Matches in SemOpenAlex for { <https://semopenalex.org/work/W2981749573> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2981749573 endingPage "101660" @default.
- W2981749573 startingPage "101660" @default.
- W2981749573 abstract "Abstract Machine learning (ML) components, especially convolutional neural network (CNN) based components, are becoming increasingly vital in cyber-physical systems (CPS), existing great influence on the dependability of CPS. Different to the popular ML model with close set hypothesis, which limits the classes of testing samples to seen classes in training samples, ML in CPS should face the problem of real-world recognition. Open set recognition (OSR) is a more suitable model for improving the dependability of ML components, which allows the presence of unknown classes at testing time. However, the ability to reject those unknown classes is concurrently required in the model. In this paper, we find the defect in compact abating probability application to most CNN-based OSR model. In order to mitigate the defect, two different methods, OpenSoftMax and OPEB are respectively proposed. Finally, extensive experiments on caltech256 data set have been conducted to verify the effectiveness and efficiency of our proposals. Compared to the well-known CNN-based OSR method OpenMax, our first method OpenSoftMax achieves 15.55% average accuracy performance gain and 28.35% F1-score performance gain, while our second method OPEB achieves 13.17% average accuracy performance gain and 25.70% F1-score performance gain." @default.
- W2981749573 created "2019-11-01" @default.
- W2981749573 creator A5010561522 @default.
- W2981749573 creator A5036347970 @default.
- W2981749573 creator A5041407793 @default.
- W2981749573 creator A5048379858 @default.
- W2981749573 creator A5056997294 @default.
- W2981749573 creator A5060087983 @default.
- W2981749573 date "2019-12-01" @default.
- W2981749573 modified "2023-10-12" @default.
- W2981749573 title "Rethinking compact abating probability modeling for open set recognition problem in Cyber-physical systems" @default.
- W2981749573 cites W2027675779 @default.
- W2981749573 cites W2117539524 @default.
- W2981749573 cites W2189201746 @default.
- W2981749573 cites W2248269543 @default.
- W2981749573 cites W2263410234 @default.
- W2981749573 cites W2418213296 @default.
- W2981749573 cites W2509809785 @default.
- W2981749573 cites W2526075485 @default.
- W2981749573 cites W2596801064 @default.
- W2981749573 cites W2763693818 @default.
- W2981749573 cites W2767247349 @default.
- W2981749573 cites W2780496682 @default.
- W2981749573 cites W2791393438 @default.
- W2981749573 cites W2804575237 @default.
- W2981749573 cites W2962689739 @default.
- W2981749573 cites W2962736495 @default.
- W2981749573 cites W572355794 @default.
- W2981749573 doi "https://doi.org/10.1016/j.sysarc.2019.101660" @default.
- W2981749573 hasPublicationYear "2019" @default.
- W2981749573 type Work @default.
- W2981749573 sameAs 2981749573 @default.
- W2981749573 citedByCount "4" @default.
- W2981749573 countsByYear W29817495732021 @default.
- W2981749573 countsByYear W29817495732022 @default.
- W2981749573 countsByYear W29817495732023 @default.
- W2981749573 crossrefType "journal-article" @default.
- W2981749573 hasAuthorship W2981749573A5010561522 @default.
- W2981749573 hasAuthorship W2981749573A5036347970 @default.
- W2981749573 hasAuthorship W2981749573A5041407793 @default.
- W2981749573 hasAuthorship W2981749573A5048379858 @default.
- W2981749573 hasAuthorship W2981749573A5056997294 @default.
- W2981749573 hasAuthorship W2981749573A5060087983 @default.
- W2981749573 hasConcept C107457646 @default.
- W2981749573 hasConcept C111919701 @default.
- W2981749573 hasConcept C118615104 @default.
- W2981749573 hasConcept C154945302 @default.
- W2981749573 hasConcept C177264268 @default.
- W2981749573 hasConcept C179768478 @default.
- W2981749573 hasConcept C199360897 @default.
- W2981749573 hasConcept C2777904410 @default.
- W2981749573 hasConcept C3018397939 @default.
- W2981749573 hasConcept C33923547 @default.
- W2981749573 hasConcept C38652104 @default.
- W2981749573 hasConcept C41008148 @default.
- W2981749573 hasConcept C42357961 @default.
- W2981749573 hasConcept C80444323 @default.
- W2981749573 hasConceptScore W2981749573C107457646 @default.
- W2981749573 hasConceptScore W2981749573C111919701 @default.
- W2981749573 hasConceptScore W2981749573C118615104 @default.
- W2981749573 hasConceptScore W2981749573C154945302 @default.
- W2981749573 hasConceptScore W2981749573C177264268 @default.
- W2981749573 hasConceptScore W2981749573C179768478 @default.
- W2981749573 hasConceptScore W2981749573C199360897 @default.
- W2981749573 hasConceptScore W2981749573C2777904410 @default.
- W2981749573 hasConceptScore W2981749573C3018397939 @default.
- W2981749573 hasConceptScore W2981749573C33923547 @default.
- W2981749573 hasConceptScore W2981749573C38652104 @default.
- W2981749573 hasConceptScore W2981749573C41008148 @default.
- W2981749573 hasConceptScore W2981749573C42357961 @default.
- W2981749573 hasConceptScore W2981749573C80444323 @default.
- W2981749573 hasFunder F4320321001 @default.
- W2981749573 hasLocation W29817495731 @default.
- W2981749573 hasOpenAccess W2981749573 @default.
- W2981749573 hasPrimaryLocation W29817495731 @default.
- W2981749573 hasRelatedWork W2467569328 @default.
- W2981749573 hasRelatedWork W2484398920 @default.
- W2981749573 hasRelatedWork W2785394676 @default.
- W2981749573 hasRelatedWork W2908278544 @default.
- W2981749573 hasRelatedWork W2914617178 @default.
- W2981749573 hasRelatedWork W3025006986 @default.
- W2981749573 hasRelatedWork W3033204818 @default.
- W2981749573 hasRelatedWork W3038372211 @default.
- W2981749573 hasRelatedWork W3107474891 @default.
- W2981749573 hasRelatedWork W4253619374 @default.
- W2981749573 hasVolume "101" @default.
- W2981749573 isParatext "false" @default.
- W2981749573 isRetracted "false" @default.
- W2981749573 magId "2981749573" @default.
- W2981749573 workType "article" @default.