AIMC Topic: Uncertainty

Clear Filters Showing 1 to 10 of 737 articles

Bayesian neural networks for genomic prediction: uncertainty quantification and SNP interpretation with SHAP and GWAS.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik
This study presents a Bayesian neural networks framework with LASSO regularization and the GSMeSP interpretability tool, enabling accurate, uncertainty-aware, and biologically interpretable genomic prediction. Deep learning offers significant potenti...

Selective classification with machine learning uncertainty estimates improves ACS prediction: a retrospective study in the prehospital setting.

Scientific reports
Accurate identification of acute coronary syndrome (ACS) in the prehospital setting is important for timely treatments that reduce damage to the compromised myocardium. Current machine learning approaches lack sufficient performance to safely rule-in...

Towards trustworthy AI in radiotherapy: a comprehensive review of uncertainty-aware techniques.

Physics in medicine and biology
. Uncertainty quantification (UQ) has emerged as a crucial component in deep learning-based medical image analysis, particularly in radiotherapy (RT). Addressing uncertainty is essential for improving the reliability, interpretability, and clinical a...

A novel algorithm for model uncertainty reduction in trapezoidal fuzzy fault tree risk assessment.

PloS one
Intelligent risk assessment in complex systems increasingly relies on methods like trapezoidal fuzzy fault trees. However, conventional techniques often struggle with accurately calculating top-event probabilities and handling model uncertainty, whic...

Incorporating and quantifying deformable image registration uncertainties in dose accumulation: a feasibility study on the benefit of online adaptive therapy.

Physics in medicine and biology
. Accurate dose accumulation relies on deformable image registration (DIR) to track dose across multiple images. However, DIR introduces uncertainties that can impact cumulative dose distributions. In this study, we present a probabilistic framework ...

Uncertainty quantification enables reliable deep learning for protein-ligand binding affinity prediction.

Scientific reports
Deep learning (DL) algorithms have increasingly been applied to predict protein-ligand binding affinity, a critical step in drug design. Yet, many models still struggle to generalize to unseen data, and when coupled with the absence of confidence est...

Advances in surrogate modeling for biological agent-based simulations: trends, challenges, and future prospects.

Journal of mathematical biology
Agent-based modeling (ABM) is a powerful computational approach for studying complex biological and biomedical systems, yet its widespread use remains limited by significant computational demands. As models become increasingly sophisticated, the numb...

Transformer-based deep learning for adaptive pedagogy under uncertain student preferences.

Scientific reports
As educational environments become increasingly heterogeneous, conventional teaching strategies often fall short in accommodating the diverse and evolving learning behaviors of students, particularly when individual learning preferences are ambiguous...

Robust adaptive control with lumped model uncertainty and wind disturbance estimation for airship trajectory tracking.

PloS one
The robotic airship can be used as an aerostatic platform for many potential applications, for example, communication, hovering payload deliveries, data-gathering for research studies, etc. These applications require a fully autonomous perspective of...

Methods and Uncertainty in Predictions of Arsenic Exposure and Health Outcomes for Private Well Users in Massachusetts.

Environmental science & technology
In the United States, most people get their drinking water from public water systems, whose quality is regulated by the Safe Drinking Water Act; however, an estimated 40 million people rely on unregulated private wells. In Massachusetts ∼500,000 peop...