Results 81 to 90 of about 3,934 (193)

Uncertainty-Aware Time Series Anomaly Detection

Future Internet
Traditional anomaly detection methods in time series data often struggle with inherent uncertainties like noise and missing values. Indeed, current approaches mostly focus on quantifying epistemic uncertainty and ignore data-dependent uncertainty ...
Paul Wiessner, Grigor Bezirganyan, Sana Sellami, Richard Chbeir, Hans-Joachim Bungartz   +4 more
doaj   +1 more source

Field-Level Uncertainty Quantification for AI-Based Ship Hull Surface Pressure Prediction

Journal of Marine Science and Engineering
This study investigates uncertainty quantification for field-level ship hull surface pressure predictions using a U-Net-based data-driven model. A speed-conditioned U-Net is trained on a large CFD dataset covering multiple ship types and velocity ...
Jeongbeom Seo, Inwon Lee
doaj   +1 more source

STACI: Spatio-Temporal Aleatoric Conformal Inference

CoRR
Fitting Gaussian Processes (GPs) provides interpretable aleatoric uncertainty quantification for estimation of spatio-temporal fields. Spatio-temporal deep learning models, while scalable, typically assume a simplistic independent covariance matrix for the response, failing to capture the underlying correlation structure.
Brandon R. Feng, David Keetae Park, Xihaier Luo, Arantxa Urdangarin, Shinjae Yoo, Brian J. Reich   +5 more
openaire   +2 more sources

An uncertainty-aware domain adaptive semantic segmentation framework

Autonomous Intelligent Systems
Semantic segmentation is significant to realize the scene understanding of autonomous driving. Due to the lack of annotated real-world data, the technology of domain adaptation is applied so that the model is trained on the synthetic data and inferred on
Huilin Yin, Pengyu Wang, Boyu Liu, Jun Yan   +3 more
doaj   +1 more source

Probabilistic Neural Networks (PNNs) for Modeling Aleatoric Uncertainty in Scientific Machine Learning

IEEE Access
This paper investigates the use of probabilistic neural networks (PNNs) to model aleatoric uncertainty, which refers to the inherent variability in the input-output relationships of a system, often characterized by unequal variance or heteroscedasticity.
Farhad Pourkamali-Anaraki, Jamal F. Husseini, Scott E. Stapleton   +2 more
doaj   +1 more source

Performance of Conformal Prediction in Capturing Aleatoric Uncertainty

2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV ...
Misgina Tsighe Hagos, Claes Lundström
openaire   +3 more sources

Multidimensional Distributional Neural Network Output Demonstrated in Super‐Resolution of Surface Wind Speed

Journal of Geophysical Research: Machine Learning and Computation
Accurate quantification of uncertainty in neural network predictions remains a central challenge for scientific applications involving high‐dimensional, correlated data.
Harrison J. Goldwyn, Mitchell Krock, Johann Rudi, Daniel Getter, Julie Bessac   +4 more
doaj   +1 more source

Label-wise Aleatoric and Epistemic Uncertainty Quantification

CoRR
Uncertainty in Artificial Intelligence.
Sale, Yusuf, Hofman, Paul, Löhr, Timo, Wimmer, Lisa, Nagler, Thomas, Hüllermeier, Eyke   +5 more
openaire   +5 more sources

Informing synthetic passive microwave predictions through Bayesian deep learning with uncertainty decomposition

Environmental Data Science
Space-borne passive microwave (PMW) data provide rich information on atmospheric state, including cloud structure and underlying surface properties. However, PMW data are sparse and limited due to low Earth orbit collection, resulting in coarse Earth ...
Pedro Ortiz, Eleanor Casas, Marko Orescanin, Scott W. Powell, Veljko Petkovic   +4 more
doaj   +1 more source

Hybrid data augmentation for uncertainty mitigation in machine learning based fault diagnosis of pressurized water reactor nuclear power plants

Nuclear Engineering and Technology
Uncertainty in machine learning-based fault diagnosis for nuclear power plants (NPPs) poses a critical challenge due to limited and noisy operational data.
Fazle Haseeb, Minjun Peng, Furqan Arshad, Khan Awais, Wasiq Ali   +4 more
doaj   +1 more source