Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036692032> ?p ?o ?g. }
- W3036692032 endingPage "075009" @default.
- W3036692032 startingPage "075009" @default.
- W3036692032 abstract "Objective Polysomnography is typically used to evaluate the severity of obstructive sleep apnea (OSA) but the inconvenience of application and high cost considerably affect the diagnostics. In this study, sleep sound signals are used to detect OSA in patients. Approach A deep feature transfer-based OSA detection approach is proposed. First, a deep convolutional neural network is trained on large-scale labeled audio data sets to distinguish respiration sounds from environmental noise. Second, the trained model is transferred to recognize respiration sounds in sleep sound signals. Third, the deep features of the detected respiration sounds are used to train a logistic regression classifier to identify OSA patients from potential patients. Polysomnography-based diagnosis is used as a reference. Main results A self-collected data set of 132 potential OSA patients is applied in OSA detection experiments. The OSA detection performances are tested on four models for different apnea-hypopnea index thresholds and sexes resulting in accuracies of 80.17%, 80.21%, 81.63% and 77.22%. The corresponding areas under the receiver operating characteristic curves are 0.82, 0.80, 0.81 and 0.79. In addition, the proposed method presented a significant performance improvement compared with the state-of-the-art methods. Significance Big data, deep learning and transfer learning can be successfully applied to improve diagnostic accuracy in OSA detection. The performance of the proposed approach is superior to that of traditional audio analysis technology. The proposed method significantly reduces difficulties in OSA detection and diagnosis, such that potential OSA patients can perform initial inspections by themselves at home." @default.
- W3036692032 created "2020-06-25" @default.
- W3036692032 creator A5004798984 @default.
- W3036692032 creator A5011508278 @default.
- W3036692032 creator A5019046203 @default.
- W3036692032 creator A5067875175 @default.
- W3036692032 creator A5072734170 @default.
- W3036692032 creator A5073391035 @default.
- W3036692032 creator A5079273968 @default.
- W3036692032 creator A5081829786 @default.
- W3036692032 date "2020-08-11" @default.
- W3036692032 modified "2023-10-02" @default.
- W3036692032 title "A novel deep feature transfer-based OSA detection method using sleep sound signals" @default.
- W3036692032 cites W1983923137 @default.
- W3036692032 cites W1990729619 @default.
- W3036692032 cites W2005821165 @default.
- W3036692032 cites W2019885025 @default.
- W3036692032 cites W2050752817 @default.
- W3036692032 cites W2052666245 @default.
- W3036692032 cites W2072600526 @default.
- W3036692032 cites W2077410237 @default.
- W3036692032 cites W2093989429 @default.
- W3036692032 cites W2106441083 @default.
- W3036692032 cites W2144194006 @default.
- W3036692032 cites W2165922113 @default.
- W3036692032 cites W2264784497 @default.
- W3036692032 cites W2344913923 @default.
- W3036692032 cites W2417718698 @default.
- W3036692032 cites W2593116425 @default.
- W3036692032 cites W2754562816 @default.
- W3036692032 cites W2765947969 @default.
- W3036692032 cites W2775019026 @default.
- W3036692032 cites W2787964244 @default.
- W3036692032 cites W2805585262 @default.
- W3036692032 cites W2962910554 @default.
- W3036692032 cites W3002414538 @default.
- W3036692032 cites W36564834 @default.
- W3036692032 cites W4243006922 @default.
- W3036692032 cites W4294830572 @default.
- W3036692032 doi "https://doi.org/10.1088/1361-6579/ab9e7b" @default.
- W3036692032 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32559754" @default.
- W3036692032 hasPublicationYear "2020" @default.
- W3036692032 type Work @default.
- W3036692032 sameAs 3036692032 @default.
- W3036692032 citedByCount "9" @default.
- W3036692032 countsByYear W30366920322021 @default.
- W3036692032 countsByYear W30366920322022 @default.
- W3036692032 countsByYear W30366920322023 @default.
- W3036692032 crossrefType "journal-article" @default.
- W3036692032 hasAuthorship W3036692032A5004798984 @default.
- W3036692032 hasAuthorship W3036692032A5011508278 @default.
- W3036692032 hasAuthorship W3036692032A5019046203 @default.
- W3036692032 hasAuthorship W3036692032A5067875175 @default.
- W3036692032 hasAuthorship W3036692032A5072734170 @default.
- W3036692032 hasAuthorship W3036692032A5073391035 @default.
- W3036692032 hasAuthorship W3036692032A5079273968 @default.
- W3036692032 hasAuthorship W3036692032A5081829786 @default.
- W3036692032 hasConcept C111919701 @default.
- W3036692032 hasConcept C121332964 @default.
- W3036692032 hasConcept C138885662 @default.
- W3036692032 hasConcept C150899416 @default.
- W3036692032 hasConcept C153180895 @default.
- W3036692032 hasConcept C154945302 @default.
- W3036692032 hasConcept C203718221 @default.
- W3036692032 hasConcept C24890656 @default.
- W3036692032 hasConcept C2775841894 @default.
- W3036692032 hasConcept C2776401178 @default.
- W3036692032 hasConcept C28490314 @default.
- W3036692032 hasConcept C41008148 @default.
- W3036692032 hasConcept C41895202 @default.
- W3036692032 hasConceptScore W3036692032C111919701 @default.
- W3036692032 hasConceptScore W3036692032C121332964 @default.
- W3036692032 hasConceptScore W3036692032C138885662 @default.
- W3036692032 hasConceptScore W3036692032C150899416 @default.
- W3036692032 hasConceptScore W3036692032C153180895 @default.
- W3036692032 hasConceptScore W3036692032C154945302 @default.
- W3036692032 hasConceptScore W3036692032C203718221 @default.
- W3036692032 hasConceptScore W3036692032C24890656 @default.
- W3036692032 hasConceptScore W3036692032C2775841894 @default.
- W3036692032 hasConceptScore W3036692032C2776401178 @default.
- W3036692032 hasConceptScore W3036692032C28490314 @default.
- W3036692032 hasConceptScore W3036692032C41008148 @default.
- W3036692032 hasConceptScore W3036692032C41895202 @default.
- W3036692032 hasFunder F4320321001 @default.
- W3036692032 hasIssue "7" @default.
- W3036692032 hasLocation W30366920321 @default.
- W3036692032 hasOpenAccess W3036692032 @default.
- W3036692032 hasPrimaryLocation W30366920321 @default.
- W3036692032 hasRelatedWork W2033914206 @default.
- W3036692032 hasRelatedWork W2146076056 @default.
- W3036692032 hasRelatedWork W2163831990 @default.
- W3036692032 hasRelatedWork W2368779261 @default.
- W3036692032 hasRelatedWork W2382607599 @default.
- W3036692032 hasRelatedWork W2546942002 @default.
- W3036692032 hasRelatedWork W2889705046 @default.
- W3036692032 hasRelatedWork W2970216048 @default.
- W3036692032 hasRelatedWork W3003836766 @default.
- W3036692032 hasRelatedWork W4211182446 @default.