FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309146016> ?p ?o ?g. }

• W4309146016 endingPage "103106" @default.
• W4309146016 startingPage "103106" @default.
• W4309146016 abstract "With the application of 3D sensors, studies on various vision tasks based on point clouds have been explored in different fields. In the field of the high-speed train safety inspection, the vision-based artificial intelligence inspection technology has received greater attention in recent years. In this paper, we introduce a graph neural network-based (GNN) two-stage anomaly identification method (GTAINet) for locking wire point clouds. GTAINet consists of two sub-networks, a segmentation network and a classification network. The segmentation network splits bolt, wire and background points, then the segmented bolt and wire points are fed into the classification network to identify whether the sample is broken. However, as an essential type of geometric data structure, how to extract the rich geometric representation from point clouds is the key to the above vision tasks. To this end, we proposed a hierarchical attentive edge convolution (HAEConv) to establish a GNN. HAEConv is able to recover hierarchical topological information from point clouds and attentively recalibrate each edge’s response, which allows the model to better capture more useful information of local and global geometric structure. Another critical point that limits the segmentation and classification performance is the lack of training data, in particular the lack of anomaly locking wire samples. To address this challenge, we propose a synthetic algorithm that can synthesize massive fake anomaly locking wire data using parameterized Bézier curves. Experiments demonstrate that the proposed networks based on HAEConv outperform popular existing methods on both segmentation and classification tasks. In addition, the synthetic method presented allows us to pre-train a model with very strong generalization ability, which can significantly improve model performance." @default.
• W4309146016 created "2022-11-23" @default.
• W4309146016 creator A5019628417 @default.
• W4309146016 creator A5049766394 @default.
• W4309146016 creator A5071773009 @default.
• W4309146016 creator A5077057995 @default.
• W4309146016 date "2022-12-01" @default.
• W4309146016 modified "2023-09-28" @default.
• W4309146016 title "GTAINet: Graph neural network-based two-stage anomaly identification for locking wire point clouds using hierarchical attentive edge convolution" @default.
• W4309146016 cites W2211722331 @default.
• W4309146016 cites W2556802233 @default.
• W4309146016 cites W2560609797 @default.
• W4309146016 cites W2606202972 @default.
• W4309146016 cites W2614059183 @default.
• W4309146016 cites W2751849977 @default.
• W4309146016 cites W2775216572 @default.
• W4309146016 cites W2962912109 @default.
• W4309146016 cites W2963035165 @default.
• W4309146016 cites W2963231572 @default.
• W4309146016 cites W2963312728 @default.
• W4309146016 cites W2963517242 @default.
• W4309146016 cites W2983098675 @default.
• W4309146016 cites W2989786816 @default.
• W4309146016 cites W2990613095 @default.
• W4309146016 cites W2995932445 @default.
• W4309146016 cites W3007809903 @default.
• W4309146016 cites W3012494314 @default.
• W4309146016 cites W3015248322 @default.
• W4309146016 cites W3017088349 @default.
• W4309146016 cites W3034239841 @default.
• W4309146016 cites W3039448353 @default.
• W4309146016 cites W3104038589 @default.
• W4309146016 cites W3169060769 @default.
• W4309146016 cites W3209330006 @default.
• W4309146016 cites W4283073947 @default.
• W4309146016 doi "https://doi.org/10.1016/j.jag.2022.103106" @default.
• W4309146016 hasPublicationYear "2022" @default.
• W4309146016 type Work @default.
• W4309146016 citedByCount "0" @default.
• W4309146016 crossrefType "journal-article" @default.
• W4309146016 hasAuthorship W4309146016A5019628417 @default.
• W4309146016 hasAuthorship W4309146016A5049766394 @default.
• W4309146016 hasAuthorship W4309146016A5071773009 @default.
• W4309146016 hasAuthorship W4309146016A5077057995 @default.
• W4309146016 hasConcept C11413529 @default.
• W4309146016 hasConcept C131979681 @default.
• W4309146016 hasConcept C132525143 @default.
• W4309146016 hasConcept C153180895 @default.
• W4309146016 hasConcept C154945302 @default.
• W4309146016 hasConcept C162307627 @default.
• W4309146016 hasConcept C165464430 @default.
• W4309146016 hasConcept C31972630 @default.
• W4309146016 hasConcept C41008148 @default.
• W4309146016 hasConcept C50644808 @default.
• W4309146016 hasConcept C80444323 @default.
• W4309146016 hasConcept C89600930 @default.
• W4309146016 hasConceptScore W4309146016C11413529 @default.
• W4309146016 hasConceptScore W4309146016C131979681 @default.
• W4309146016 hasConceptScore W4309146016C132525143 @default.
• W4309146016 hasConceptScore W4309146016C153180895 @default.
• W4309146016 hasConceptScore W4309146016C154945302 @default.
• W4309146016 hasConceptScore W4309146016C162307627 @default.
• W4309146016 hasConceptScore W4309146016C165464430 @default.
• W4309146016 hasConceptScore W4309146016C31972630 @default.
• W4309146016 hasConceptScore W4309146016C41008148 @default.
• W4309146016 hasConceptScore W4309146016C50644808 @default.
• W4309146016 hasConceptScore W4309146016C80444323 @default.
• W4309146016 hasConceptScore W4309146016C89600930 @default.
• W4309146016 hasFunder F4320321001 @default.
• W4309146016 hasFunder F4320322922 @default.
• W4309146016 hasFunder F4320333335 @default.
• W4309146016 hasLocation W43091460161 @default.
• W4309146016 hasOpenAccess W4309146016 @default.
• W4309146016 hasPrimaryLocation W43091460161 @default.
• W4309146016 hasRelatedWork W1669643531 @default.
• W4309146016 hasRelatedWork W2005437358 @default.
• W4309146016 hasRelatedWork W2008656436 @default.
• W4309146016 hasRelatedWork W2023558673 @default.
• W4309146016 hasRelatedWork W2039154422 @default.
• W4309146016 hasRelatedWork W2122581818 @default.
• W4309146016 hasRelatedWork W2134924024 @default.
• W4309146016 hasRelatedWork W2517104666 @default.
• W4309146016 hasRelatedWork W3169001153 @default.
• W4309146016 hasRelatedWork W2182382398 @default.
• W4309146016 hasVolume "115" @default.
• W4309146016 isParatext "false" @default.
• W4309146016 isRetracted "false" @default.
• W4309146016 workType "article" @default.