Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385569823> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4385569823 endingPage "22776" @default.
- W4385569823 startingPage "22763" @default.
- W4385569823 abstract "Electrocardiograms (ECG) can be considered a viable method for cardiovascular disease diagnosis. Recently, machine learning algorithms such as deep neural networks trained on ECG signals have demonstrated the capability to identify cardiovascular diseases (CVD). However, existing models for ECG anomaly detection learn from relatively long (60s) ECG signals and tend to be heavily parameterized. Thus, they require large time and computational resources during training. To address this, we propose a novel deep-learning architecture that exploits dilated convolution layers. Our architecture benefits from a classical ResNet-like formulation, and we introduce a recurrent component to better leverage temporal information in the data, while also benefiting from the dilated convolution operation. Our proposed architecture is capable of learning from single and 12-lead ECG signals and thus offers a flexible solution for CVD diagnosis. In our experiments, we perform subject-independent ten-fold cross-validations and compare our results with two existing benchmark models using the PhysioNet Atrial Fibrillation challenge dataset, the China Physiological challenge the PTB-XL repository from PhysioNet and the Georgia dataset. For all four datasets, our model archives state-of-the-art performance, with an upto 8% F1 score gain achieved. Our neural conduction plots demonstrate the effectiveness of having convolution layers with varying dilation factors, and the use of recurrent networks to capture rhythmic patterns. Our architecture is explainable and has the ability to learn from short ECG segments. Using neural conductance, we reveal interesting hidden patterns learned by our model, which reflect the medical phenomenons/characteristics associated with CVD. Code is publically available here." @default.
- W4385569823 created "2023-08-05" @default.
- W4385569823 creator A5000736425 @default.
- W4385569823 creator A5020661742 @default.
- W4385569823 creator A5034095159 @default.
- W4385569823 creator A5055128383 @default.
- W4385569823 creator A5083626840 @default.
- W4385569823 date "2023-10-01" @default.
- W4385569823 modified "2023-10-06" @default.
- W4385569823 title "DConv-LSTM-Net: A Novel Architecture for Single and 12-Lead ECG Anomaly Detection." @default.
- W4385569823 cites W1965664263 @default.
- W4385569823 cites W2162800060 @default.
- W4385569823 cites W2167277498 @default.
- W4385569823 cites W2291961022 @default.
- W4385569823 cites W2779797561 @default.
- W4385569823 cites W2794819237 @default.
- W4385569823 cites W2887119478 @default.
- W4385569823 cites W2888456553 @default.
- W4385569823 cites W2898941944 @default.
- W4385569823 cites W2953193031 @default.
- W4385569823 cites W3005055041 @default.
- W4385569823 cites W3015692457 @default.
- W4385569823 cites W3022945091 @default.
- W4385569823 cites W3026019966 @default.
- W4385569823 cites W3083550439 @default.
- W4385569823 cites W3084949122 @default.
- W4385569823 cites W3119282903 @default.
- W4385569823 cites W3121032337 @default.
- W4385569823 cites W3133814784 @default.
- W4385569823 cites W3134859729 @default.
- W4385569823 cites W3137700257 @default.
- W4385569823 cites W3158749186 @default.
- W4385569823 cites W4207054915 @default.
- W4385569823 cites W4226050069 @default.
- W4385569823 cites W4226150995 @default.
- W4385569823 cites W4226287143 @default.
- W4385569823 cites W4285224206 @default.
- W4385569823 cites W4321369461 @default.
- W4385569823 doi "https://doi.org/10.1109/jsen.2023.3300752" @default.
- W4385569823 hasPublicationYear "2023" @default.
- W4385569823 type Work @default.
- W4385569823 citedByCount "0" @default.
- W4385569823 crossrefType "journal-article" @default.
- W4385569823 hasAuthorship W4385569823A5000736425 @default.
- W4385569823 hasAuthorship W4385569823A5020661742 @default.
- W4385569823 hasAuthorship W4385569823A5034095159 @default.
- W4385569823 hasAuthorship W4385569823A5055128383 @default.
- W4385569823 hasAuthorship W4385569823A5083626840 @default.
- W4385569823 hasConcept C108583219 @default.
- W4385569823 hasConcept C11413529 @default.
- W4385569823 hasConcept C119857082 @default.
- W4385569823 hasConcept C124101348 @default.
- W4385569823 hasConcept C13280743 @default.
- W4385569823 hasConcept C147168706 @default.
- W4385569823 hasConcept C153083717 @default.
- W4385569823 hasConcept C153180895 @default.
- W4385569823 hasConcept C154945302 @default.
- W4385569823 hasConcept C165464430 @default.
- W4385569823 hasConcept C185798385 @default.
- W4385569823 hasConcept C205649164 @default.
- W4385569823 hasConcept C41008148 @default.
- W4385569823 hasConcept C45347329 @default.
- W4385569823 hasConcept C50644808 @default.
- W4385569823 hasConcept C739882 @default.
- W4385569823 hasConceptScore W4385569823C108583219 @default.
- W4385569823 hasConceptScore W4385569823C11413529 @default.
- W4385569823 hasConceptScore W4385569823C119857082 @default.
- W4385569823 hasConceptScore W4385569823C124101348 @default.
- W4385569823 hasConceptScore W4385569823C13280743 @default.
- W4385569823 hasConceptScore W4385569823C147168706 @default.
- W4385569823 hasConceptScore W4385569823C153083717 @default.
- W4385569823 hasConceptScore W4385569823C153180895 @default.
- W4385569823 hasConceptScore W4385569823C154945302 @default.
- W4385569823 hasConceptScore W4385569823C165464430 @default.
- W4385569823 hasConceptScore W4385569823C185798385 @default.
- W4385569823 hasConceptScore W4385569823C205649164 @default.
- W4385569823 hasConceptScore W4385569823C41008148 @default.
- W4385569823 hasConceptScore W4385569823C45347329 @default.
- W4385569823 hasConceptScore W4385569823C50644808 @default.
- W4385569823 hasConceptScore W4385569823C739882 @default.
- W4385569823 hasIssue "19" @default.
- W4385569823 hasLocation W43855698231 @default.
- W4385569823 hasOpenAccess W4385569823 @default.
- W4385569823 hasPrimaryLocation W43855698231 @default.
- W4385569823 hasRelatedWork W1494268238 @default.
- W4385569823 hasRelatedWork W154868527 @default.
- W4385569823 hasRelatedWork W1976468483 @default.
- W4385569823 hasRelatedWork W1983207144 @default.
- W4385569823 hasRelatedWork W2051058708 @default.
- W4385569823 hasRelatedWork W2407611282 @default.
- W4385569823 hasRelatedWork W2480116122 @default.
- W4385569823 hasRelatedWork W2490706771 @default.
- W4385569823 hasRelatedWork W4255576661 @default.
- W4385569823 hasRelatedWork W2563912921 @default.
- W4385569823 hasVolume "23" @default.
- W4385569823 isParatext "false" @default.
- W4385569823 isRetracted "false" @default.
- W4385569823 workType "article" @default.