Donghyeon Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Donghyeon Yu has a total of 101 co-authors. Here are the top co-authors by number of shared publications:
Johan Lim
Department of Statistics, Seoul National University
13 shared publications- Johan Lim
Department of Statistics Seoul National University Seoul South Korea
6 shared publications - Bogang Jun
Research Center for Small Businesses Ecosystem, Inha University , 100 Inha-ro, Incheon 22212
3 shared publications Byung Soo Kim
3 shared publications- Guanghua Xiao
Quantitative Biomedical Research Center, Peter O’Donnell Jr. School of Public Health, University of Texas Southwestern Medical Center, Dallas, USA
3 shared publications - Jaeoh Kim
Department of Statistics and Data Science Inha University Incheon Republic of Korea
3 shared publications
Latest Publications
- 5 June 2025
- Published by Springer Nature in Computational Statistics
- Vol. 40 (7) , 4007-4035
Synthetic data generation method providing enhanced covariance matrix estimation
- 5 June 2025
- Published by Springer Nature in Computational Statistics
- Vol. 40 (7) , 4007-4035
Synthetic data generation method providing enhanced covariance matrix estimation
- Open Access
- 30 April 2025
- Published by The Korean Statistical Society in Korean Journal of Applied Statistics
- Vol. 38 (2) , 299-308
A comprehensive and empirical review of the synthpop for synthetic data generation
Johan Lim, Seungkyu Kim, Donghyeon Yu. Korean J Appl Stat 2025;38:299-308. https://doi.org/10.5351/KJAS.2025.38.2.299
- 30 April 2025
- Published by The Korean Statistical Society in Korean Journal of Applied Statistics
- Vol. 38 (2) , 299-308
Open AccessA comprehensive and empirical review of the synthpop for synthetic data generation
Johan Lim, Seungkyu Kim, Donghyeon Yu. Korean J Appl Stat 2025;38:299-308. https://doi.org/10.5351/KJAS.2025.38.2.299
- Open Access
- 10 February 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (2) , 1-19
Improving Vapor Pressure Prediction Through Integration of Multiple Molecular Representations: A Super Learner Approach
Accurate prediction of vapor pressure is essential in chemical engineering, environmental science, and pharmaceutical development, impacting the volatility and stability of compounds. Traditional methods often fall short for complex and new molecular structures. This study introduces an advanced machine learning approach, integrating graph neural networks (GNNs), and CHEM‐BERT models to improve prediction accuracy. Utilizing the largest dataset to date, we derived comprehensive chemical descriptors and fingerprints. We evaluated 19 predictive models, including ridge regression, random forest, support vector regression, and feed‐forward neural networks, trained on diverse features like PaDEL and Morgan fingerprints, chemical descriptors, and Chem‐BERT embeddings. Central to our methodology is the super learner architecture, which combines 19 multiple models to enhance accuracy. The super learner achieved a root mean squared error (RMSE) of 0.8200, outperforming individual models and previous reports. These successful results highlight the effectiveness of integrating GNNs and Chem‐BERT for capturing detailed molecular information, setting a new benchmark for vapor pressure prediction. This study underscores the value of advanced machine learning techniques and comprehensive datasets, offering a robust tool for researchers and paving the way for future advancements in chemical property prediction.
- 10 February 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (2) , 1-19
Open AccessImproving Vapor Pressure Prediction Through Integration of Multiple Molecular Representations: A Super Learner Approach
Accurate prediction of vapor pressure is essential in chemical engineering, environmental science, and pharmaceutical development, impacting the volatility and stability of compounds. Traditional methods often fall short for complex and new molecular structures. This study introduces an advanced machine learning approach, integrating graph neural networks (GNNs), and CHEM‐BERT models to improve prediction accuracy. Utilizing the largest dataset to date, we derived comprehensive chemical descriptors and fingerprints. We evaluated 19 predictive models, including ridge regression, random forest, support vector regression, and feed‐forward neural networks, trained on diverse features like PaDEL and Morgan fingerprints, chemical descriptors, and Chem‐BERT embeddings. Central to our methodology is the super learner architecture, which combines 19 multiple models to enhance accuracy. The super learner achieved a root mean squared error (RMSE) of 0.8200, outperforming individual models and previous reports. These successful results highlight the effectiveness of integrating GNNs and Chem‐BERT for capturing detailed molecular information, setting a new benchmark for vapor pressure prediction. This study underscores the value of advanced machine learning techniques and comprehensive datasets, offering a robust tool for researchers and paving the way for future advancements in chemical property prediction.
- 24 January 2025
- Published by Oxford University Press (OUP) in Cambridge Journal of Regions, Economy and Society
- Vol. 18 (1) , 41-56
Population concentration in high-complexity regions within city during the heat wave
This study investigates the impact of the 2018 summer heat wave on urban mobility in Seoul and the role of economic complexity in the region’s resilience. Analysis of subway and mobile phone data reveals a significant decrease in the floating population during the extreme heat wave, underscoring the thermal vulnerability of urban areas. However, urban regions with higher complexity demonstrate resilience, attracting more visitors despite high temperatures. Our results suggest the centrality of economic complexity in urban resilience against climate-induced stressors. Additionally, high-complexity small business clusters appear to serve as focal points for sustaining urban vitality in the face of thermal shocks within the city. From a long-term perspective, our results imply that people might become more concentrated in highly complex regions in the era of global warming.
- 24 January 2025
- Published by Oxford University Press (OUP) in Cambridge Journal of Regions, Economy and Society
- Vol. 18 (1) , 41-56
Population concentration in high-complexity regions within city during the heat wave
This study investigates the impact of the 2018 summer heat wave on urban mobility in Seoul and the role of economic complexity in the region’s resilience. Analysis of subway and mobile phone data reveals a significant decrease in the floating population during the extreme heat wave, underscoring the thermal vulnerability of urban areas. However, urban regions with higher complexity demonstrate resilience, attracting more visitors despite high temperatures. Our results suggest the centrality of economic complexity in urban resilience against climate-induced stressors. Additionally, high-complexity small business clusters appear to serve as focal points for sustaining urban vitality in the face of thermal shocks within the city. From a long-term perspective, our results imply that people might become more concentrated in highly complex regions in the era of global warming.
- Open Access
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 65093-65104
Sparse Partial Correlation Estimation With Scaled Lasso and Its GPU-Parallel Algorithm
Sparse partial correlation estimation is a popular topic in high-dimensional data analysis, where nonzero partial correlation represents the conditional dependency between two corresponding variables given the other variables. In the Gaussian graphical model, many methods have been developed using the ℓ 1 regularization to achieve sparsity on conditional dependency. Most of the existing methods impose ℓ 1 penalty on the off-diagonal entries of the precision matrix. This approach may fail to identify the conditional dependencies with partial correlations of moderate magnitudes when the corresponding elements of the precision matrix are relatively small. In this study, we propose a two-stage procedure to estimate sparse partial correlations using scaled Lasso. The proposed procedure resolves the non-convexity of partial correlation estimation by using a consistent estimator of the diagonal elements of the precision matrix from scaled Lasso. Moreover, we develop an efficient algorithm for the proposed method using graphics processing units based on the iterative shrinkage algorithm. Our numerical study shows that the proposed method performs better than the existing methods in terms of edge recovery and the estimation of the partial correlations under the Frobenius norm.
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 65093-65104
Open AccessSparse Partial Correlation Estimation With Scaled Lasso and Its GPU-Parallel Algorithm
Sparse partial correlation estimation is a popular topic in high-dimensional data analysis, where nonzero partial correlation represents the conditional dependency between two corresponding variables given the other variables. In the Gaussian graphical model, many methods have been developed using the ℓ 1 regularization to achieve sparsity on conditional dependency. Most of the existing methods impose ℓ 1 penalty on the off-diagonal entries of the precision matrix. This approach may fail to identify the conditional dependencies with partial correlations of moderate magnitudes when the corresponding elements of the precision matrix are relatively small. In this study, we propose a two-stage procedure to estimate sparse partial correlations using scaled Lasso. The proposed procedure resolves the non-convexity of partial correlation estimation by using a consistent estimator of the diagonal elements of the precision matrix from scaled Lasso. Moreover, we develop an efficient algorithm for the proposed method using graphics processing units based on the iterative shrinkage algorithm. Our numerical study shows that the proposed method performs better than the existing methods in terms of edge recovery and the estimation of the partial correlations under the Frobenius norm.
- Open Access
- 20 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 28490-28505
Technological Leadership in Industry 4.0: A Comparison Between Manufacturing and ICT Sectors Among Korean Firms
This paper examines the technological structures of the manufacturing and the ICT sectors in Korea to examine the potential shift of dominant technological sectors in the era of the Fourth Industrial Revolution (4IR). By using patent data of Korean firms from 1990 to 2021, we find that the manufacturing sector has been the dominant technological leader in Korea in terms of both the number of patents and the diversity of technologies, even in the era of 4IR. Although the ICT sector has shown an increasing focus on Industry 4.0 (I4) technologies after the 2000s, indicating the potential for a shift in dominance in the future, the gap between the two sectors is still significant. The study also reveals that the manufacturing sector tends to diversify technologies, while the ICT sector specializes in several target technologies. Our analysis also suggests that both sectors exhibit path-dependency, with the ICT sector exhibiting stronger characteristics, and firms in both sectors exhibit the tendency of intensive and extensive margin in their patenting activities, but this tendency is stronger for firms in the manufacturing sector.
- 20 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 28490-28505
Open AccessTechnological Leadership in Industry 4.0: A Comparison Between Manufacturing and ICT Sectors Among Korean Firms
This paper examines the technological structures of the manufacturing and the ICT sectors in Korea to examine the potential shift of dominant technological sectors in the era of the Fourth Industrial Revolution (4IR). By using patent data of Korean firms from 1990 to 2021, we find that the manufacturing sector has been the dominant technological leader in Korea in terms of both the number of patents and the diversity of technologies, even in the era of 4IR. Although the ICT sector has shown an increasing focus on Industry 4.0 (I4) technologies after the 2000s, indicating the potential for a shift in dominance in the future, the gap between the two sectors is still significant. The study also reveals that the manufacturing sector tends to diversify technologies, while the ICT sector specializes in several target technologies. Our analysis also suggests that both sectors exhibit path-dependency, with the ICT sector exhibiting stronger characteristics, and firms in both sectors exhibit the tendency of intensive and extensive margin in their patenting activities, but this tendency is stronger for firms in the manufacturing sector.
- 19 October 2022
- Published by Wiley in International Statistical Review
- Vol. 91 (2) , 218-242
Path algorithms for fused lasso signal approximator with application to COVID‐19 spread in Korea
The fused lasso signal approximator (FLSA) is a smoothing procedure for noisy observations that uses fused lasso penalty on unobserved mean levels to find sparse signal blocks. Several path algorithms have been developed to obtain the whole solution path of the FLSA. However, it is known that the FLSA has model selection inconsistency when the underlying signals have a stair-case block, where three consecutive signal blocks are either strictly increasing or decreasing. Modified path algorithms for the FLSA have been proposed to guarantee model selection consistency regardless of the stair-case block. In this paper, we provide a comprehensive review of the path algorithms for the FLSA and prove the properties of the recently modified path algorithms' hitting times. Specifically, we reinterpret the modified path algorithm as the path algorithm for local FLSA problems and reveal the condition that the hitting time for the fusion of the modified path algorithm is not monotone in a tuning parameter. To recover the monotonicity of the solution path, we propose a pathwise adaptive FLSA having monotonicity with similar performance as the modified solution path algorithm. Finally, we apply the proposed method to the number of daily-confirmed cases of COVID-19 in Korea to identify the change points of its spread.
- 19 October 2022
- Published by Wiley in International Statistical Review
- Vol. 91 (2) , 218-242
Path algorithms for fused lasso signal approximator with application to COVID‐19 spread in Korea
The fused lasso signal approximator (FLSA) is a smoothing procedure for noisy observations that uses fused lasso penalty on unobserved mean levels to find sparse signal blocks. Several path algorithms have been developed to obtain the whole solution path of the FLSA. However, it is known that the FLSA has model selection inconsistency when the underlying signals have a stair-case block, where three consecutive signal blocks are either strictly increasing or decreasing. Modified path algorithms for the FLSA have been proposed to guarantee model selection consistency regardless of the stair-case block. In this paper, we provide a comprehensive review of the path algorithms for the FLSA and prove the properties of the recently modified path algorithms' hitting times. Specifically, we reinterpret the modified path algorithm as the path algorithm for local FLSA problems and reveal the condition that the hitting time for the fusion of the modified path algorithm is not monotone in a tuning parameter. To recover the monotonicity of the solution path, we propose a pathwise adaptive FLSA having monotonicity with similar performance as the modified solution path algorithm. Finally, we apply the proposed method to the number of daily-confirmed cases of COVID-19 in Korea to identify the change points of its spread.
- 8 September 2022
- Published by Oxford University Press (OUP) in Cambridge Journal of Regions, Economy and Society
- Vol. 15 (3) , 551-573
The economic resilience of a city: the effect of relatedness on the survival of amenity shops during the COVID-19 pandemic
Amenity clusters consisting of coffee shops, restaurants and other small businesses improve urban life and are a source of employment for city dwellers. Although most small business clusters were hit hard by restrictions imposed during the COVID-19 pandemic, some were able to adapt. What determines the economic resilience of amenity clusters? Using store-location data for Seoul from 2016 to 2021, we identify spatial clusters of amenities, and from that build an amenity space to examine the effect of relatedness on the resilience of each cluster. We find that businesses are more likely to survive when located in clusters of related amenities.
- 8 September 2022
- Published by Oxford University Press (OUP) in Cambridge Journal of Regions, Economy and Society
- Vol. 15 (3) , 551-573
The economic resilience of a city: the effect of relatedness on the survival of amenity shops during the COVID-19 pandemic
Amenity clusters consisting of coffee shops, restaurants and other small businesses improve urban life and are a source of employment for city dwellers. Although most small business clusters were hit hard by restrictions imposed during the COVID-19 pandemic, some were able to adapt. What determines the economic resilience of amenity clusters? Using store-location data for Seoul from 2016 to 2021, we identify spatial clusters of amenities, and from that build an amenity space to examine the effect of relatedness on the resilience of each cluster. We find that businesses are more likely to survive when located in clusters of related amenities.
- Open Access
- 18 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 53324-53343
Comparative Study of CUDA GPU Implementations in Python With the Fast Iterative Shrinkage-Thresholding Algorithm for LASSO
A general-purpose GPU (GPGPU) is employed in a variety of domains, including accelerating the spread of deep natural network models; however, further research into its effective implementation is needed. When using the compute unified device architecture (CUDA), which has recently gained popularity, the situation is analogous to use the GPUs and its memory space. This is due to the lack of a gold standard for selecting the most efficient approach for CUDA GPU parallel computation. Contrarily, as solving the least absolute shrinkage and selection operator (LASSO) regression fully consists of the basic linear algebra operations, the computation using GPGPU is more effective than other models. Additionally, its optimization problem often requires fast and efficient calculations. The purpose of this study is to provide brief introductions to the implementation approaches and numerically compare the computational efficiency of GPU parallel computation with that of the fast iterative shrinkage-thresholding algorithm for LASSO. This study contributes to providing gold standards for the CUDA GPU parallel computation, considering both computational efficiency and ease of implementation. Based on our comparison results, we recommend implementing the CUDA GPU parallel computation using Python, with either a dynamic-link library or PyTorch for the iterative algorithms.
- 18 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 53324-53343
Open AccessComparative Study of CUDA GPU Implementations in Python With the Fast Iterative Shrinkage-Thresholding Algorithm for LASSO
A general-purpose GPU (GPGPU) is employed in a variety of domains, including accelerating the spread of deep natural network models; however, further research into its effective implementation is needed. When using the compute unified device architecture (CUDA), which has recently gained popularity, the situation is analogous to use the GPUs and its memory space. This is due to the lack of a gold standard for selecting the most efficient approach for CUDA GPU parallel computation. Contrarily, as solving the least absolute shrinkage and selection operator (LASSO) regression fully consists of the basic linear algebra operations, the computation using GPGPU is more effective than other models. Additionally, its optimization problem often requires fast and efficient calculations. The purpose of this study is to provide brief introductions to the implementation approaches and numerically compare the computational efficiency of GPU parallel computation with that of the fast iterative shrinkage-thresholding algorithm for LASSO. This study contributes to providing gold standards for the CUDA GPU parallel computation, considering both computational efficiency and ease of implementation. Based on our comparison results, we recommend implementing the CUDA GPU parallel computation using Python, with either a dynamic-link library or PyTorch for the iterative algorithms.
- Open Access
- 16 April 2022
- Published by Springer Nature in Computational Statistics
- Vol. 38 (1) , 217-242
An efficient GPU-parallel coordinate descent algorithm for sparse precision matrix estimation via scaled lasso
- 16 April 2022
- Published by Springer Nature in Computational Statistics
- Vol. 38 (1) , 217-242
Open AccessAn efficient GPU-parallel coordinate descent algorithm for sparse precision matrix estimation via scaled lasso