COVID-19 Diagnosis at early stage Based on smartwatches and machine learning Techniques

Simple item page
dc.contributor.authorSkibiƄska, Justynacs
dc.contributor.authorBurget, Radimcs
dc.contributor.authorChanna, Asmacs
dc.contributor.authorPopescu, Nirvanacs
dc.contributor.authorKoucheryavy, Yevgenics
dc.coverage.issue1cs
dc.coverage.volume9cs
dc.date.issued2021-08-07cs
dc.description.abstractEarly detection of COVID-19 positive people are now extremely needed and considered to be one of the most effective ways how to limit spreading the infection. Commonly used screening methods are reverse transcription polymerase chain reaction (RT-PCR) or antigen tests, which need to be periodically repeated. This paper proposes a methodology for detecting the disease in non-invasive way using wearable devices and for the analysis of bio-markers using artificial intelligence. This paper have reused a publicly available dataset containing COVID-19, influenza, and Healthy control data. In total 27 COVID-19 positive and 27 healthy control were pre-selected for the experiment, and several feature extraction methods were applied to the data. This paper have experimented with several machine learning methods, such as XGBoost, k-nearest neighbour k-NN, support vector machine, logistic regression, decision tree, and random forest, and statistically evaluated their perfomance using various metrics, including accuracy, sensitivity and specificity. The proposed experiment reached 78% accuracy using the k-NN algorithm which is significantly higher than reported for state-of-the-art methods. For the cohort containing influenza, the accuracy was 73 % for k-NN. Additionally, we identified the most relevant features that could indicate the changes between the healthy and infected state. The proposed methodology can complement the existing RT-PCR or antigen screening tests, and it can help to limit the spreading of the viral diseases, not only COVID-19, in the non-invasive way.en
dc.formattextcs
dc.format.extent119476-119491cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationIEEE Access. 2021, vol. 9, issue 1, p. 119476-119491.en
dc.identifier.doi10.1109/ACCESS.2021.3106255cs
dc.identifier.issn2169-3536cs
dc.identifier.orcid0000-0002-8531-3393cs
dc.identifier.orcid0000-0003-1849-5390cs
dc.identifier.other172256cs
dc.identifier.scopus23011250200cs
dc.identifier.urihttp://hdl.handle.net/11012/203104
dc.language.isoencs
dc.publisherIEEEcs
dc.relation.ispartofIEEE Accesscs
dc.relation.urihttps://ieeexplore.ieee.org/document/9517046cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/2169-3536/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectartificial intelligenceen
dc.subjectCOVIDen
dc.subjectsingal processingen
dc.titleCOVID-19 Diagnosis at early stage Based on smartwatches and machine learning Techniquesen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-172256en
sync.item.dbtypeVAVen
sync.item.insts2024.03.06 11:45:49en
sync.item.modts2024.03.06 11:13:53en
thesis.grantorVysokĂ© učenĂ­ technickĂ© v Brně. Fakulta elektrotechniky a komunikačnĂ­ch technologiĂ­. Ústav telekomunikacĂ­cs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
3106255.pdf
Size:
2.17 MB
Format:
Adobe Portable Document Format
Description:
3106255.pdf
Download
Collections
Ústav telekomunikací