Zobrazeno 1 - 10
of 800
pro vyhledávání: '"Daniele, E."'
Autor:
Menon, Karthik, Zanoni, Andrea, Khan, Owais, Geraci, Gianluca, Nieman, Koen, Schiavazzi, Daniele E., Marsden, Alison L.
Simulations of coronary hemodynamics have improved non-invasive clinical risk stratification and treatment outcomes for coronary artery disease, compared to relying on anatomical imaging alone. However, simulations typically use empirical approaches
Externí odkaz:
http://arxiv.org/abs/2409.02247
Estimation of cardiovascular model parameters from electronic health records (EHR) poses a significant challenge primarily due to lack of identifiability. Structural non-identifiability arises when a manifold in the space of parameters is mapped to a
Externí odkaz:
http://arxiv.org/abs/2408.08264
When predicting physical phenomena through simulation, quantification of the total uncertainty due to multiple sources is as crucial as making sure the underlying numerical model is accurate. Possible sources include irreducible aleatoric uncertainty
Externí odkaz:
http://arxiv.org/abs/2408.07201
Autor:
Zanoni, Andrea, Geraci, Gianluca, Salvador, Matteo, Marsden, Alison L., Schiavazzi, Daniele E.
We present a new approach for nonlinear dimensionality reduction, specifically designed for computationally expensive mathematical models. We leverage autoencoders to discover a one-dimensional neural active manifold (NeurAM) capturing the model outp
Externí odkaz:
http://arxiv.org/abs/2408.03534
Autor:
Richter, Jakob, Nitzler, Jonas, Pegolotti, Luca, Menon, Karthik, Biehler, Jonas, Wall, Wolfgang A., Schiavazzi, Daniele E., Marsden, Alison L., Pfaller, Martin R.
Boundary condition (BC) calibration to assimilate clinical measurements is an essential step in any subject-specific simulation of cardiovascular fluid dynamics. Bayesian calibration approaches have successfully quantified the uncertainties inherent
Externí odkaz:
http://arxiv.org/abs/2404.14187
Computational models of the cardiovascular system are increasingly used for the diagnosis, treatment, and prevention of cardiovascular disease. Before being used for translational applications, the predictive abilities of these models need to be thor
Externí odkaz:
http://arxiv.org/abs/2401.04889
Autor:
Zanoni, Andrea, Geraci, Gianluca, Salvador, Matteo, Menon, Karthik, Marsden, Alison L., Schiavazzi, Daniele E.
We study the problem of multifidelity uncertainty propagation for computationally expensive models. In particular, we consider the general setting where the high-fidelity and low-fidelity models have a dissimilar parameterization both in terms of num
Externí odkaz:
http://arxiv.org/abs/2312.12361
Autor:
Lee, John D., Richter, Jakob, Pfaller, Martin R., Szafron, Jason M., Menon, Karthik, Zanoni, Andrea, Ma, Michael R., Feinstein, Jeffrey A., Kreutzer, Jacqueline, Marsden, Alison L., Schiavazzi, Daniele E.
The substantial computational cost of high-fidelity models in numerical hemodynamics has, so far, relegated their use mainly to offline treatment planning. New breakthroughs in data-driven architectures and optimization techniques for fast surrogate
Externí odkaz:
http://arxiv.org/abs/2312.00854
Use of generative models and deep learning for physics-based systems is currently dominated by the task of emulation. However, the remarkable flexibility offered by data-driven architectures would suggest to extend this representation to other aspect
Externí odkaz:
http://arxiv.org/abs/2307.12586
Autor:
Wang, Yu, Cobian, Emma R., Lee, Jubilee, Liu, Fang, Hauenstein, Jonathan D., Schiavazzi, Daniele E.
Variational inference is an increasingly popular method in statistics and machine learning for approximating probability distributions. We developed LINFA (Library for Inference with Normalizing Flow and Annealing), a Python library for variational i
Externí odkaz:
http://arxiv.org/abs/2307.04675