Results 61 to 70 of about 3,934 (193)

CAPO: Causal-Adaptive Preference Optimization for Diffusion Models via Causal Inference Uncertainty

IEEE Access
Post-training alignment of diffusion models based on human feedback uniformly applies equal weights to all preference pairs, ignoring the inherent aleatoric and epistemic uncertainty in feedback, leading to overfitting on noisy signals and insufficient ...
Sihan Hu
doaj   +1 more source

Automation and Active Learning for the Multi‐Objective Optimization of Antibody Formulations

Advanced Science, Volume 13, Issue 55, 5 October 2026.
Successful antibody formulation necessitates balancing factors such as thermal stability, colloidal stability, and viscosity across a vast excipient design space. This work integrates robotic liquid handling, high‐throughput biophysical characterization, and multi‐objective Bayesian optimization in an iterative closed‐loop Design‐Build‐Test‐Learn cycle.
D. Christopher Radford, Matthew Tamasi, Elena Di Mare, Adam J. Gormley   +3 more
wiley   +1 more source

Physics‐encoded transfer learning for scale‐up modeling of CHO cell bioreactors

AIChE Journal, Volume 72, Issue 10, October 2026.
Abstract Developing reliable predictive models for mammalian cell bioreactors, particularly Chinese hamster ovary (CHO) cultures widely used in biopharmaceutical manufacturing, remains challenging due to severe data scarcity in industrial‐scale reactors.
Muyang Li, Ming Xiao, Zhe Wu
wiley   +1 more source

Taguchi–Bayesian Sampling: A Roadmap for Polymer Database Construction Toward Small Representative Machine Learning

Advanced Intelligent Discovery, Volume 2, Issue 5, October 2026.
This article establishes a Taguchi–Bayesian sampling strategy to reconstruct polymer processing–property landscape at minimal sampling cost, generically building the roadmap for materials database construction from sampling their vast design space. This sampling strategy is featured by an alternating lesson between uniformity and representativeness ...
Han Liu, Liantang Li
wiley   +1 more source

TrustSpec: Simulation‐Grounded Physics‐Driven Spectral Inversion With Uncertainty Quantification for SiC Epitaxial Thickness Metrology

Engineering Reports, Volume 8, Issue 10, October 2026.
TrustSpec reuses a single spectral digital twin both to train a deep ensemble and to verify each prediction via analysis‐by‐synthesis. A two‐channel trust plane automatically releases, reviews, or rejects every SiC epitaxial thickness reading, achieving 0.110 μm mean error with full out‐of‐distribution rejection in simulation.
Zijie Nie, Shunlin Yang, Qingjie Guo
wiley   +1 more source

Analytical Framework for System‐Level Fragility Surfaces of Reinforced Concrete Bridges Under Mainshock‐Aftershock Sequences

Earthquake Engineering &Structural Dynamics, Volume 55, Issue 13, Page 3264-3284, 25 October 2026.
ABSTRACT Conventional single intensity measure (IM) fragility approaches with simplified component dependency assumptions overlook the progressive damage accumulation and evolving inter‐component correlations that govern system behavior under mainshock‐aftershock (MSAS) loading.
Muhammad Rashid, Mayuko Nishio
wiley   +1 more source

Uncertainty in property valuation: aleatoric and epistemic challenges in the Nigerian real estate market

Acta Scientiarum Polonorum. Administratio Locorum
Motivation: Real estate markets, particularly in emerging economies such as Nigeria, are subject to significant uncertainties. These can be broadly categorized into aleatoric uncertainties, which arise from inherent market variability, and epistemic ...
Nonso Izuchukwu Ewurum, Njideka Maryclara Aguome, Cezary Kowalczyk, Ikechukwu William-Johnson Ozigbo, Jacek Kil   +4 more
doaj   +1 more source

Rheokinetic Study of Polycarbodiimide Formation From 4,4’‐MDI Using Rotational Viscometry—A Characterization of Gelation

Macromolecular Materials and Engineering, Volume 311, Issue 10, October 2026.
Temperature‐dependent rheokinetic analysis reveals how MDI solution evolves into a transparent polycarbodiimide gel. Rotational viscometry, isoviscosity mapping, and fractional‐order modeling quantify viscosity growth, gel‐time estimation, and apparent activation energy, providing a compact framework for understanding carbodiimide‐driven gelation in ...
Marcell Dániel Csécsi, Péter Tóth, László Farkas, Christa Fittschen, Milán Szőri, Béla Viskolcz   +5 more
wiley   +1 more source

A Practical Tutorial on Physics‐Informed Networks for Pharmacometrics and Quantitative Systems Pharmacology

CPT: Pharmacometrics &Systems Pharmacology, Volume 15, Issue 10, October 2026.
ABSTRACT Inverse problems in pharmacometrics and quantitative systems pharmacology (QSP) often involve sparse, noisy data, limited measurable states, and complex dynamical systems. Traditional parameter estimation methods can struggle with ill‐posed problems, stiffness, discontinuities, and gray‐box scenarios where only part of the system dynamics is ...
Nazanin Ahmadi Daryakenari, Mohammad Kohandel   +1 more
wiley   +1 more source

An ensemble learning framework for streamflow reconstruction incorporating aleatoric and epistemic uncertainty

Journal of Hydrology: Regional Studies
Study Region: South Sulawesi, Indonesia Study Focus: Machine learning (ML) models have been utilized to reconstruct streamflow data over data-sparse regions, but their aleatoric and epistemic uncertainty have been limitedly assessed. To address this gap,
Devi Icha Ludyawati, Byeong-Hee Kim, Jonghun Kam   +2 more
doaj   +1 more source