Neural networks for reconstruction and uncertainty quantification of fast-ion phase-space distributions using FILD and INPA measurements
BS Schmidt, J Rueda-Rueda, J Galdon-Quíroga… - Nuclear …, 2024 - iopscience.iop.org
This study introduces the use of a deep convolutional neural network for reconstructing fast-
ion velocity distributions from fast-ion loss detectors and imaging neutral particle analyzers …
ion velocity distributions from fast-ion loss detectors and imaging neutral particle analyzers …
Enhancing disruption prediction through Bayesian neural network in KSTAR
In this research, we develop a data-driven disruption predictor based on Bayesian deep
probabilistic learning, capable of predicting disruptions and modeling uncertainty in KSTAR …
probabilistic learning, capable of predicting disruptions and modeling uncertainty in KSTAR …
[PDF][PDF] Optimal Fractional-Order PID Controllers Design for Plasma Current and Horizontal Position Control in IR-T1 Tokamak Based on Particle-Swarm Optimization
A Naghidokht, B Khanbabaei - Journal of Theoretical and Applied …, 2024 - researchgate.net
Tokamak reactors' performance is inherently tied to the precise control of plasma shape,
position, and current while staying within the operational constraints, specifically managing …
position, and current while staying within the operational constraints, specifically managing …
Comparación de métodos de explicación del comportamiento de modelos de aprendizaje profundo en el procesamiento de imágenes digitales
VR Jimenez Lucumi, FB Mercado Sarmiento - 2024 - repositorio.uss.edu.pe
Este estudio tuvo como objetivo comparar diferentes métodos de explicación del
comportamiento de modelos de aprendizaje profundo en el procesamiento de imágenes …
comportamiento de modelos de aprendizaje profundo en el procesamiento de imágenes …