FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385655218> ?p ?o ?g. }

• W4385655218 endingPage "1632" @default.
• W4385655218 startingPage "1617" @default.
• W4385655218 abstract "Purpose In recent years, the convolutional neural network (CNN) based deep learning approach has succeeded in data-mining the relationship between microstructures and macroscopic properties of materials. However, such CNN models usually rely heavily on a large set of labeled images to ensure the accuracy and generalization ability of the predictive models. Unfortunately, in many fields, acquiring image data is expensive and inconvenient. This study aims to propose a data augmentation technique to enhance the performance of the CNN models for linking microstructural images to the macroscopic properties of composites. Design/methodology/approach Microstructures of composites are synthesized using discrete element simulations and Potts kinetic Monte Carlo simulations. Macroscopic properties such as the elastic modulus, Poisson's ratio, shear modulus, coefficient of thermal expansion, and triple-phase boundary length density are extracted on representative volume elements. The CNN model is trained using the 3D microstructural images as inputs and corresponding macroscopic properties as the labels. The comparison of the predictive performance of the CNN models with and without data augmentation treatment are compared. Findings The comparison between the prediction performance of CNN models with and without data augmentation showed that the former reduced the weighted mean absolute percentage error (WMAPE) for the prediction from 5.1627% to 1.7014%. This significant reduction signifies that the proposed data augmentation method can effectively enhance the generalization ability and robustness of CNN models. Originality/value This study demonstrates that data augmentation is beneficial for solving the problems of model overfitting, data scarcity, and sample imbalance for CNN-based deep learning tasks at a low cost. By developing more and advanced data augmentation techniques, deep learning accelerated homogenization will boost the multi-scale computational mechanics and materials." @default.
• W4385655218 created "2023-08-09" @default.
• W4385655218 creator A5018860229 @default.
• W4385655218 creator A5024499651 @default.
• W4385655218 creator A5058604134 @default.
• W4385655218 creator A5077513075 @default.
• W4385655218 creator A5077865670 @default.
• W4385655218 creator A5088810627 @default.
• W4385655218 date "2023-08-09" @default.
• W4385655218 modified "2023-10-12" @default.
• W4385655218 title "Data augmentation and data mining towards microstructure and property relationship for composites" @default.
• W4385655218 cites W1995562189 @default.
• W4385655218 cites W2000598250 @default.
• W4385655218 cites W2042793618 @default.
• W4385655218 cites W2085858509 @default.
• W4385655218 cites W2103018059 @default.
• W4385655218 cites W2516865405 @default.
• W4385655218 cites W2538920246 @default.
• W4385655218 cites W2777965033 @default.
• W4385655218 cites W2783424964 @default.
• W4385655218 cites W2794022343 @default.
• W4385655218 cites W2883108341 @default.
• W4385655218 cites W2883588054 @default.
• W4385655218 cites W2887978733 @default.
• W4385655218 cites W2900595477 @default.
• W4385655218 cites W2928714920 @default.
• W4385655218 cites W2954089860 @default.
• W4385655218 cites W2954996726 @default.
• W4385655218 cites W2981868774 @default.
• W4385655218 cites W2991294993 @default.
• W4385655218 cites W3025110191 @default.
• W4385655218 cites W3029869103 @default.
• W4385655218 cites W3060435609 @default.
• W4385655218 cites W3099319035 @default.
• W4385655218 cites W3118651212 @default.
• W4385655218 cites W3121876815 @default.
• W4385655218 cites W3161383970 @default.
• W4385655218 cites W3183903096 @default.
• W4385655218 cites W3187661730 @default.
• W4385655218 cites W4200519059 @default.
• W4385655218 cites W4225821375 @default.
• W4385655218 cites W4280599295 @default.
• W4385655218 cites W4289110087 @default.
• W4385655218 cites W4293099969 @default.
• W4385655218 doi "https://doi.org/10.1108/ec-10-2022-0639" @default.
• W4385655218 hasPublicationYear "2023" @default.
• W4385655218 type Work @default.
• W4385655218 citedByCount "0" @default.
• W4385655218 crossrefType "journal-article" @default.
• W4385655218 hasAuthorship W4385655218A5018860229 @default.
• W4385655218 hasAuthorship W4385655218A5024499651 @default.
• W4385655218 hasAuthorship W4385655218A5058604134 @default.
• W4385655218 hasAuthorship W4385655218A5077513075 @default.
• W4385655218 hasAuthorship W4385655218A5077865670 @default.
• W4385655218 hasAuthorship W4385655218A5088810627 @default.
• W4385655218 hasConcept C104317684 @default.
• W4385655218 hasConcept C11413529 @default.
• W4385655218 hasConcept C134306372 @default.
• W4385655218 hasConcept C150217764 @default.
• W4385655218 hasConcept C154945302 @default.
• W4385655218 hasConcept C177148314 @default.
• W4385655218 hasConcept C185592680 @default.
• W4385655218 hasConcept C22019652 @default.
• W4385655218 hasConcept C33923547 @default.
• W4385655218 hasConcept C41008148 @default.
• W4385655218 hasConcept C50644808 @default.
• W4385655218 hasConcept C55493867 @default.
• W4385655218 hasConcept C58489278 @default.
• W4385655218 hasConcept C63479239 @default.
• W4385655218 hasConcept C81363708 @default.
• W4385655218 hasConceptScore W4385655218C104317684 @default.
• W4385655218 hasConceptScore W4385655218C11413529 @default.
• W4385655218 hasConceptScore W4385655218C134306372 @default.
• W4385655218 hasConceptScore W4385655218C150217764 @default.
• W4385655218 hasConceptScore W4385655218C154945302 @default.
• W4385655218 hasConceptScore W4385655218C177148314 @default.
• W4385655218 hasConceptScore W4385655218C185592680 @default.
• W4385655218 hasConceptScore W4385655218C22019652 @default.
• W4385655218 hasConceptScore W4385655218C33923547 @default.
• W4385655218 hasConceptScore W4385655218C41008148 @default.
• W4385655218 hasConceptScore W4385655218C50644808 @default.
• W4385655218 hasConceptScore W4385655218C55493867 @default.
• W4385655218 hasConceptScore W4385655218C58489278 @default.
• W4385655218 hasConceptScore W4385655218C63479239 @default.
• W4385655218 hasConceptScore W4385655218C81363708 @default.
• W4385655218 hasIssue "7/8" @default.
• W4385655218 hasLocation W43856552181 @default.
• W4385655218 hasOpenAccess W4385655218 @default.
• W4385655218 hasPrimaryLocation W43856552181 @default.
• W4385655218 hasRelatedWork W1574414179 @default.
• W4385655218 hasRelatedWork W2490526372 @default.
• W4385655218 hasRelatedWork W2922305141 @default.
• W4385655218 hasRelatedWork W3185156046 @default.
• W4385655218 hasRelatedWork W4221142204 @default.
• W4385655218 hasRelatedWork W4281702477 @default.
• W4385655218 hasRelatedWork W4297676672 @default.
• W4385655218 hasRelatedWork W4362597605 @default.
• W4385655218 hasRelatedWork W4376166922 @default.

• next