Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808011919> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2808011919 abstract "In this work, we propose an ensemble of classifiers to distinguish between various degrees of abnormalities of the heart using Phonocardiogram (PCG) signals acquired using digital stethoscopes in a clinical setting, for the INTERSPEECH 2018 Computational Paralinguistics (ComParE) Heart Beats SubChallenge. Our primary classification framework constitutes a convolutional neural network with 1D-CNN time-convolution (tConv) layers, which uses features transferred from a model trained on the 2016 Physionet Heart Sound Database. We also employ a Representation Learning (RL) approach to generate features in an unsupervised manner using Deep Recurrent Autoencoders and use Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) classifiers. Finally, we utilize an SVM classifier on a high-dimensional segment-level feature extracted using various functionals on short-term acoustic features, i.e., Low-Level Descriptors (LLD). An ensemble of the three different approaches provides a relative improvement of 11.13% compared to our best single sub-system in terms of the Unweighted Average Recall (UAR) performance metric on the evaluation dataset." @default.
- W2808011919 created "2018-06-21" @default.
- W2808011919 creator A5023171869 @default.
- W2808011919 creator A5040866561 @default.
- W2808011919 creator A5046358586 @default.
- W2808011919 creator A5063460883 @default.
- W2808011919 creator A5069792590 @default.
- W2808011919 date "2018-09-02" @default.
- W2808011919 modified "2023-10-13" @default.
- W2808011919 title "An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification" @default.
- W2808011919 cites W2020459286 @default.
- W2808011919 cites W2085662862 @default.
- W2808011919 cites W2130942839 @default.
- W2808011919 cites W2137837503 @default.
- W2808011919 cites W2149933564 @default.
- W2808011919 cites W2301158262 @default.
- W2808011919 cites W2398826216 @default.
- W2808011919 cites W2557139718 @default.
- W2808011919 cites W2593628220 @default.
- W2808011919 cites W2594181946 @default.
- W2808011919 cites W2594557222 @default.
- W2808011919 cites W2619236880 @default.
- W2808011919 cites W2622526092 @default.
- W2808011919 cites W2740616720 @default.
- W2808011919 cites W2772935161 @default.
- W2808011919 cites W2889342907 @default.
- W2808011919 cites W2964308564 @default.
- W2808011919 cites W64646310 @default.
- W2808011919 cites W2516413581 @default.
- W2808011919 doi "https://doi.org/10.21437/interspeech.2018-2413" @default.
- W2808011919 hasPublicationYear "2018" @default.
- W2808011919 type Work @default.
- W2808011919 sameAs 2808011919 @default.
- W2808011919 citedByCount "10" @default.
- W2808011919 countsByYear W28080119192020 @default.
- W2808011919 countsByYear W28080119192021 @default.
- W2808011919 countsByYear W28080119192022 @default.
- W2808011919 countsByYear W28080119192023 @default.
- W2808011919 crossrefType "proceedings-article" @default.
- W2808011919 hasAuthorship W2808011919A5023171869 @default.
- W2808011919 hasAuthorship W2808011919A5040866561 @default.
- W2808011919 hasAuthorship W2808011919A5046358586 @default.
- W2808011919 hasAuthorship W2808011919A5063460883 @default.
- W2808011919 hasAuthorship W2808011919A5069792590 @default.
- W2808011919 hasBestOaLocation W28080119192 @default.
- W2808011919 hasConcept C119857082 @default.
- W2808011919 hasConcept C12267149 @default.
- W2808011919 hasConcept C150899416 @default.
- W2808011919 hasConcept C153180895 @default.
- W2808011919 hasConcept C154945302 @default.
- W2808011919 hasConcept C159693508 @default.
- W2808011919 hasConcept C162324750 @default.
- W2808011919 hasConcept C176217482 @default.
- W2808011919 hasConcept C21547014 @default.
- W2808011919 hasConcept C28490314 @default.
- W2808011919 hasConcept C41008148 @default.
- W2808011919 hasConcept C52622490 @default.
- W2808011919 hasConcept C69738355 @default.
- W2808011919 hasConcept C81363708 @default.
- W2808011919 hasConcept C95623464 @default.
- W2808011919 hasConceptScore W2808011919C119857082 @default.
- W2808011919 hasConceptScore W2808011919C12267149 @default.
- W2808011919 hasConceptScore W2808011919C150899416 @default.
- W2808011919 hasConceptScore W2808011919C153180895 @default.
- W2808011919 hasConceptScore W2808011919C154945302 @default.
- W2808011919 hasConceptScore W2808011919C159693508 @default.
- W2808011919 hasConceptScore W2808011919C162324750 @default.
- W2808011919 hasConceptScore W2808011919C176217482 @default.
- W2808011919 hasConceptScore W2808011919C21547014 @default.
- W2808011919 hasConceptScore W2808011919C28490314 @default.
- W2808011919 hasConceptScore W2808011919C41008148 @default.
- W2808011919 hasConceptScore W2808011919C52622490 @default.
- W2808011919 hasConceptScore W2808011919C69738355 @default.
- W2808011919 hasConceptScore W2808011919C81363708 @default.
- W2808011919 hasConceptScore W2808011919C95623464 @default.
- W2808011919 hasLocation W28080119191 @default.
- W2808011919 hasLocation W28080119192 @default.
- W2808011919 hasLocation W28080119193 @default.
- W2808011919 hasOpenAccess W2808011919 @default.
- W2808011919 hasPrimaryLocation W28080119191 @default.
- W2808011919 hasRelatedWork W1571173121 @default.
- W2808011919 hasRelatedWork W2009284386 @default.
- W2808011919 hasRelatedWork W2066804906 @default.
- W2808011919 hasRelatedWork W2163299290 @default.
- W2808011919 hasRelatedWork W2184139745 @default.
- W2808011919 hasRelatedWork W2387004671 @default.
- W2808011919 hasRelatedWork W2463659687 @default.
- W2808011919 hasRelatedWork W2951122819 @default.
- W2808011919 hasRelatedWork W2979740303 @default.
- W2808011919 hasRelatedWork W4288315282 @default.
- W2808011919 isParatext "false" @default.
- W2808011919 isRetracted "false" @default.
- W2808011919 magId "2808011919" @default.
- W2808011919 workType "article" @default.