FastSVD-ML–ROM: A reduced-order modeling framework based on machine learning for real-time applications

GI Drakoulas, TV Gortsas, GC Bourantas… - Computer Methods in …, 2023 - Elsevier
Digital twins have emerged as a key technology for optimizing the performance of
engineering products and systems. High-fidelity numerical simulations constitute the …

Ensemble Kalman filtering meets Gaussian process SSM for non-mean-field and online inference

Z Lin, Y Sun, F Yin, AH Thiéry - IEEE Transactions on Signal …, 2024 - ieeexplore.ieee.org
The Gaussian process state-space models (GPSSMs) represent a versatile class of data-
driven nonlinear dynamical system models. However, the presence of numerous latent …

An explainable machine learning-based probabilistic framework for the design of scaffolds in bone tissue engineering

G Drakoulas, T Gortsas, E Polyzos… - … and Modeling in …, 2024 - Springer
Recently, 3D-printed biodegradable scaffolds have shown great potential for bone repair in
critical-size fractures. The differentiation of the cells on a scaffold is impacted among other …

Bayesian optimization with ensemble learning models and adaptive expected improvement

KD Polyzos, Q Lu, GB Giannakis - ICASSP 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
Optimizing a black-box function that is expensive to evaluate emerges in a gamut of
machine learning and artificial intelligence applications including drug discovery, policy …

Physics-based reduced order modeling for uncertainty quantification of guided wave propagation using bayesian optimization

GI Drakoulas, TV Gortsas, D Polyzos - Engineering Applications of Artificial …, 2024 - Elsevier
Guided wave propagation (GWP) is commonly employed for the design of SHM systems.
However, GWP is sensitive to variations in the material properties, often leading to false …

Weighted ensembles for active learning with adaptivity

KD Polyzos, Q Lu, GB Giannakis - arXiv preprint arXiv:2206.05009, 2022 - arxiv.org
Labeled data can be expensive to acquire in several application domains, including medical
imaging, robotics, and computer vision. To efficiently train machine learning models under …

Surrogate modeling for Bayesian optimization beyond a single Gaussian process

Q Lu, KD Polyzos, B Li, GB Giannakis - arXiv preprint arXiv:2205.14090, 2022 - arxiv.org
Bayesian optimization (BO) has well-documented merits for optimizing black-box functions
with an expensive evaluation cost. Such functions emerge in applications as diverse as …

Graph-guided gaussian process-based diagnosis of cvd severity with uncertainty measures

S Tassi, V Kigka, P Siogkas… - 2023 45th Annual …, 2023 - ieeexplore.ieee.org
The severity of coronary artery disease can be assessed invasively using the Fractional
Flow Reserve (FFR) index which is a useful diagnostic tool for the clinicians to select the …

Active sampling over graphs for Bayesian reconstruction with Gaussian ensembles

KD Polyzos, Q Lu, GB Giannakis - 2022 56th Asilomar …, 2022 - ieeexplore.ieee.org
Graph-guided semi-supervised learning (SSL) has gained popularity in several network
science applications, including biological, social, and financial ones. SSL becomes …

Bayesian optimization for online management in dynamic mobile edge computing

J Yan, Q Lu, GB Giannakis - IEEE Transactions on Wireless …, 2023 - ieeexplore.ieee.org
Recent years have witnessed the emergence of mobile edge computing (MEC), on the
premise of a cost-effective enhancement in the computational ability of hardware …