Repository logo
 
Publication

COVID-19 activity screening by a smart-data-driven multi-band voice analysis

dc.contributor.authorSilva, Gabriel
dc.contributor.authorBatista, Patrícia
dc.contributor.authorRodrigues, Pedro Miguel
dc.date.accessioned2023-07-10T09:33:25Z
dc.date.available2023-07-10T09:33:25Z
dc.date.issued2022-11-15
dc.description.abstractCOVID-19 is a disease caused by the new coronavirus SARS-COV-2 which can lead to severe respiratory infections. Since its first detection it caused more than six million worldwide deaths. COVID-19 diagnosis non-invasive and low-cost methods with faster and accurate results are still needed for a fast disease control. In this research, 3 different signal analyses have been applied (per broadband, per sub-bands and per broadband & sub-bands) to Cough, Breathing & Speech signals of Coswara dataset to extract non-linear patterns (Energy, Entropies, Correlation Dimension, Detrended Fluctuation Analysis, Lyapunov Exponent & Fractal Dimensions) for feeding a XGBoost classifier to discriminate COVID-19 activity on its different stages. Classification accuracies ranged between 83.33% and 98.46% have been achieved, surpassing the state-of-art methods in some comparisons. It should be empathized the 98.46% of accuracy reached on pair Healthy Controls vs all COVID-19 stages. The results shows that the method may be adequate for COVID-19 diagnosis screening assistance.pt_PT
dc.description.versioninfo:eu-repo/semantics/acceptedVersionpt_PT
dc.identifier.doi10.1016/j.jvoice.2022.11.008pt_PT
dc.identifier.eid85143292554
dc.identifier.issn0892-1997
dc.identifier.pmcPMC9663738
dc.identifier.pmid36464573
dc.identifier.urihttp://hdl.handle.net/10400.14/41625
dc.identifier.wos001494077600001
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/pt_PT
dc.subjectBreathingpt_PT
dc.subjectClassificationpt_PT
dc.subjectCoughpt_PT
dc.subjectCOVID-19pt_PT
dc.subjectNon-linear patternspt_PT
dc.subjectSpeech signalspt_PT
dc.titleCOVID-19 activity screening by a smart-data-driven multi-band voice analysispt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.titleJournal of Voicept_PT
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
58446914.pdf
Size:
637.24 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.44 KB
Format:
Item-specific license agreed upon to submission
Description: