FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288693944> ?p ?o ?g. }

• W4288693944 endingPage "1632" @default.
• W4288693944 startingPage "1616" @default.
• W4288693944 abstract "Abstract The surface defect detection (SDD) problem is one of the crucial techniques during production process, so it has become a key research area to control the quality of industrial products, which has been increasingly of greater interest to the researchers especially with the rapid development of artificial neural networks technology in recent years. Therefore, this paper proposes a novel deep convolutional neural network algorithm aiming at SDD. Firstly, a dense cross-stage partial Darknet backbone network is designed for feature extraction by optimizing cross-stage partial Darknet through the idea of dense connections, which can, not only enhance feature reuse but also greatly alleviate the overfitting issue. Secondly, a new cross-stage hierarchy module is presented combining the cross-stage feature fusion strategy and depthwise separable convolution technique for each node of the path aggregated feature pyramid network (PAN). Finally, an efficient channel attention (ECA) mechanism is introduced in PAN to construct a novel ECA PAN. The experimental results on three surface defect datasets show that the mean average precision of this network is 2.63, 5.48, and 1.16$%$ which is higher than that of the baseline network, respectively. The proposed network outperforms not only the classical models but state-of-the-art models, which indicates the proposed algorithm can achieve higher accuracy and speed with fewer calculation parameters. And what is more, the proposed algorithm also has outstanding generalization ability." @default.
• W4288693944 created "2022-07-30" @default.
• W4288693944 creator A5010886799 @default.
• W4288693944 creator A5038629051 @default.
• W4288693944 creator A5045879529 @default.
• W4288693944 creator A5069540002 @default.
• W4288693944 creator A5071037763 @default.
• W4288693944 date "2022-07-29" @default.
• W4288693944 modified "2023-10-18" @default.
• W4288693944 title "A novel deep convolutional neural network algorithm for surface defect detection" @default.
• W4288693944 cites W2039051707 @default.
• W4288693944 cites W2078087367 @default.
• W4288693944 cites W2094158905 @default.
• W4288693944 cites W2107878631 @default.
• W4288693944 cites W2118348777 @default.
• W4288693944 cites W2139963745 @default.
• W4288693944 cites W2146655125 @default.
• W4288693944 cites W2181150946 @default.
• W4288693944 cites W2293457052 @default.
• W4288693944 cites W2416529854 @default.
• W4288693944 cites W2598457882 @default.
• W4288693944 cites W2807520932 @default.
• W4288693944 cites W2884561390 @default.
• W4288693944 cites W2912873949 @default.
• W4288693944 cites W2917663261 @default.
• W4288693944 cites W2963420686 @default.
• W4288693944 cites W2998291476 @default.
• W4288693944 cites W3012374719 @default.
• W4288693944 cites W3034552520 @default.
• W4288693944 cites W3042011474 @default.
• W4288693944 cites W3048201280 @default.
• W4288693944 cites W3120943932 @default.
• W4288693944 cites W3195969653 @default.
• W4288693944 doi "https://doi.org/10.1093/jcde/qwac071" @default.
• W4288693944 hasPublicationYear "2022" @default.
• W4288693944 type Work @default.
• W4288693944 citedByCount "5" @default.
• W4288693944 countsByYear W42886939442022 @default.
• W4288693944 countsByYear W42886939442023 @default.
• W4288693944 crossrefType "journal-article" @default.
• W4288693944 hasAuthorship W4288693944A5010886799 @default.
• W4288693944 hasAuthorship W4288693944A5038629051 @default.
• W4288693944 hasAuthorship W4288693944A5045879529 @default.
• W4288693944 hasAuthorship W4288693944A5069540002 @default.
• W4288693944 hasAuthorship W4288693944A5071037763 @default.
• W4288693944 hasBestOaLocation W42886939441 @default.
• W4288693944 hasConcept C108583219 @default.
• W4288693944 hasConcept C111919701 @default.
• W4288693944 hasConcept C11413529 @default.
• W4288693944 hasConcept C124101348 @default.
• W4288693944 hasConcept C138885662 @default.
• W4288693944 hasConcept C142575187 @default.
• W4288693944 hasConcept C153180895 @default.
• W4288693944 hasConcept C154945302 @default.
• W4288693944 hasConcept C22019652 @default.
• W4288693944 hasConcept C2524010 @default.
• W4288693944 hasConcept C2776401178 @default.
• W4288693944 hasConcept C33923547 @default.
• W4288693944 hasConcept C41008148 @default.
• W4288693944 hasConcept C41895202 @default.
• W4288693944 hasConcept C45347329 @default.
• W4288693944 hasConcept C50644808 @default.
• W4288693944 hasConcept C52622490 @default.
• W4288693944 hasConcept C81363708 @default.
• W4288693944 hasConcept C98045186 @default.
• W4288693944 hasConceptScore W4288693944C108583219 @default.
• W4288693944 hasConceptScore W4288693944C111919701 @default.
• W4288693944 hasConceptScore W4288693944C11413529 @default.
• W4288693944 hasConceptScore W4288693944C124101348 @default.
• W4288693944 hasConceptScore W4288693944C138885662 @default.
• W4288693944 hasConceptScore W4288693944C142575187 @default.
• W4288693944 hasConceptScore W4288693944C153180895 @default.
• W4288693944 hasConceptScore W4288693944C154945302 @default.
• W4288693944 hasConceptScore W4288693944C22019652 @default.
• W4288693944 hasConceptScore W4288693944C2524010 @default.
• W4288693944 hasConceptScore W4288693944C2776401178 @default.
• W4288693944 hasConceptScore W4288693944C33923547 @default.
• W4288693944 hasConceptScore W4288693944C41008148 @default.
• W4288693944 hasConceptScore W4288693944C41895202 @default.
• W4288693944 hasConceptScore W4288693944C45347329 @default.
• W4288693944 hasConceptScore W4288693944C50644808 @default.
• W4288693944 hasConceptScore W4288693944C52622490 @default.
• W4288693944 hasConceptScore W4288693944C81363708 @default.
• W4288693944 hasConceptScore W4288693944C98045186 @default.
• W4288693944 hasFunder F4320321001 @default.
• W4288693944 hasFunder F4320322878 @default.
• W4288693944 hasFunder F4320335955 @default.
• W4288693944 hasIssue "5" @default.
• W4288693944 hasLocation W42886939441 @default.
• W4288693944 hasOpenAccess W4288693944 @default.
• W4288693944 hasPrimaryLocation W42886939441 @default.
• W4288693944 hasRelatedWork W2279398222 @default.
• W4288693944 hasRelatedWork W2295021132 @default.
• W4288693944 hasRelatedWork W2767651786 @default.
• W4288693944 hasRelatedWork W3156786002 @default.
• W4288693944 hasRelatedWork W4220996320 @default.
• W4288693944 hasRelatedWork W4283701629 @default.
• W4288693944 hasRelatedWork W4299822940 @default.

• next