Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289785633> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4289785633 abstract "There has been an increased interest in applying deep neural networks to automatically interpret and analyze the 12-lead electrocardiogram (ECG). The current paradigms with machine learning methods are often limited by the amount of labeled data. This phenomenon is particularly problematic for clinically-relevant data, where labeling at scale can be time-consuming and costly in terms of the specialized expertise and human effort required. Moreover, deep learning classifiers may be vulnerable to adversarial examples and perturbations, which could have catastrophic consequences, for example, when applied in the context of medical treatment, clinical trials, or insurance claims. In this paper, we propose a physiologically-inspired data augmentation method to improve performance and increase the robustness of heart disease detection based on ECG signals. We obtain augmented samples by perturbing the data distribution towards other classes along the geodesic in Wasserstein space. To better utilize domain-specific knowledge, we design a ground metric that recognizes the difference between ECG signals based on physiologically determined features. Learning from 12-lead ECG signals, our model is able to distinguish five categories of cardiac conditions. Our results demonstrate improvements in accuracy and robustness, reflecting the effectiveness of our data augmentation method." @default.
- W4289785633 created "2022-08-04" @default.
- W4289785633 creator A5023737302 @default.
- W4289785633 creator A5024911410 @default.
- W4289785633 creator A5034995105 @default.
- W4289785633 creator A5044586758 @default.
- W4289785633 creator A5058194829 @default.
- W4289785633 creator A5066493621 @default.
- W4289785633 creator A5085940278 @default.
- W4289785633 creator A5088928670 @default.
- W4289785633 date "2022-08-01" @default.
- W4289785633 modified "2023-09-29" @default.
- W4289785633 title "GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction" @default.
- W4289785633 doi "https://doi.org/10.48550/arxiv.2208.01220" @default.
- W4289785633 hasPublicationYear "2022" @default.
- W4289785633 type Work @default.
- W4289785633 citedByCount "0" @default.
- W4289785633 crossrefType "posted-content" @default.
- W4289785633 hasAuthorship W4289785633A5023737302 @default.
- W4289785633 hasAuthorship W4289785633A5024911410 @default.
- W4289785633 hasAuthorship W4289785633A5034995105 @default.
- W4289785633 hasAuthorship W4289785633A5044586758 @default.
- W4289785633 hasAuthorship W4289785633A5058194829 @default.
- W4289785633 hasAuthorship W4289785633A5066493621 @default.
- W4289785633 hasAuthorship W4289785633A5085940278 @default.
- W4289785633 hasAuthorship W4289785633A5088928670 @default.
- W4289785633 hasBestOaLocation W42897856331 @default.
- W4289785633 hasConcept C104317684 @default.
- W4289785633 hasConcept C108583219 @default.
- W4289785633 hasConcept C119857082 @default.
- W4289785633 hasConcept C124101348 @default.
- W4289785633 hasConcept C127413603 @default.
- W4289785633 hasConcept C134306372 @default.
- W4289785633 hasConcept C153180895 @default.
- W4289785633 hasConcept C154945302 @default.
- W4289785633 hasConcept C165818556 @default.
- W4289785633 hasConcept C176217482 @default.
- W4289785633 hasConcept C185592680 @default.
- W4289785633 hasConcept C21547014 @default.
- W4289785633 hasConcept C2984842247 @default.
- W4289785633 hasConcept C33923547 @default.
- W4289785633 hasConcept C37736160 @default.
- W4289785633 hasConcept C41008148 @default.
- W4289785633 hasConcept C50644808 @default.
- W4289785633 hasConcept C55493867 @default.
- W4289785633 hasConcept C63479239 @default.
- W4289785633 hasConceptScore W4289785633C104317684 @default.
- W4289785633 hasConceptScore W4289785633C108583219 @default.
- W4289785633 hasConceptScore W4289785633C119857082 @default.
- W4289785633 hasConceptScore W4289785633C124101348 @default.
- W4289785633 hasConceptScore W4289785633C127413603 @default.
- W4289785633 hasConceptScore W4289785633C134306372 @default.
- W4289785633 hasConceptScore W4289785633C153180895 @default.
- W4289785633 hasConceptScore W4289785633C154945302 @default.
- W4289785633 hasConceptScore W4289785633C165818556 @default.
- W4289785633 hasConceptScore W4289785633C176217482 @default.
- W4289785633 hasConceptScore W4289785633C185592680 @default.
- W4289785633 hasConceptScore W4289785633C21547014 @default.
- W4289785633 hasConceptScore W4289785633C2984842247 @default.
- W4289785633 hasConceptScore W4289785633C33923547 @default.
- W4289785633 hasConceptScore W4289785633C37736160 @default.
- W4289785633 hasConceptScore W4289785633C41008148 @default.
- W4289785633 hasConceptScore W4289785633C50644808 @default.
- W4289785633 hasConceptScore W4289785633C55493867 @default.
- W4289785633 hasConceptScore W4289785633C63479239 @default.
- W4289785633 hasLocation W42897856331 @default.
- W4289785633 hasOpenAccess W4289785633 @default.
- W4289785633 hasPrimaryLocation W42897856331 @default.
- W4289785633 hasRelatedWork W10786582 @default.
- W4289785633 hasRelatedWork W11389402 @default.
- W4289785633 hasRelatedWork W14516383 @default.
- W4289785633 hasRelatedWork W2701911 @default.
- W4289785633 hasRelatedWork W3865299 @default.
- W4289785633 hasRelatedWork W4771408 @default.
- W4289785633 hasRelatedWork W4972971 @default.
- W4289785633 hasRelatedWork W6680660 @default.
- W4289785633 hasRelatedWork W8198582 @default.
- W4289785633 hasRelatedWork W9190101 @default.
- W4289785633 isParatext "false" @default.
- W4289785633 isRetracted "false" @default.
- W4289785633 workType "article" @default.