Related papers: Identifying L-H transition in HL-2A through deep l…
Extreme Learning Machine (ELM) is an emerging learning paradigm for nonlinear regression problems and has shown its effectiveness in the machine learning community. An important feature of ELM is that the learning speed is extremely fast…
Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks; however, their large size makes their inference slow and computationally expensive. Focusing on this problem, we propose to…
The ability to rapidly detect hydrogen gas upon occurrence of a leak is critical for the safe large-scale implementation of hydrogen (energy) technologies. However, to date, no technically viable sensor solution exists that meets the…
Deep Learning (DL) methods show very good performance when trained on large, balanced data sets. However, many practical problems involve imbalanced data sets, or/and classes with a small number of training samples. The performance of DL…
Recent observations in HL-2A tokamak give new experimental evidences of energetic particle mode (EPM) avalanche. In a strong EPM burst, the mode structure propagates radially outward within two hundred Alfv\'en time, while the frequency of…
Magnetically confined plasmas are often subject to relaxation oscillations accompanied by large transport events. This is particularly the case for the high confinement regime of tokamaks where these events are termed edge localized modes…
Long-tailed out-of-distribution (LT-OOD) detection is often addressed with specialized training, including auxiliary out-of-distribution (OOD) data, abstention heads, contrastive objectives, energy losses, or gradient-conflict control. We…
Periodic edge localized modes (ELMs) are the non-linear consequences of pressure-gradient-driven ballooning modes and current-driven peeling modes becoming unstable in the pedestal region of high confinement fusion plasmas. In future…
We consider a resource-constrained Edge Device (ED), such as an IoT sensor or a microcontroller unit, embedded with a small-size ML model (S-ML) for a generic classification application and an Edge Server (ES) that hosts a large-size ML…
We set up a mapping procedure able to translate the evolution of the radial profile of fast ions, interacting with Toroidal Alfv\'en Eigenmodes, into the dynamics of an equivalent one dimensional bump-on-tail system. We apply this mapping…
The plasma response to an externally generated, static, n=2, resonant magnetic perturbation (RMP) in the pedestal region of DIII-D discharge #158115 is investigated. In this particular discharge, the resonant amplitudes of the RMP are…
Training large language models (LLMs) at the network edge faces fundamental challenges arising from device resource constraints, severe data heterogeneity, and heightened privacy risks. To address these challenges, we propose ELSA…
A neural network model, EFITNN, has been developed capable of real-time magnetic equilibrium reconstruction based on HL-3 tokamak magnetic measurement signals. The model processes inputs from 68 channels of magnetic measurement data…
Advancements in deep learning and machine learning have improved the ability to model complex, nonlinear relationships, such as those encountered in complex material inverse problems. However, the effectiveness of these methods often…
We propose a systematic methodology to identify the topological phase transition through a self-supervised machine learning model, which is trained to correlate system parameters to the non-local observables in time-of-flight experiments of…
Endpoint Detection and Remediation (EDR) platforms are essential for identifying and responding to cyber threats. This study presents a novel approach using Large Language Models (LLMs) to detect Hands-on-Keyboard (HOK) cyberattacks. Our…
Pellet ELM triggering is a well established scheme for decreasing the time between two successive ELM crashes below its natural value. Reliable ELM pacing has been demonstrated experimentally in several devices increasing the ELM frequency…
Edge-Localized-Mode (ELM) suppression by resonant magnetic perturbations (RMPs) generally occurs over very narrow ranges of the plasma current (or magnetic safety factor q95) in the DIII-D tokamak. However, wide q95 ranges of ELM…
In this paper a deep learning architecture is presented that can, in real time, detect the 2D locations of certain landmarks of physical tools, such as a hammer or screwdriver. To avoid the labor of manual labeling, the network is trained…
In the initial stages of operation for future tokamak, facing limited data availability, deploying data-driven disruption predictors requires optimal performance with minimal use of new device data. This paper studies the issue of data…