FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307635378> ?p ?o ?g. }

• W4307635378 endingPage "10896" @default.
• W4307635378 startingPage "10896" @default.
• W4307635378 abstract "Deep learning has significantly improved the recognition efficiency and accuracy of ground-penetrating radar (GPR) images. A significant number of weight parameters need to be specified, which requires lots of labeled GPR images. However, obtaining the ground-truth subsurface distress labels is challenging as they are invisible. Data augmentation is a predominant method to expand the dataset. The traditional data augmentation methods, such as rotating, scaling, cropping, and flipping, would change the GPR signals’ real features and cause the model’s poor generalization ability. We proposed three GPR data augmentation methods (gain compensation, station spacing, and radar signal mapping) to overcome these challenges by incorporating domain knowledge. Then, the most state-of-the-art model YOLOv7 was applied to verify the effectiveness of these data augmentation methods. The results showed that the proposed data augmentation methods decrease loss function values when the training epochs grow. The performance of the deep learning model gradually became stable when the original datasets were augmented two times, four times, and eight times, proving that the augmented datasets can increase the robustness of the training model. The proposed data augmentation methods can be used to expand the datasets when the labeled training GPR images are insufficient." @default.
• W4307635378 created "2022-11-04" @default.
• W4307635378 creator A5004656256 @default.
• W4307635378 creator A5026623495 @default.
• W4307635378 creator A5051283553 @default.
• W4307635378 creator A5062213210 @default.
• W4307635378 creator A5072331448 @default.
• W4307635378 date "2022-10-27" @default.
• W4307635378 modified "2023-10-15" @default.
• W4307635378 title "GPR Data Augmentation Methods by Incorporating Domain Knowledge" @default.
• W4307635378 cites W1480103247 @default.
• W4307635378 cites W1996107076 @default.
• W4307635378 cites W2395626468 @default.
• W4307635378 cites W2611249899 @default.
• W4307635378 cites W2618530766 @default.
• W4307635378 cites W2741056591 @default.
• W4307635378 cites W2799748868 @default.
• W4307635378 cites W2884561390 @default.
• W4307635378 cites W2911660423 @default.
• W4307635378 cites W2913669962 @default.
• W4307635378 cites W2949936679 @default.
• W4307635378 cites W2955333808 @default.
• W4307635378 cites W2973687803 @default.
• W4307635378 cites W2981807062 @default.
• W4307635378 cites W2989604896 @default.
• W4307635378 cites W3034147267 @default.
• W4307635378 cites W3035571503 @default.
• W4307635378 cites W3089682080 @default.
• W4307635378 cites W3090474196 @default.
• W4307635378 cites W3099319035 @default.
• W4307635378 cites W3106250896 @default.
• W4307635378 cites W3116448918 @default.
• W4307635378 cites W3130011030 @default.
• W4307635378 cites W3146332956 @default.
• W4307635378 cites W3171093259 @default.
• W4307635378 cites W3173245127 @default.
• W4307635378 cites W3192673362 @default.
• W4307635378 cites W3199448129 @default.
• W4307635378 cites W3207234184 @default.
• W4307635378 cites W3213806259 @default.
• W4307635378 cites W3217020410 @default.
• W4307635378 cites W4213290534 @default.
• W4307635378 cites W4213345173 @default.
• W4307635378 cites W4285233081 @default.
• W4307635378 cites W4292550183 @default.
• W4307635378 doi "https://doi.org/10.3390/app122110896" @default.
• W4307635378 hasPublicationYear "2022" @default.
• W4307635378 type Work @default.
• W4307635378 citedByCount "2" @default.
• W4307635378 countsByYear W43076353782023 @default.
• W4307635378 crossrefType "journal-article" @default.
• W4307635378 hasAuthorship W4307635378A5004656256 @default.
• W4307635378 hasAuthorship W4307635378A5026623495 @default.
• W4307635378 hasAuthorship W4307635378A5051283553 @default.
• W4307635378 hasAuthorship W4307635378A5062213210 @default.
• W4307635378 hasAuthorship W4307635378A5072331448 @default.
• W4307635378 hasBestOaLocation W43076353781 @default.
• W4307635378 hasConcept C104317684 @default.
• W4307635378 hasConcept C119857082 @default.
• W4307635378 hasConcept C124101348 @default.
• W4307635378 hasConcept C146849305 @default.
• W4307635378 hasConcept C153180895 @default.
• W4307635378 hasConcept C154945302 @default.
• W4307635378 hasConcept C185592680 @default.
• W4307635378 hasConcept C41008148 @default.
• W4307635378 hasConcept C554190296 @default.
• W4307635378 hasConcept C55493867 @default.
• W4307635378 hasConcept C63479239 @default.
• W4307635378 hasConcept C71813955 @default.
• W4307635378 hasConcept C76155785 @default.
• W4307635378 hasConceptScore W4307635378C104317684 @default.
• W4307635378 hasConceptScore W4307635378C119857082 @default.
• W4307635378 hasConceptScore W4307635378C124101348 @default.
• W4307635378 hasConceptScore W4307635378C146849305 @default.
• W4307635378 hasConceptScore W4307635378C153180895 @default.
• W4307635378 hasConceptScore W4307635378C154945302 @default.
• W4307635378 hasConceptScore W4307635378C185592680 @default.
• W4307635378 hasConceptScore W4307635378C41008148 @default.
• W4307635378 hasConceptScore W4307635378C554190296 @default.
• W4307635378 hasConceptScore W4307635378C55493867 @default.
• W4307635378 hasConceptScore W4307635378C63479239 @default.
• W4307635378 hasConceptScore W4307635378C71813955 @default.
• W4307635378 hasConceptScore W4307635378C76155785 @default.
• W4307635378 hasFunder F4320335777 @default.
• W4307635378 hasIssue "21" @default.
• W4307635378 hasLocation W43076353781 @default.
• W4307635378 hasLocation W43076353782 @default.
• W4307635378 hasOpenAccess W4307635378 @default.
• W4307635378 hasPrimaryLocation W43076353781 @default.
• W4307635378 hasRelatedWork W2356754952 @default.
• W4307635378 hasRelatedWork W2366839571 @default.
• W4307635378 hasRelatedWork W2374146176 @default.
• W4307635378 hasRelatedWork W2524387102 @default.
• W4307635378 hasRelatedWork W2601319996 @default.
• W4307635378 hasRelatedWork W2946057701 @default.
• W4307635378 hasRelatedWork W4223960160 @default.
• W4307635378 hasRelatedWork W4315471419 @default.
• W4307635378 hasRelatedWork W4386931161 @default.

• next