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

This paper proposes a novel framework for lung sound event detection,segmenting continuous lung sound recordings into discrete events and performingrecognition on each event. Exploiting the lightweight nature of TemporalConvolution Networks (TCNs) and their superior results compared to theirrecurrent counterparts, we propose a lightweight, yet robust, and completelyinterpretable framework for lung sound event detection. We propose the use of amulti-branch TCN architecture and exploit a novel fusion strategy to combinethe resultant features from these branches. This not only allows the network toretain the most salient information across different temporal granularities anddisregards irrelevant information, but also allows our network to processrecordings of arbitrary length. Results: The proposed method is evaluated onmultiple public and in-house benchmarks of irregular and noisy recordings ofthe respiratory auscultation process for the identification of numerousauscultation events including inhalation, exhalation, crackles, wheeze,stridor, and rhonchi. We exceed the state-of-the-art results in allevaluations. Furthermore, we empirically analyse the effect of the proposedmulti-branch TCN architecture and the feature fusion strategy and providequantitative and qualitative evaluations to illustrate their efficiency.Moreover, we provide an end-to-end model interpretation pipeline thatinterprets the operations of all the components of the proposed framework. Ouranalysis of different feature fusion strategies shows that the proposed featureconcatenation method leads to better suppression of non-informative features,which drastically reduces the classifier overhead resulting in a robustlightweight network.The lightweight nature of our model allows it to bedeployed in end-user devices such as smartphones, and it has the ability togenerate predictions in real-time.

Robust and Interpretable Temporal Convolution Network for Event Detection in Lung Sound Recordings