FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288069892> ?p ?o ?g. }

• W4288069892 endingPage "109539" @default.
• W4288069892 startingPage "109539" @default.
• W4288069892 abstract "Alongside the currently used nasal swab testing, the COVID-19 pandemic situation would gain noticeable advantages from low-cost tests that are available at any-time, anywhere, at a large-scale, and with real time answers. A novel approach for COVID-19 assessment is adopted here, discriminating negative subjects versus positive or recovered subjects. The scope is to identify potential discriminating features, highlight mid and short-term effects of COVID on the voice and compare two custom algorithms. A pool of 310 subjects took part in the study; recordings were collected in a low-noise, controlled setting employing three different vocal tasks. Binary classifications followed, using two different custom algorithms. The first was based on the coupling of boosting and bagging, with an AdaBoost classifier using Random Forest learners. A feature selection process was employed for the training, identifying a subset of features acting as clinically relevant biomarkers. The other approach was centered on two custom CNN architectures applied to mel-Spectrograms, with a custom knowledge-based data augmentation. Performances, evaluated on an independent test set, were comparable: Adaboost and CNN differentiated COVID-19 positive from negative with accuracies of 100% and 95% respectively, and recovered from negative individuals with accuracies of 86.1% and 75% respectively. This study highlights the possibility to identify COVID-19 positive subjects, foreseeing a tool for on-site screening, while also considering recovered subjects and the effects of COVID-19 on the voice. The two proposed novel architectures allow for the identification of biomarkers and demonstrate the ongoing relevance of traditional ML versus deep learning in speech analysis." @default.
• W4288069892 created "2022-07-28" @default.
• W4288069892 creator A5011788367 @default.
• W4288069892 creator A5012383192 @default.
• W4288069892 creator A5021959535 @default.
• W4288069892 creator A5022210828 @default.
• W4288069892 creator A5036706048 @default.
• W4288069892 creator A5040705226 @default.
• W4288069892 creator A5041843332 @default.
• W4288069892 creator A5056031186 @default.
• W4288069892 creator A5065382094 @default.
• W4288069892 creator A5068946724 @default.
• W4288069892 creator A5076711012 @default.
• W4288069892 creator A5077110521 @default.
• W4288069892 creator A5086277183 @default.
• W4288069892 date "2022-10-01" @default.
• W4288069892 modified "2023-10-18" @default.
• W4288069892 title "Deep learning and machine learning-based voice analysis for the detection of COVID-19: A proposal and comparison of architectures" @default.
• W4288069892 cites W1533546067 @default.
• W4288069892 cites W1847247712 @default.
• W4288069892 cites W1985066527 @default.
• W4288069892 cites W2017991720 @default.
• W4288069892 cites W2020746066 @default.
• W4288069892 cites W2038428786 @default.
• W4288069892 cites W2082285307 @default.
• W4288069892 cites W2085662862 @default.
• W4288069892 cites W2126401726 @default.
• W4288069892 cites W2131822572 @default.
• W4288069892 cites W2137075158 @default.
• W4288069892 cites W2159875381 @default.
• W4288069892 cites W2311523351 @default.
• W4288069892 cites W2749315055 @default.
• W4288069892 cites W2753916199 @default.
• W4288069892 cites W2767951468 @default.
• W4288069892 cites W2885806496 @default.
• W4288069892 cites W2911964244 @default.
• W4288069892 cites W2936774411 @default.
• W4288069892 cites W2947527390 @default.
• W4288069892 cites W2986037570 @default.
• W4288069892 cites W3003236386 @default.
• W4288069892 cites W3009565263 @default.
• W4288069892 cites W3011311796 @default.
• W4288069892 cites W3011452997 @default.
• W4288069892 cites W3048326119 @default.
• W4288069892 cites W3083029291 @default.
• W4288069892 cites W3084240052 @default.
• W4288069892 cites W3089168043 @default.
• W4288069892 cites W3091468319 @default.
• W4288069892 cites W3092203860 @default.
• W4288069892 cites W3105837102 @default.
• W4288069892 cites W3109783949 @default.
• W4288069892 cites W3127549753 @default.
• W4288069892 cites W3128508004 @default.
• W4288069892 cites W3129517450 @default.
• W4288069892 cites W3133317121 @default.
• W4288069892 cites W3152844745 @default.
• W4288069892 cites W3173449808 @default.
• W4288069892 cites W3204369928 @default.
• W4288069892 cites W3205790296 @default.
• W4288069892 cites W3211729376 @default.
• W4288069892 cites W3216450352 @default.
• W4288069892 cites W4239510810 @default.
• W4288069892 cites W4247571494 @default.
• W4288069892 doi "https://doi.org/10.1016/j.knosys.2022.109539" @default.
• W4288069892 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35915642" @default.
• W4288069892 hasPublicationYear "2022" @default.
• W4288069892 type Work @default.
• W4288069892 citedByCount "13" @default.
• W4288069892 countsByYear W42880698922023 @default.
• W4288069892 crossrefType "journal-article" @default.
• W4288069892 hasAuthorship W4288069892A5011788367 @default.
• W4288069892 hasAuthorship W4288069892A5012383192 @default.
• W4288069892 hasAuthorship W4288069892A5021959535 @default.
• W4288069892 hasAuthorship W4288069892A5022210828 @default.
• W4288069892 hasAuthorship W4288069892A5036706048 @default.
• W4288069892 hasAuthorship W4288069892A5040705226 @default.
• W4288069892 hasAuthorship W4288069892A5041843332 @default.
• W4288069892 hasAuthorship W4288069892A5056031186 @default.
• W4288069892 hasAuthorship W4288069892A5065382094 @default.
• W4288069892 hasAuthorship W4288069892A5068946724 @default.
• W4288069892 hasAuthorship W4288069892A5076711012 @default.
• W4288069892 hasAuthorship W4288069892A5077110521 @default.
• W4288069892 hasAuthorship W4288069892A5086277183 @default.
• W4288069892 hasBestOaLocation W42880698922 @default.
• W4288069892 hasConcept C119857082 @default.
• W4288069892 hasConcept C12267149 @default.
• W4288069892 hasConcept C141404830 @default.
• W4288069892 hasConcept C142724271 @default.
• W4288069892 hasConcept C148483581 @default.
• W4288069892 hasConcept C153180895 @default.
• W4288069892 hasConcept C154945302 @default.
• W4288069892 hasConcept C169258074 @default.
• W4288069892 hasConcept C169903167 @default.
• W4288069892 hasConcept C2779134260 @default.
• W4288069892 hasConcept C28490314 @default.
• W4288069892 hasConcept C3008058167 @default.
• W4288069892 hasConcept C41008148 @default.
• W4288069892 hasConcept C46686674 @default.

• next