Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048270903> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3048270903 abstract "Electrocardiogram (ECG) is the most widely used diagnostic tool to monitor the condition of the cardiovascular system. Deep neural networks (DNNs), have been developed in many research labs for automatic interpretation of ECG signals to identify potential abnormalities in patient hearts. Studies have shown that given a sufficiently large amount of data, the classification accuracy of DNNs could reach human-expert cardiologist level. However, despite of the excellent performance in classification accuracy, it has been shown that DNNs are highly vulnerable to adversarial noises which are subtle changes in input of a DNN and lead to a wrong class-label prediction with a high confidence. Thus, it is challenging and essential to improve robustness of DNNs against adversarial noises for ECG signal classification, a life-critical application. In this work, we designed a CNN for classification of 12-lead ECG signals with variable length, and we applied three defense methods to improve robustness of this CNN for this classification task. The ECG data in this study is very challenging because the sample size is limited, and the length of each ECG recording varies in a large range. The evaluation results show that our customized CNN reached satisfying F1 score and average accuracy, comparable to the top-6 entries in the CPSC2018 ECG classification challenge, and the defense methods enhanced robustness of our CNN against adversarial noises and white noises, with a minimal reduction in accuracy on clean data." @default.
- W3048270903 created "2020-08-13" @default.
- W3048270903 creator A5067242485 @default.
- W3048270903 creator A5070629109 @default.
- W3048270903 date "2020-08-08" @default.
- W3048270903 modified "2023-09-28" @default.
- W3048270903 title "Enhance CNN Robustness Against Noises for Classification of 12-Lead ECG with Variable Length" @default.
- W3048270903 cites W1576089372 @default.
- W3048270903 cites W2291961022 @default.
- W3048270903 cites W2603766943 @default.
- W3048270903 cites W2731010577 @default.
- W3048270903 cites W2748902594 @default.
- W3048270903 cites W2786104118 @default.
- W3048270903 cites W2888456553 @default.
- W3048270903 cites W2913266441 @default.
- W3048270903 cites W2962700793 @default.
- W3048270903 cites W2962821226 @default.
- W3048270903 cites W2963249138 @default.
- W3048270903 cites W2963542245 @default.
- W3048270903 cites W2964253222 @default.
- W3048270903 cites W2970317235 @default.
- W3048270903 cites W2995245581 @default.
- W3048270903 cites W3027791828 @default.
- W3048270903 cites W3103340107 @default.
- W3048270903 cites W3106455851 @default.
- W3048270903 doi "https://doi.org/10.48550/arxiv.2008.03609" @default.
- W3048270903 hasPublicationYear "2020" @default.
- W3048270903 type Work @default.
- W3048270903 sameAs 3048270903 @default.
- W3048270903 citedByCount "0" @default.
- W3048270903 crossrefType "posted-content" @default.
- W3048270903 hasAuthorship W3048270903A5067242485 @default.
- W3048270903 hasAuthorship W3048270903A5070629109 @default.
- W3048270903 hasBestOaLocation W30482709031 @default.
- W3048270903 hasConcept C104317684 @default.
- W3048270903 hasConcept C105795698 @default.
- W3048270903 hasConcept C108583219 @default.
- W3048270903 hasConcept C119857082 @default.
- W3048270903 hasConcept C129848803 @default.
- W3048270903 hasConcept C153180895 @default.
- W3048270903 hasConcept C154945302 @default.
- W3048270903 hasConcept C185592680 @default.
- W3048270903 hasConcept C2984842247 @default.
- W3048270903 hasConcept C33923547 @default.
- W3048270903 hasConcept C37736160 @default.
- W3048270903 hasConcept C41008148 @default.
- W3048270903 hasConcept C55493867 @default.
- W3048270903 hasConcept C63479239 @default.
- W3048270903 hasConceptScore W3048270903C104317684 @default.
- W3048270903 hasConceptScore W3048270903C105795698 @default.
- W3048270903 hasConceptScore W3048270903C108583219 @default.
- W3048270903 hasConceptScore W3048270903C119857082 @default.
- W3048270903 hasConceptScore W3048270903C129848803 @default.
- W3048270903 hasConceptScore W3048270903C153180895 @default.
- W3048270903 hasConceptScore W3048270903C154945302 @default.
- W3048270903 hasConceptScore W3048270903C185592680 @default.
- W3048270903 hasConceptScore W3048270903C2984842247 @default.
- W3048270903 hasConceptScore W3048270903C33923547 @default.
- W3048270903 hasConceptScore W3048270903C37736160 @default.
- W3048270903 hasConceptScore W3048270903C41008148 @default.
- W3048270903 hasConceptScore W3048270903C55493867 @default.
- W3048270903 hasConceptScore W3048270903C63479239 @default.
- W3048270903 hasLocation W30482709031 @default.
- W3048270903 hasOpenAccess W3048270903 @default.
- W3048270903 hasPrimaryLocation W30482709031 @default.
- W3048270903 hasRelatedWork W11738893 @default.
- W3048270903 hasRelatedWork W13260401 @default.
- W3048270903 hasRelatedWork W1368183 @default.
- W3048270903 hasRelatedWork W14070459 @default.
- W3048270903 hasRelatedWork W1997323 @default.
- W3048270903 hasRelatedWork W3865299 @default.
- W3048270903 hasRelatedWork W4112095 @default.
- W3048270903 hasRelatedWork W4972971 @default.
- W3048270903 hasRelatedWork W5006466 @default.
- W3048270903 hasRelatedWork W7299809 @default.
- W3048270903 isParatext "false" @default.
- W3048270903 isRetracted "false" @default.
- W3048270903 magId "3048270903" @default.
- W3048270903 workType "article" @default.