Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211640671> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3211640671 endingPage "10373" @default.
- W3211640671 startingPage "10373" @default.
- W3211640671 abstract "Due to the imperfect assembly process, the unqualified assembly of a missing gasket or lead seal will affect the product’s performance and possibly cause safety accidents. Machine vision method based on deep learning has been widely used in quality inspection. Semi-supervised learning (SSL) has been applied in training deep learning models to reduce the burden of data annotation. The dataset obtained from the production line tends to be class-imbalanced because the assemblies are qualified in most cases. However, most SSL methods suffer from lower performance in class-imbalanced datasets. Therefore, we propose a new semi-supervised algorithm that achieves high classification accuracy on the class-imbalanced assembly dataset with limited labeled data. Based on the mean teacher algorithm, the proposed algorithm uses certainty to select reliable teacher predictions for student learning dynamically, and loss functions are modified to improve the model’s robustness against class imbalance. Results show that when only 10% of the total data are labeled, and the imbalance rate is 5.3, the proposed method can improve the accuracy from 85.34% to 93.67% compared to supervised learning. When the amount of annotated data accounts for 20%, the accuracy can reach 98.83%." @default.
- W3211640671 created "2021-11-22" @default.
- W3211640671 creator A5018219682 @default.
- W3211640671 creator A5019844744 @default.
- W3211640671 creator A5022245139 @default.
- W3211640671 creator A5034202168 @default.
- W3211640671 date "2021-11-04" @default.
- W3211640671 modified "2023-10-18" @default.
- W3211640671 title "Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning" @default.
- W3211640671 cites W2040483045 @default.
- W3211640671 cites W2118978333 @default.
- W3211640671 cites W2191848209 @default.
- W3211640671 cites W2332885174 @default.
- W3211640671 cites W2406523001 @default.
- W3211640671 cites W2490420619 @default.
- W3211640671 cites W2735360945 @default.
- W3211640671 cites W2767106145 @default.
- W3211640671 cites W2772386856 @default.
- W3211640671 cites W2793036691 @default.
- W3211640671 cites W2793899888 @default.
- W3211640671 cites W2853491009 @default.
- W3211640671 cites W2886603761 @default.
- W3211640671 cites W2891319189 @default.
- W3211640671 cites W2899280016 @default.
- W3211640671 cites W2945228284 @default.
- W3211640671 cites W3011799887 @default.
- W3211640671 cites W3034942609 @default.
- W3211640671 cites W3041076719 @default.
- W3211640671 cites W3106586287 @default.
- W3211640671 cites W3132422289 @default.
- W3211640671 cites W3155079234 @default.
- W3211640671 cites W3161051405 @default.
- W3211640671 cites W3162544942 @default.
- W3211640671 cites W3183804269 @default.
- W3211640671 doi "https://doi.org/10.3390/app112110373" @default.
- W3211640671 hasPublicationYear "2021" @default.
- W3211640671 type Work @default.
- W3211640671 sameAs 3211640671 @default.
- W3211640671 citedByCount "3" @default.
- W3211640671 countsByYear W32116406712022 @default.
- W3211640671 countsByYear W32116406712023 @default.
- W3211640671 crossrefType "journal-article" @default.
- W3211640671 hasAuthorship W3211640671A5018219682 @default.
- W3211640671 hasAuthorship W3211640671A5019844744 @default.
- W3211640671 hasAuthorship W3211640671A5022245139 @default.
- W3211640671 hasAuthorship W3211640671A5034202168 @default.
- W3211640671 hasBestOaLocation W32116406711 @default.
- W3211640671 hasConcept C104317684 @default.
- W3211640671 hasConcept C119857082 @default.
- W3211640671 hasConcept C124101348 @default.
- W3211640671 hasConcept C153180895 @default.
- W3211640671 hasConcept C154945302 @default.
- W3211640671 hasConcept C185592680 @default.
- W3211640671 hasConcept C2776321320 @default.
- W3211640671 hasConcept C41008148 @default.
- W3211640671 hasConcept C55493867 @default.
- W3211640671 hasConcept C58973888 @default.
- W3211640671 hasConcept C63479239 @default.
- W3211640671 hasConceptScore W3211640671C104317684 @default.
- W3211640671 hasConceptScore W3211640671C119857082 @default.
- W3211640671 hasConceptScore W3211640671C124101348 @default.
- W3211640671 hasConceptScore W3211640671C153180895 @default.
- W3211640671 hasConceptScore W3211640671C154945302 @default.
- W3211640671 hasConceptScore W3211640671C185592680 @default.
- W3211640671 hasConceptScore W3211640671C2776321320 @default.
- W3211640671 hasConceptScore W3211640671C41008148 @default.
- W3211640671 hasConceptScore W3211640671C55493867 @default.
- W3211640671 hasConceptScore W3211640671C58973888 @default.
- W3211640671 hasConceptScore W3211640671C63479239 @default.
- W3211640671 hasFunder F4320321001 @default.
- W3211640671 hasIssue "21" @default.
- W3211640671 hasLocation W32116406711 @default.
- W3211640671 hasLocation W32116406712 @default.
- W3211640671 hasOpenAccess W3211640671 @default.
- W3211640671 hasPrimaryLocation W32116406711 @default.
- W3211640671 hasRelatedWork W2795261237 @default.
- W3211640671 hasRelatedWork W3025582806 @default.
- W3211640671 hasRelatedWork W3094076422 @default.
- W3211640671 hasRelatedWork W3162567751 @default.
- W3211640671 hasRelatedWork W3196155444 @default.
- W3211640671 hasRelatedWork W4285260836 @default.
- W3211640671 hasRelatedWork W4306321456 @default.
- W3211640671 hasRelatedWork W4319309271 @default.
- W3211640671 hasRelatedWork W4320063314 @default.
- W3211640671 hasRelatedWork W4386025632 @default.
- W3211640671 hasVolume "11" @default.
- W3211640671 isParatext "false" @default.
- W3211640671 isRetracted "false" @default.
- W3211640671 magId "3211640671" @default.
- W3211640671 workType "article" @default.