A5035407171- Bayesian Methods and Mixture Models
- Statistical Methods and Bayesian Inference
- Statistical Methods and Inference
- Gaussian Processes and Bayesian Inference
- Blind Source Separation Techniques
- Spectroscopy and Chemometric Analyses
- Climate variability and models
- COVID-19 epidemiological studies
- SARS-CoV-2 and COVID-19 Research
- Hepatocellular Carcinoma Treatment and Prognosis
- Hydrological Forecasting Using AI
- Meteorological Phenomena and Simulations
- Markov Chains and Monte Carlo Methods
- Financial Risk and Volatility Modeling
- Liver Disease Diagnosis and Treatment
- Statistical Distribution Estimation and Applications
- Vaccine Coverage and Hesitancy
- Hydrology and Drought Analysis
- MRI in cancer diagnosis
- Cerebrovascular and Carotid Artery Diseases
- COVID-19 Clinical Research Studies
- Probabilistic and Robust Engineering Design
- Remote Sensing in Agriculture
- Fault Detection and Control Systems
- Soil Geostatistics and Mapping
Inha University
2005-2025
Jeonbuk National University
2016-2019
Korea University
2015-2019
Chonbuk National University Hospital
2019
University of Michigan–Ann Arbor
2019
Catholic University of Korea
2018
Statistics Korea
2015-2017
National University of Singapore
2017
National Cancer Center
2011-2015
Seoul National University
2011-2014
Methylmercury is well known for causing adverse health effects in the brain and nervous system. Estimating elimination constant derived from biological half-life of methylmercury blood or hair an important part calculating guidelines intake. Thus, this study was conducted to estimate Korean adults. We used a one-compartment model with direct relationship between concentrations daily dietary intake methylmercury. quantified between-person variability population, informative priors were...
The cultivation of abalone, a species with high economic value, faces significant challenges due to its slow growth rate and sensitivity environmental conditions, resulting in prolonged periods increased mortality risks. To address these challenges, we propose novel probabilistic machine learning approach based on Bayesian framework predict abalone by modeling key factors, including water temperature, pH, salinity, nutrient supply, dissolved oxygen levels. proposed method employs weighted...
ABSTRACT Accurate prediction of vapor pressure is essential in chemical engineering, environmental science, and pharmaceutical development, impacting the volatility stability compounds. Traditional methods often fall short for complex new molecular structures. This study introduces an advanced machine learning approach, integrating graph neural networks (GNNs), CHEM‐BERT models to improve accuracy. Utilizing largest dataset date, we derived comprehensive descriptors fingerprints. We...
We consider a novel Bayesian nonparametric model for density estimation with an underlying spatial structure. The is built on class of species sampling models, which are discrete random probability measures that can be represented as mixture support points and weights. Specifically, we construct collection spatially dependent models propose based this collection. key idea the introduction dependence by modeling weights through conditional autoregressive model. present extensive simulation...
In the following article, we consider approximate Bayesian computation (ABC) inference. We introduce a method for numerically approximating ABC posteriors using multilevel Monte Carlo (MLMC). A sequential version of approach is developed and it shown under some assumptions that given level mean square error, this has lower cost than i.i.d. sampling from most accurate approximation. Several numerical examples are given.
Abstract This article proposes a statistical method based on the regularized canonical correlation analysis (RCCA) to improve conventional (CCA) for seasonal climate prediction. The fundamental idea of this is combine regularization principle with classical CCA handle high‐dimensional data in which number variables larger than observations. study focuses prediction future precipitation boreal summer (June‐July‐August, JJA) both global and regional scales. We apply RCCA JJA hindcast/forecast...
The Bayesian spectral analysis model (BSAM) is a powerful tool to deal with semiparametric methods in regression and density estimation based on the representation of Gaussian process priors. bsamGP package for R provides comprehensive set programs implementation fully BSAM. Currently, includes additive models regression, generalized estimation. In particular, deals constrained monotone, convex/concave, S-shaped U-shaped functions by modeling derivatives as squared processes. also contains...
This paper presents a Bayesian analysis of partially linear additive models for quantile regression. We develop semiparametric approach to regression using spectral representation the nonparametric functions and Dirichlet process (DP) mixture error distribution. also consider variable selection procedures both parametric components in model structure based on shrinkage priors via stochastic search algorithm. Based proposed referred as BSAQ, inference is considered estimation selection. For...
This paper provides a Bayesian estimation procedure for monotone regression models incorporating the trend constraint subject to uncertainty. For modeling with stochastic restrictions, we propose Bernstein polynomial model using two-stage hierarchical prior distributions based on family of rectangle-screened multivariate Gaussian extended from work Gurtis and Ghosh [7 S.M. Curtis S.K. Ghosh, A variable selection approach monotonic polynomials, J. Appl. Stat. 38 (2011), pp. 961–976. doi:...
In this paper, we estimate the seroprevalence against COVID-19 by country and derive over world. To among adults, use serological surveys (also called serosurveys) conducted within each country. When serosurveys are incorporated to world seroprevalence, there two issues. First, countries in which a survey has not been conducted. Second, sample collection dates differ from We attempt tackle these problems using vaccination data, confirmed cases national statistics. construct Bayesian models...
ABSTRACT The determination of flash points is a critical aspect chemical safety, essential for assessing explosion hazards and fire risks associated with flammable solutions. With the advent new blends increasing complexity waste management, need accurate reliable point prediction methods has become more pronounced. This study introduces novel predictive approach using Bayesian kernel machine regression (BKMR) Gaussian process priors, designed to meet growing demand precise estimation in...