Biomechanical surrogate modelling using stabilized vectorial greedy kernel methods
This work addresses biomechanical modeling challenges for clinical applications, representing an incremental improvement in existing kernel methods.
The authors tackled the problem of improving accuracy and stability in biomechanical surrogate modeling by extending stabilized greedy kernel approximation algorithms to vectorial outputs. Their experiments on human spine modeling data showed that the new stabilized algorithms achieved improved accuracy and stability compared to non-stabilized versions.
Greedy kernel approximation algorithms are successful techniques for sparse and accurate data-based modelling and function approximation. Based on a recent idea of stabilization of such algorithms in the scalar output case, we here consider the vectorial extension built on VKOGA. We introduce the so called $γ$-restricted VKOGA, comment on analytical properties and present numerical evaluation on data from a clinically relevant application, the modelling of the human spine. The experiments show that the new stabilized algorithms result in improved accuracy and stability over the non-stabilized algorithms.