Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315694925> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4315694925 abstract "Coughing is a common symptom of respiratory diseases and past works have used the audio and acoustic properties of coughs to detect those diseases. In this study, we propose a new NLP-style cough embedding technique which is the characterisation of the cough signal as a binary sequence preserving temporal information, and show how this not only allows the discrimination between coughing by tuberculosis (TB) patients and those with other respiratory ailments, but even outperforms more traditional spectral audio features. We have used the vocal audio recordings gathered from 15 TB and 33 non-TB patients, who suffer from other lung diseases. In total, almost 2 hours of cough embeddings were used as feature vectors to train and evaluate four shallow (LR, SVM, KNN, MLP) and two deep architectures (CNN, LSTM) using nested cross-validation. We have also experimentally extracted MFCC, ZCR and kurtosis from the same audio recordings preserving cough patterns and used these to train the classifiers. The results show that an LSTM trained on the cough embeddings achieved the highest AUC of 0.81. When using the audio features, a CNN performed the best by producing the highest AUC of 0.72. We show that detecting TB using cough embeddings preserves privacy and is possible due to the unique temporal cough patterns between TB and non-TB patients. It can also be fused as an additional tool to improve the TB cough audio classification task." @default.
- W4315694925 created "2023-01-12" @default.
- W4315694925 creator A5029466845 @default.
- W4315694925 creator A5050849172 @default.
- W4315694925 creator A5077397137 @default.
- W4315694925 date "2022-10-27" @default.
- W4315694925 modified "2023-09-27" @default.
- W4315694925 title "Automatic Tuberculosis detection in cough patterns using NLP-style cough embeddings" @default.
- W4315694925 cites W1517164593 @default.
- W4315694925 cites W1523608467 @default.
- W4315694925 cites W1992109923 @default.
- W4315694925 cites W2024134733 @default.
- W4315694925 cites W2064675550 @default.
- W4315694925 cites W2135291856 @default.
- W4315694925 cites W2148143831 @default.
- W4315694925 cites W2158698691 @default.
- W4315694925 cites W2510867062 @default.
- W4315694925 cites W2617241599 @default.
- W4315694925 cites W2618530766 @default.
- W4315694925 cites W2755421148 @default.
- W4315694925 cites W2791133433 @default.
- W4315694925 cites W2794376461 @default.
- W4315694925 cites W2797817943 @default.
- W4315694925 cites W2913997948 @default.
- W4315694925 cites W2963353005 @default.
- W4315694925 cites W2963923670 @default.
- W4315694925 cites W2979298088 @default.
- W4315694925 cites W3012342680 @default.
- W4315694925 cites W3109783949 @default.
- W4315694925 cites W3119753638 @default.
- W4315694925 cites W3126537460 @default.
- W4315694925 cites W3131057326 @default.
- W4315694925 cites W3193775699 @default.
- W4315694925 cites W3198066218 @default.
- W4315694925 cites W3204707456 @default.
- W4315694925 cites W3206247858 @default.
- W4315694925 cites W3207167009 @default.
- W4315694925 cites W4280533310 @default.
- W4315694925 cites W947140380 @default.
- W4315694925 doi "https://doi.org/10.1109/iceet56468.2022.10007261" @default.
- W4315694925 hasPublicationYear "2022" @default.
- W4315694925 type Work @default.
- W4315694925 citedByCount "0" @default.
- W4315694925 crossrefType "proceedings-article" @default.
- W4315694925 hasAuthorship W4315694925A5029466845 @default.
- W4315694925 hasAuthorship W4315694925A5050849172 @default.
- W4315694925 hasAuthorship W4315694925A5077397137 @default.
- W4315694925 hasConcept C12267149 @default.
- W4315694925 hasConcept C138885662 @default.
- W4315694925 hasConcept C13895895 @default.
- W4315694925 hasConcept C151989614 @default.
- W4315694925 hasConcept C153180895 @default.
- W4315694925 hasConcept C154945302 @default.
- W4315694925 hasConcept C2776401178 @default.
- W4315694925 hasConcept C28490314 @default.
- W4315694925 hasConcept C41008148 @default.
- W4315694925 hasConcept C41895202 @default.
- W4315694925 hasConcept C52622490 @default.
- W4315694925 hasConcept C64922751 @default.
- W4315694925 hasConceptScore W4315694925C12267149 @default.
- W4315694925 hasConceptScore W4315694925C138885662 @default.
- W4315694925 hasConceptScore W4315694925C13895895 @default.
- W4315694925 hasConceptScore W4315694925C151989614 @default.
- W4315694925 hasConceptScore W4315694925C153180895 @default.
- W4315694925 hasConceptScore W4315694925C154945302 @default.
- W4315694925 hasConceptScore W4315694925C2776401178 @default.
- W4315694925 hasConceptScore W4315694925C28490314 @default.
- W4315694925 hasConceptScore W4315694925C41008148 @default.
- W4315694925 hasConceptScore W4315694925C41895202 @default.
- W4315694925 hasConceptScore W4315694925C52622490 @default.
- W4315694925 hasConceptScore W4315694925C64922751 @default.
- W4315694925 hasFunder F4320310735 @default.
- W4315694925 hasFunder F4320336389 @default.
- W4315694925 hasFunder F4320338440 @default.
- W4315694925 hasLocation W43156949251 @default.
- W4315694925 hasOpenAccess W4315694925 @default.
- W4315694925 hasPrimaryLocation W43156949251 @default.
- W4315694925 hasRelatedWork W2016461833 @default.
- W4315694925 hasRelatedWork W2126100045 @default.
- W4315694925 hasRelatedWork W2156566403 @default.
- W4315694925 hasRelatedWork W2336974148 @default.
- W4315694925 hasRelatedWork W2381773606 @default.
- W4315694925 hasRelatedWork W2382607599 @default.
- W4315694925 hasRelatedWork W2546942002 @default.
- W4315694925 hasRelatedWork W4225360039 @default.
- W4315694925 hasRelatedWork W2187500075 @default.
- W4315694925 hasRelatedWork W2345184372 @default.
- W4315694925 isParatext "false" @default.
- W4315694925 isRetracted "false" @default.
- W4315694925 workType "article" @default.