Classification of tokamak plasma confinement states with convolutional recurrent neural networks

F Matos, V Menkovski, F Felici, A Pau, F Jenko… - Nuclear …, 2020 - iopscience.iop.org
During a tokamak discharge, the plasma can vary between different confinement regimes:
low (L), high (H) and, in some cases, a temporary (intermediate state), called dithering (D). In …

Plasma confinement mode classification using a sequence-to-sequence neural network with attention

F Matos, V Menkovski, A Pau, G Marceca… - Nuclear …, 2021 - iopscience.iop.org
In a typical fusion experiment, the plasma can have several possible confinement modes. At
the tokamak à configuration variable, aside from the low (L) and high (H) confinement …

Automated estimation of L/H transition times at JET by combining Bayesian statistics and support vector machines

J Vega, A Murari, G Vagliasindi, GA Rattá… - Nuclear …, 2009 - iopscience.iop.org
This paper describes a pattern recognition method for off-line estimation of both L/H and H/L
transition times in JET. The technique is based on a combined classifier to identify the …

[PDF][PDF] Автоматическое определение изменений эмоционального состояния по речевому сигналу

АА Лукьяница, АГ Шишкин - Речевые, 2009 - lab314.brsu.by
This paper reports results in development of a computer system that explores the emotional
state of a human by his speech. The system consists of two parts: speech features extraction …

Realization of automatic data cleaning and feedback conditioning for J-TEXT ECEI signals based on machine learning

Z Zhang, Z Yang, Y Gao, X Zha, Z Jin, Q Luo… - Fusion Engineering and …, 2022 - Elsevier
Abstract In recent years, Electron Cyclotron Emission Imaging (ECEI) diagnostics and many
other imaging diagnostics have become increasingly important in magnetic confinement …

Modeling fusion data in probabilistic metric spaces: Applications to the identification of confinement regimes and plasma disruptions

G Verdoolaege, G Karagounis, A Murari… - Fusion Science and …, 2012 - Taylor & Francis
Pattern recognition is becoming an increasingly important tool for making inferences from
the massive amounts of data produced in fusion experiments. In this work, we present an …

Automatic location of L/H transition times for physical studies with a large statistical basis

S González, J Vega, A Murari, A Pereira… - Plasma Physics and …, 2012 - iopscience.iop.org
Completely automatic techniques to estimate and validate L/H transition times can be
essential in L/H transition analyses. The generation of databases with hundreds of transition …

Neural Network-Based Confinement Mode Prediction for Real-Time Disruption Avoidance

D Orozco, B Sammuli, J Barr, W Wehner… - … on Plasma Science, 2022 - ieeexplore.ieee.org
Reliable disruption avoidance techniques are critical for the development of safe and
economically viable fusion reactors. This incipient need has driven the fusion community to …

Deep Learning for Tomography, State Classification and Event Detection in Nuclear Fusion Plasmas

F Duarte Pinto de Almeida Matos - 2021 - mediatum.ub.tum.de
Nuclear fusion experiments regularly generate large amounts of data that can constitute a
rich source of information for new scientific and engineering insights. Yet in many cases, the …

The NNTMM code: Mathematical modeling, optimization, and data analysis through neural networks

DP Kostomarov, FS Zaitsev, AA Luk'yanitsa… - Moscow University …, 2013 - Springer
The concept, functional capabilities, graphic interface, and application technology for the
NNTMM code (Neural Network Tool for Mathematical Modeling), designed for analyzing …