Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311593456> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4311593456 endingPage "1466" @default.
- W4311593456 startingPage "1456" @default.
- W4311593456 abstract "As an essential approach in many Internet of Things (IoT) applications, multiview learning synthesizes multiple features to achieve more comprehensive descriptions of data items. Most of the previous studies on multiview learning have been dedicated to increasing the prediction accuracy, while ignoring the reliability of the decision. This would limit their deployment in high-risk IoT and industrial applications such as the automated vehicle. Although a trusted multiview classification model has been proposed recently, it cannot well deal with the highly complementary multiview data. In this work, we present an evidential multiview deep learning (EMDL) method to make reliable decisions. EMDL first seeks view-specific evidence of each category, which could be termed as the amount of support to each category collected from data. It then dynamically fuses different views at the evidence level to construct the multiview common evidence and makes reliable prediction accordingly (strong evidence indicates high prediction confidence). In particular, we establish a degradation layer to learn the mappings from the common evidence (comprehensive information) to view-specific evidences (partial information) for evidence fusion. It aims to explicitly model consistent and complementary relations in multiview data at the evidence level. We apply EMDL on a synthetic toy dataset and five real-world datasets (three datasets are related to industrial scenarios). Experiments show that EMDL outperforms state-of-the-art baseline methods." @default.
- W4311593456 created "2022-12-27" @default.
- W4311593456 creator A5007403499 @default.
- W4311593456 creator A5026879096 @default.
- W4311593456 creator A5045624196 @default.
- W4311593456 creator A5053270215 @default.
- W4311593456 creator A5065194313 @default.
- W4311593456 creator A5080615821 @default.
- W4311593456 date "2023-02-01" @default.
- W4311593456 modified "2023-10-16" @default.
- W4311593456 title "Uncertainty-Aware Multiview Deep Learning for Internet of Things Applications" @default.
- W4311593456 cites W1579925870 @default.
- W4311593456 cites W2061521613 @default.
- W4311593456 cites W2107034620 @default.
- W4311593456 cites W2144348409 @default.
- W4311593456 cites W22229905 @default.
- W4311593456 cites W2470413457 @default.
- W4311593456 cites W2770472008 @default.
- W4311593456 cites W2791276322 @default.
- W4311593456 cites W2899604627 @default.
- W4311593456 cites W2906529026 @default.
- W4311593456 cites W2965970896 @default.
- W4311593456 cites W2969083552 @default.
- W4311593456 cites W2971032560 @default.
- W4311593456 cites W3015232403 @default.
- W4311593456 cites W3021342796 @default.
- W4311593456 cites W3172210583 @default.
- W4311593456 cites W3200343674 @default.
- W4311593456 doi "https://doi.org/10.1109/tii.2022.3206343" @default.
- W4311593456 hasPublicationYear "2023" @default.
- W4311593456 type Work @default.
- W4311593456 citedByCount "21" @default.
- W4311593456 countsByYear W43115934562023 @default.
- W4311593456 crossrefType "journal-article" @default.
- W4311593456 hasAuthorship W4311593456A5007403499 @default.
- W4311593456 hasAuthorship W4311593456A5026879096 @default.
- W4311593456 hasAuthorship W4311593456A5045624196 @default.
- W4311593456 hasAuthorship W4311593456A5053270215 @default.
- W4311593456 hasAuthorship W4311593456A5065194313 @default.
- W4311593456 hasAuthorship W4311593456A5080615821 @default.
- W4311593456 hasConcept C105339364 @default.
- W4311593456 hasConcept C108583219 @default.
- W4311593456 hasConcept C111919701 @default.
- W4311593456 hasConcept C119857082 @default.
- W4311593456 hasConcept C121332964 @default.
- W4311593456 hasConcept C124101348 @default.
- W4311593456 hasConcept C127413603 @default.
- W4311593456 hasConcept C154945302 @default.
- W4311593456 hasConcept C163258240 @default.
- W4311593456 hasConcept C175154964 @default.
- W4311593456 hasConcept C201995342 @default.
- W4311593456 hasConcept C2780451532 @default.
- W4311593456 hasConcept C33954974 @default.
- W4311593456 hasConcept C41008148 @default.
- W4311593456 hasConcept C43214815 @default.
- W4311593456 hasConcept C62520636 @default.
- W4311593456 hasConceptScore W4311593456C105339364 @default.
- W4311593456 hasConceptScore W4311593456C108583219 @default.
- W4311593456 hasConceptScore W4311593456C111919701 @default.
- W4311593456 hasConceptScore W4311593456C119857082 @default.
- W4311593456 hasConceptScore W4311593456C121332964 @default.
- W4311593456 hasConceptScore W4311593456C124101348 @default.
- W4311593456 hasConceptScore W4311593456C127413603 @default.
- W4311593456 hasConceptScore W4311593456C154945302 @default.
- W4311593456 hasConceptScore W4311593456C163258240 @default.
- W4311593456 hasConceptScore W4311593456C175154964 @default.
- W4311593456 hasConceptScore W4311593456C201995342 @default.
- W4311593456 hasConceptScore W4311593456C2780451532 @default.
- W4311593456 hasConceptScore W4311593456C33954974 @default.
- W4311593456 hasConceptScore W4311593456C41008148 @default.
- W4311593456 hasConceptScore W4311593456C43214815 @default.
- W4311593456 hasConceptScore W4311593456C62520636 @default.
- W4311593456 hasFunder F4320321001 @default.
- W4311593456 hasFunder F4320321435 @default.
- W4311593456 hasFunder F4320336350 @default.
- W4311593456 hasIssue "2" @default.
- W4311593456 hasLocation W43115934561 @default.
- W4311593456 hasOpenAccess W4311593456 @default.
- W4311593456 hasPrimaryLocation W43115934561 @default.
- W4311593456 hasRelatedWork W2922457425 @default.
- W4311593456 hasRelatedWork W3014300295 @default.
- W4311593456 hasRelatedWork W3164822677 @default.
- W4311593456 hasRelatedWork W3215138031 @default.
- W4311593456 hasRelatedWork W4223943233 @default.
- W4311593456 hasRelatedWork W4225161397 @default.
- W4311593456 hasRelatedWork W4250304930 @default.
- W4311593456 hasRelatedWork W4299487748 @default.
- W4311593456 hasRelatedWork W4309045103 @default.
- W4311593456 hasRelatedWork W4312200629 @default.
- W4311593456 hasVolume "19" @default.
- W4311593456 isParatext "false" @default.
- W4311593456 isRetracted "false" @default.
- W4311593456 workType "article" @default.