Conformal quantile regression endows existing neural constitutive models with distribution-free probabilistic predictions for anisotropic soft tissues while preserving thermodynamic consistency via a polyconvex strain-invariant formulation.
A Bayesian approach to accounting for variability in mechanical properties in biomaterials
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we present an approach for modeling bio-tissues that incorporates the variability in properties as part of their characteristics. This is achieved by considering the parameters of the model of a biomaterial to themselves be random variables and represented by a probability distribution over the space of parameters. This probability distribution is obtained by the systematic use of Bayesian inference together with a continuum mechanics based solution of a boundary value problem. We illustrate this approach by characterizing sheep arteries by using a combination of experimental data and different hyperelastic models. Furthermore, we also develop a model based Bayesian classification of new data into different classes based on the computed model parameter probability distribution.
fields
physics.comp-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Conformal Quantile Regression for Neural Probabilistic Constitutive Modeling
Conformal quantile regression endows existing neural constitutive models with distribution-free probabilistic predictions for anisotropic soft tissues while preserving thermodynamic consistency via a polyconvex strain-invariant formulation.