T. Yong-Jin Han
YOU?
Author Swipe
View article: Novel anatomical landmark guided puncture method in L4/L5 spine posterior interlaminar endoscopic surgery: a technical note and case series
Novel anatomical landmark guided puncture method in L4/L5 spine posterior interlaminar endoscopic surgery: a technical note and case series Open
Background L4/L5 segment lumbar disc herniation and canal stenosis commonly cause low back and leg pain. Posterior interlaminar spine endoscopy has proven efficacy, but puncture positioning relies on experience and requires multiple fluoro…
View article: Percutaneous endoscopic interlaminar decompression for degenerative scoliosis in the elderly: a safe and effective minimally invasive alternative
Percutaneous endoscopic interlaminar decompression for degenerative scoliosis in the elderly: a safe and effective minimally invasive alternative Open
Background Elderly patients with degenerative scoliosis combined with spinal stenosis present significant treatment challenges. Traditional open fusion surgery carries high risks and complications in this population. This study investigate…
View article: Entity-enhanced BERT for medical specialty prediction based on clinical questionnaire data
Entity-enhanced BERT for medical specialty prediction based on clinical questionnaire data Open
A medical specialty prediction system for remote diagnosis can reduce the unexpected costs incurred by first-visit patients who visit the wrong hospital department for their symptoms. To develop medical specialty prediction systems, severa…
View article: The molecular mechanisms and new classification of resistant starch – A review
The molecular mechanisms and new classification of resistant starch – A review Open
View article: Accelerating the design of lattice structures using machine learning
Accelerating the design of lattice structures using machine learning Open
View article: Transparency and color tunable electro-optical device using colloidal core/shell nanoparticles
Transparency and color tunable electro-optical device using colloidal core/shell nanoparticles Open
According to one embodiment, a product is a mixture including a solvent and generally spherical colloidal nanoparticles, the colloidal nanoparticles each having a core and a shell surrounding the core, and an electrode. In addition, the mi…
View article: High surface area, electrically conductive nanocarbon-supported metal oxide
High surface area, electrically conductive nanocarbon-supported metal oxide Open
A metal oxide-carbon composite includes a carbon aerogel with an oxide overcoat. The metal oxide-carbon composite is made by providing a carbon aerogel, immersing the carbon aerogel in a metal oxide sol under a vacuum, raising the carbon a…
View article: Organized energetic composites based on micro and nanostructures and methods thereof
Organized energetic composites based on micro and nanostructures and methods thereof Open
An ordered energetic composite structure according to one embodiment includes an ordered array of metal fuel portions; and an oxidizer in gaps located between the metal fuel portions. An ordered energetic composite structure according to a…
View article: Rapid detection and identification of energetic materials with surface enhanced raman spectrometry (SERS)
Rapid detection and identification of energetic materials with surface enhanced raman spectrometry (SERS) Open
In one embodiment, a system includes a plurality of metal nanoparticles functionalized with a plurality of organic molecules tethered thereto, wherein the plurality of organic molecules preferentially interact with one or more analytes whe…
View article: Deep learning of electrochemical CO<sub>2</sub> conversion literature reveals research trends and directions
Deep learning of electrochemical CO<sub>2</sub> conversion literature reveals research trends and directions Open
Machine learning (ML)-based protocol for selecting highly relevant papers, extracting important experimental data, and analyzing research trends & directions focusing on the field of CO 2 reduction reactions (CO 2 RRs).
View article: Explainable machine learning in materials science
Explainable machine learning in materials science Open
Machine learning models are increasingly used in materials studies because of their exceptional accuracy. However, the most accurate machine learning models are usually difficult to explain. Remedies to this problem lie in explainable arti…
View article: A Strategic Approach to Machine Learning for Material Science: How to Tackle Real-World Challenges and Avoid Pitfalls
A Strategic Approach to Machine Learning for Material Science: How to Tackle Real-World Challenges and Avoid Pitfalls Open
The exponential growth and success of Machine Learning (ML) has resulted in its application in all scientific domains including Material Science. Advancement in experimental techniques has led to an increase in the volume of material scien…
View article: Attribution-Driven Explanation of the Deep Neural Network Model via Conditional Microstructure Image Synthesis
Attribution-Driven Explanation of the Deep Neural Network Model via Conditional Microstructure Image Synthesis Open
The materials science community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite their effectiveness in building highly predictive models, e.g., predicting mater…
View article: A study of real-world micrograph data quality and machine learning model robustness
A study of real-world micrograph data quality and machine learning model robustness Open
View article: Leveraging Uncertainty from Deep Learning for Trustworthy Material Discovery Workflows
Leveraging Uncertainty from Deep Learning for Trustworthy Material Discovery Workflows Open
In this paper, we leverage predictive uncertainty of deep neural networks to answer challenging questions material scientists usually encounter in machine learning-based material application workflows. First, we show that by leveraging pre…
View article: In situ Raman Spectroscopy of COOH-functionalized SWCNTs Trapped with Optoelectronic Tweezers
In situ Raman Spectroscopy of COOH-functionalized SWCNTs Trapped with Optoelectronic Tweezers Open
Optoelectronic tweezers (OETs) were used to trap and deposit aqueous dispersions of carboxylic-acid-functionalized single-walled carbon nanotube bundles. Dark-field video microscopy was used to visualize the dynamics of the bundles both wi…
View article: Predicting Energetics Materials’ Crystalline Density from Chemical Structure by Machine Learning
Predicting Energetics Materials’ Crystalline Density from Chemical Structure by Machine Learning Open
To expedite new molecular compound development, a long-sought goal within the chemistry community has been to predict molecules' bulk properties of interest a priori to synthesis from a chemical structure alone. In this work, we demonstrat…
View article: Size-Dependent Alloying Ability of Immiscible W-Cu Bimetallic Nanoparticles: A Theoretical and Experimental Study
Size-Dependent Alloying Ability of Immiscible W-Cu Bimetallic Nanoparticles: A Theoretical and Experimental Study Open
The preparation of alloyed bimetallic nanoparticles (BNPs) between immiscible elements is always a huge challenge due to the lack of thermodynamic driving forces. W–Cu is a typical immiscible binary system, and it is difficult to alloy the…
View article: MR-GAN: Manifold Regularized Generative Adversarial Networks for Scientific Data
MR-GAN: Manifold Regularized Generative Adversarial Networks for Scientific Data Open
Despite the growing interest in applying generative adversarial networks (GANs) in complex scientific applications, training GANs on scientific data remains a challenging problem from both theoretical and practical standpoints. One reason …
View article: Crystal structure prediction of energetic materials and a twisted arene with Genarris and GAtor
Crystal structure prediction of energetic materials and a twisted arene with Genarris and GAtor Open
A molecular crystal structure prediction workflow, based on the random structure generator, Genarris, and the genetic algorithm (GA), GAtor, is successfully applied to two energetic materials and a chiral arene.
View article: Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery Workflows
Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery Workflows Open
In this paper, we leverage predictive uncertainty of deep neural networks to answer challenging questions material scientists usually encounter in machine learning based materials applications workflows. First, we show that by leveraging p…
View article: Data-driven materials research enabled by natural language processing and information extraction
Data-driven materials research enabled by natural language processing and information extraction Open
Given the emergence of data science and machine learning throughout all aspects of society, but particularly in the scientific domain, there is increased importance placed on obtaining data. Data in materials science are particularly heter…
View article: Automated Identification of Molecular Crystals’ Packing Motifs
Automated Identification of Molecular Crystals’ Packing Motifs Open
Packing motifs-patterns in how molecules orient relative to one another in a crystal structure-are an important concept in many subdisciplines of materials science because of correlations observed between specific packing motifs and proper…
View article: Correlating dynamic microstructure to observed color in electrophoretic displays via <i>in situ</i> small-angle x-ray scattering
Correlating dynamic microstructure to observed color in electrophoretic displays via <i>in situ</i> small-angle x-ray scattering Open
Electrophoretic deposition (EPD) is an industrially relevant and scalable technique used to form particle deposits from colloidal suspensions. Highly concentrated particle suspensions generally prevent real-time in situ microscopy observat…
View article: Probabilistic Neighbourhood Component Analysis: Sample Efficient Uncertainty Estimation in Deep Learning
Probabilistic Neighbourhood Component Analysis: Sample Efficient Uncertainty Estimation in Deep Learning Open
While Deep Neural Networks (DNNs) achieve state-of-the-art accuracy in various applications, they often fall short in accurately estimating their predictive uncertainty and, in turn, fail to recognize when these predictions may be wrong. S…
View article: Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design
Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design Open
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in building predictive models, fundamental challenges exist in extrac…
View article: Actionable Attribution Maps for Scientific Machine Learning
Actionable Attribution Maps for Scientific Machine Learning Open
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in building predictive models, fundamental challenges exist in extrac…
View article: Nanomaterial Synthesis Insights from Machine Learning of Scientific Articles by Extracting, Structuring, and Visualizing Knowledge
Nanomaterial Synthesis Insights from Machine Learning of Scientific Articles by Extracting, Structuring, and Visualizing Knowledge Open
Nanomaterials of varying compositions and morphologies are of interest for many applications from catalysis to optics, but the synthesis of nanomaterials and their scale-up are most often time-consuming and Edisonian processes. Information…
View article: Mix-n-Match: Ensemble and Compositional Methods for Uncertainty\n Calibration in Deep Learning
Mix-n-Match: Ensemble and Compositional Methods for Uncertainty\n Calibration in Deep Learning Open
This paper studies the problem of post-hoc calibration of machine learning\nclassifiers. We introduce the following desiderata for uncertainty calibration:\n(a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We\nsh…
View article: Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning Open
This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show …