Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209744178> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3209744178 abstract "The electrocardiogram (ECG) is a widespread diagnostic tool in healthcare and supports the diagnosis of cardiovascular disorders. Deep learning methods are a successful and popular technique to detect indications of disorders from an ECG signal. However, there are open questions around the robustness of these methods to various factors, including physiological ECG noise. In this study, we generate clean and noisy versions of an ECG dataset before applying symmetric projection attractor reconstruction (SPAR) and scalogram image transformations. A convolutional neural network is used to classify these image transforms. For the clean ECG dataset, F1 scores for SPAR attractor and scalogram transforms were 0.70 and 0.79, respectively. Scores decreased by less than 0.05 for the noisy ECG datasets. Notably, when the network trained on clean data was used to classify the noisy datasets, performance decreases of up to 0.18 in F1 scores were seen. However, when the network trained on the noisy data was used to classify the clean dataset, the decrease was less than 0.05. We conclude that physiological ECG noise impacts classification using deep learning methods and careful consideration should be given to the inclusion of noisy ECG signals in the training data when developing supervised networks for ECG classification. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'." @default.
- W3209744178 created "2021-11-08" @default.
- W3209744178 creator A5025668855 @default.
- W3209744178 creator A5027038093 @default.
- W3209744178 creator A5036627753 @default.
- W3209744178 creator A5072157603 @default.
- W3209744178 creator A5088264583 @default.
- W3209744178 date "2021-10-25" @default.
- W3209744178 modified "2023-10-02" @default.
- W3209744178 title "Robustness of convolutional neural networks to physiological electrocardiogram noise" @default.
- W3209744178 cites W1468476315 @default.
- W3209744178 cites W1787224781 @default.
- W3209744178 cites W2017263726 @default.
- W3209744178 cites W2056351478 @default.
- W3209744178 cites W2078174563 @default.
- W3209744178 cites W2108598243 @default.
- W3209744178 cites W2124136621 @default.
- W3209744178 cites W2155185020 @default.
- W3209744178 cites W2282821441 @default.
- W3209744178 cites W2761097105 @default.
- W3209744178 cites W2785544921 @default.
- W3209744178 cites W2884211983 @default.
- W3209744178 cites W2892892777 @default.
- W3209744178 cites W2902644322 @default.
- W3209744178 cites W2915279277 @default.
- W3209744178 cites W2936503027 @default.
- W3209744178 cites W2946152371 @default.
- W3209744178 cites W3009460750 @default.
- W3209744178 cites W3033523981 @default.
- W3209744178 cites W3049106197 @default.
- W3209744178 cites W3093699748 @default.
- W3209744178 cites W3112204318 @default.
- W3209744178 doi "https://doi.org/10.1098/rsta.2020.0262" @default.
- W3209744178 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8543045" @default.
- W3209744178 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34689617" @default.
- W3209744178 hasPublicationYear "2021" @default.
- W3209744178 type Work @default.
- W3209744178 sameAs 3209744178 @default.
- W3209744178 citedByCount "14" @default.
- W3209744178 countsByYear W32097441782021 @default.
- W3209744178 countsByYear W32097441782022 @default.
- W3209744178 countsByYear W32097441782023 @default.
- W3209744178 crossrefType "journal-article" @default.
- W3209744178 hasAuthorship W3209744178A5025668855 @default.
- W3209744178 hasAuthorship W3209744178A5027038093 @default.
- W3209744178 hasAuthorship W3209744178A5036627753 @default.
- W3209744178 hasAuthorship W3209744178A5072157603 @default.
- W3209744178 hasAuthorship W3209744178A5088264583 @default.
- W3209744178 hasBestOaLocation W32097441781 @default.
- W3209744178 hasConcept C104317684 @default.
- W3209744178 hasConcept C108583219 @default.
- W3209744178 hasConcept C115961682 @default.
- W3209744178 hasConcept C119857082 @default.
- W3209744178 hasConcept C153180895 @default.
- W3209744178 hasConcept C154945302 @default.
- W3209744178 hasConcept C185592680 @default.
- W3209744178 hasConcept C41008148 @default.
- W3209744178 hasConcept C50644808 @default.
- W3209744178 hasConcept C55493867 @default.
- W3209744178 hasConcept C63479239 @default.
- W3209744178 hasConcept C81363708 @default.
- W3209744178 hasConcept C99498987 @default.
- W3209744178 hasConceptScore W3209744178C104317684 @default.
- W3209744178 hasConceptScore W3209744178C108583219 @default.
- W3209744178 hasConceptScore W3209744178C115961682 @default.
- W3209744178 hasConceptScore W3209744178C119857082 @default.
- W3209744178 hasConceptScore W3209744178C153180895 @default.
- W3209744178 hasConceptScore W3209744178C154945302 @default.
- W3209744178 hasConceptScore W3209744178C185592680 @default.
- W3209744178 hasConceptScore W3209744178C41008148 @default.
- W3209744178 hasConceptScore W3209744178C50644808 @default.
- W3209744178 hasConceptScore W3209744178C55493867 @default.
- W3209744178 hasConceptScore W3209744178C63479239 @default.
- W3209744178 hasConceptScore W3209744178C81363708 @default.
- W3209744178 hasConceptScore W3209744178C99498987 @default.
- W3209744178 hasFunder F4320313458 @default.
- W3209744178 hasIssue "2212" @default.
- W3209744178 hasLocation W32097441781 @default.
- W3209744178 hasLocation W32097441782 @default.
- W3209744178 hasLocation W32097441783 @default.
- W3209744178 hasLocation W32097441784 @default.
- W3209744178 hasLocation W32097441785 @default.
- W3209744178 hasOpenAccess W3209744178 @default.
- W3209744178 hasPrimaryLocation W32097441781 @default.
- W3209744178 hasRelatedWork W2731899572 @default.
- W3209744178 hasRelatedWork W2999805992 @default.
- W3209744178 hasRelatedWork W3116150086 @default.
- W3209744178 hasRelatedWork W3133861977 @default.
- W3209744178 hasRelatedWork W4200173597 @default.
- W3209744178 hasRelatedWork W4223943233 @default.
- W3209744178 hasRelatedWork W4291897433 @default.
- W3209744178 hasRelatedWork W4312417841 @default.
- W3209744178 hasRelatedWork W4321369474 @default.
- W3209744178 hasRelatedWork W4380075502 @default.
- W3209744178 hasVolume "379" @default.
- W3209744178 isParatext "false" @default.
- W3209744178 isRetracted "false" @default.
- W3209744178 magId "3209744178" @default.
- W3209744178 workType "article" @default.