisstep aims to transform the respiratory sound input into a two-dimensionalspectrogram where both spectral and temporal features are presented. Then, ourproposed system integrates Inception-residual-based backbone models combinedwith multi-head attention and multi-objective loss to classify respiratoryanomalies. Instead of applying a simple concatenation approach by combiningresults from various spectrograms, we propose a Linear combination, which hasthe ability to regulate equally the contribution of each individual spectrogramthroughout the training process. To evaluate the performance, we conductedexperiments over the benchmark dataset of SPRSound (The Open-Source SJTUPaediatric Respiratory Sound) proposed by the IEEE BioCAS 2022 challenge. Asregards the Score computed by an average between the average score and harmonicscore, our proposed system gained significant improvements of 9.7%, 15.8%,17.8%, and 16.1% in Task 1-1, Task 1-2, Task 2-1, and Task 2-2, respectively,compared to the challenge baseline system. Notably, we achieved the Top-1performance in Task 2-1 and Task 2-2 with the highest Score of 74.5% and 53.9%,respectively.

An Inception-Residual-Based Architecture with Multi-Objective Loss for Detecting Respiratory Anomalies