X. Ju
YOU?
Author Swipe
View article: Application of Geometric Deep Learning for Tracking of Hyperons in a Straw Tube Detector
Application of Geometric Deep Learning for Tracking of Hyperons in a Straw Tube Detector Open
We present track reconstruction algorithms based on deep learning, tailored to overcome specific central challenges in the field of hadron physics. Two approaches are used: (i) deep learning (DL) model known as fully-connected neural netwo…
View article: Early continuous blood purification and timely liver transplantation in a neonatal-onset ornithine transcarbamylase deficiency: a case report
Early continuous blood purification and timely liver transplantation in a neonatal-onset ornithine transcarbamylase deficiency: a case report Open
This case highlights the importance of early diagnosis and intervention in neonatal-onset OTCD. Timely application of continuous blood purification (CBP) followed by liver transplantation resulted in significant improvements in both metabo…
View article: Sex differences in preterm birth and the impact of particulate matter pollution: A retrospective cross-sectional study of the Global Burden of Disease 2021
Sex differences in preterm birth and the impact of particulate matter pollution: A retrospective cross-sectional study of the Global Burden of Disease 2021 Open
Objective Preterm birth is a major global public health issue. However, sex difference in incidence and the potential association with air pollution in these disparities have not been fully explored globally. Methods This study is a retros…
View article: Uncertainty Quantification and Propagation for ACORN, a geometric deep learning tracking pipeline for HEP experiments
Uncertainty Quantification and Propagation for ACORN, a geometric deep learning tracking pipeline for HEP experiments Open
We have developed an Uncertainty Quantification process for multistep pipelines and applied it to the ACORN particle tracking pipeline. All our experiments are made using the TrackML open dataset. Using the Monte Carlo Dropout method, we m…
View article: Track reconstruction as a service for collider physics
Track reconstruction as a service for collider physics Open
Optimizing charged-particle track reconstruction algorithms is crucial for efficient event reconstruction in Large Hadron Collider (LHC) experiments due to their significant computational demands. Existing track reconstruction algorithms h…
View article: Integrating particle flavor into deep learning models for hadronization
Integrating particle flavor into deep learning models for hadronization Open
Hadronization models used in event generators are physics-inspired functions with many tunable parameters. Since we do not understand hadronization from first principles, there have been multiple proposals to improve the accuracy of hadron…
View article: Design and Characteristic Research of Hydraulic Power Generation Module for Compact Ocean Thermal Energy Conversion System
Design and Characteristic Research of Hydraulic Power Generation Module for Compact Ocean Thermal Energy Conversion System Open
View article: AthenaTriton: A tool for running machine learning inference as a service in Athena
AthenaTriton: A tool for running machine learning inference as a service in Athena Open
Machine learning (ML)-based algorithms play increasingly important roles in almost all aspects of the data analyses in ATLAS, including detector simulations, event reconstructions, and data analyses. These diverse ML models are being deplo…
View article: The Future of Scheduling in Athena on HPCs
The Future of Scheduling in Athena on HPCs Open
The large increase in luminosity expected from Run 4 of the LHC presents the ATLAS experiment with a new scale of computing challenge, and we can no longer restrict our computing to CPUs in a High Throughput Computing paradigm. We must mak…
View article: Engagement: Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations
Engagement: Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations Open
We present our SciDAC FASTMath-HEP partnership results for tuning generative adversarial models (GANs) for high energy physics applications. The GANs are used in hybrid simulations to accelerate otherwise time-consuming computations. We op…
View article: TrackSorter: A Transformer-based sorting algorithm for track finding in High Energy Physics
TrackSorter: A Transformer-based sorting algorithm for track finding in High Energy Physics Open
Track finding in particle data is a challenging pattern recognition problem in High Energy Physics. It takes as inputs a point cloud of space points and labels them so that space points created by the same particle have the same label. The…
View article: Graph Neural Network-based Tracking as a Service
Graph Neural Network-based Tracking as a Service Open
Recent studies have shown promising results for track finding in dense environments using Graph Neural Network (GNN)-based algorithms. However, GNN-based track finding is computationally slow on CPUs, necessitating the use of coprocessors …
View article: A Language Model for Particle Tracking
A Language Model for Particle Tracking Open
Particle tracking is crucial for almost all physics analysis programs at the Large Hadron Collider. Deep learning models are pervasively used in particle tracking related tasks. However, the current practice is to design and train one deep…
View article: Generative machine learning for detector response modeling with a conditional normalizing flow
Generative machine learning for detector response modeling with a conditional normalizing flow Open
In this paper, we explore the potential of generative machine learning models as an alternative to the computationally expensive Monte Carlo (MC) simulations commonly used by the Large Hadron Collider (LHC) experiments. Our objective is to…
View article: An Application of HEP Track Seeding to Astrophysical Data
An Application of HEP Track Seeding to Astrophysical Data Open
We apply methods of particle track reconstruction in High Energy Physics (HEP) to the search for distinct stellar populations in the Milky Way, using the Gaia EDR3 data set. This was motivated by analogies between the 3D space points in HE…
View article: Physics Performance of the ATLAS GNN4ITk Track Reconstruction Chain
Physics Performance of the ATLAS GNN4ITk Track Reconstruction Chain Open
Particle tracking is vital for the ATLAS physics programs. To cope with the increased number of particles in the High Luminosity LHC, ATLAS is building a new all-silicon Inner Tracker (ITk), consisting of a Pixel and a Strip subdetector. A…
View article: Event Generator Tuning Incorporating Systematic Uncertainty
Event Generator Tuning Incorporating Systematic Uncertainty Open
Event generators play an important role in all physics programs at the Large Hadron Collider and beyond. Dedicated efforts are required to tune the parameters of event generators to accurately describe data. There are many tuning methods r…
View article: Simulation of Hadronic Interactions with Deep Generative Models
Simulation of Hadronic Interactions with Deep Generative Models Open
Accurate simulation of detector responses to hadrons is paramount for all physics programs at the Large Hadron Collider (LHC). Central to this simulation is the modeling of hadronic interactions. Unfortunately, the absence of first-princip…
View article: Towards a distributed heterogeneous task scheduler for the ATLAS offline software framework
Towards a distributed heterogeneous task scheduler for the ATLAS offline software framework Open
With the increased data volumes expected to be delivered by the HLLHC, it becomes critical for the ATLAS experiment to maximize the utilization of available computing resources ranging from conventional GRID clusters to supercomputers and …
View article: Integrating Particle Flavor into Deep Learning Models for Hadronization
Integrating Particle Flavor into Deep Learning Models for Hadronization Open
Hadronization models used in event generators are physics-inspired functions with many tunable parameters. Since we do not understand hadronization from first principles, there have been multiple proposals to improve the accuracy of hadron…
View article: Herwig dataset for HadML particle GAN training
Herwig dataset for HadML particle GAN training Open
These are the simulation data of hadronization using Herwig 7.2.1 Monte Carlo generator, which uses a cluster hadronization model. They have been used for the HadML particle GAN training and evaluation. Two samples are prepared. One uses a…
View article: Herwig dataset for HadML particle GAN training
Herwig dataset for HadML particle GAN training Open
These are the simulation data of hadronization using Herwig 7.2.1 Monte Carlo generator, which uses a cluster hadronization model. They have been used for the HadML particle GAN training and evaluation. Two samples are prepared. One uses a…
View article: Event Generator Tuning Incorporating Systematic Uncertainty
Event Generator Tuning Incorporating Systematic Uncertainty Open
Event generators play an important role in all physics programs at the Large Hadron Collider and beyond. Dedicated efforts are required to tune the parameters of event generators to accurately describe data. There are many tuning methods r…
View article: Simulation of Hadronic Interactions with Deep Generative Models
Simulation of Hadronic Interactions with Deep Generative Models Open
Accurate simulation of detector responses to hadrons is paramount for all physics programs at the Large Hadron Collider (LHC). Central to this simulation is the modeling of hadronic interactions. Unfortunately, the absence of first-princip…
View article: Surrogate Model Based Optimization for Finding Robust Deep Learning Model Architectures
Surrogate Model Based Optimization for Finding Robust Deep Learning Model Architectures Open
Deep Learning (DL) models are increasingly used throughout the sciences. However, their performance and usefulness depend greatly on their architecture which is defined by hyperparameters such as the number of nodes, layers, the learning r…
View article: Fitting a deep generative hadronization model
Fitting a deep generative hadronization model Open
View article: Parton labeling without matching: unveiling emergent labelling capabilities in regression models
Parton labeling without matching: unveiling emergent labelling capabilities in regression models Open
Parton labeling methods are widely used when reconstructing collider events with top quarks or other massive particles. State-of-the-art techniques are based on machine learning and require training data with events that have been matched …
View article: Heterogeneous Graph Neural Network for identifying hadronically decayed tau leptons at the High Luminosity LHC
Heterogeneous Graph Neural Network for identifying hadronically decayed tau leptons at the High Luminosity LHC Open
We present a new algorithm that identifies reconstructed jets originating from hadronic decays of tau leptons against those from quarks or gluons. No tau lepton reconstruction algorithm is used. Instead, the algorithm represents jets as he…
View article: CTD2022: ATLAS ITk Track Reconstruction with a GNN-based Pipeline
CTD2022: ATLAS ITk Track Reconstruction with a GNN-based Pipeline Open
Graph Neural Networks (GNNs) have been shown to produce high accuracy performance on track reconstruction in the TrackML challenge. However, GNNs are less explored in applications with noisy, heterogeneous or ambiguous data. These elements…
View article: CTD2022: ATLAS ITk Track Reconstruction with a GNN-based Pipeline
CTD2022: ATLAS ITk Track Reconstruction with a GNN-based Pipeline Open
Graph Neural Networks (GNNs) have been shown to produce high accuracy performance on track reconstruction in the TrackML challenge. However, GNNs are less explored in applications with noisy, heterogeneous or ambiguous data. These elements…