English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Traditional computational methods, such as the finite element analysis, haveprovided valuable insights into uncovering the underlying mechanisms of brainphysical behaviors. However, precise predictions of brain physics requireeffective constitutive models to represent the intricate mechanical propertiesof brain tissue. In this study, we aimed to identify the most favorableconstitutive material model for human brain tissue. To achieve this, we appliedartificial neural network and multiple regression methods to a generalizationof widely accepted classic models, and compared the results obtained from thesetwo approaches. To evaluate the applicability and efficacy of the model, allsetups were kept consistent across both methods, except for the approach toprevent potential overfitting. Our results demonstrate that artificial neuralnetworks are capable of automatically identifying accurate constitutive modelsfrom given admissible estimators. Nonetheless, the five-term and two-termneural network models trained under single-mode and multi-mode loadingscenarios, were found to be suboptimal and could be further simplified intotwo-term and single-term, respectively, with higher accuracy using multipleregression. Our findings highlight the importance of hyperparameters for theartificial neural network and emphasize the necessity for detailedcross-validations of regularization parameters to ensure optimal selection at aglobal level in the development of material constitutive models. This studyvalidates the applicability and accuracy of artificial neural network toautomatically discover constitutive material models with proper regularizationas well as the benefits in model simplification without compromising accuracyfor traditional multivariable regression.

Exploring hyperelastic material model discovery for human brain cortex: multivariate analysis vs. artificial neural network approaches