Jihoon Kang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jihoon Kang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Su Hong Min6 shared publications
- Jong-Sung Yoon
Department of Fire and Disaster Prevention Engineering Inje University Gyeongsangnam-do Republic of Korea
5 shared publications - Joon Hun Kim
Director Haekwang Eng Jeollanam-do Korea
2 shared publications - Jung-A Yang
Konkuk University (Seoul, Korea, Republic of)
2 shared publications - Mandeuk Lee
CEO Haekwang Eng Haenam-Gun Jeollanam-do Korea
2 shared publications - Hyo Beom Heo
Department of Mechanical Engineering, Chungnam National University, 99 Daehak-ro, Yuseong-Gu, Daejeon 34134, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 21 April 2026
- Published by Springer Nature in Research Square
Stochastic Response Analysis for Multivariate Manufacturing Processes
In modern manufacturing, artificial intelligence and data analytics techniques are frequently used and developed for various industrial applications. The final purpose of the smart-factory problem is to automatically control the process recipe so that the manufacturer can obtain the desired standard or yield of the production processes. A datadriven model predictive control (D-MPC) strategy is widely used to quantitatively improve control systems. In this study, we introduce a novel modeling and control method termed stochastic response modeling (SRM). The method performs properly when a target variable has zero-inflated, intermittent, and time-invariant patterns. The proposed method comprises two main concepts: stochastic transformation of the response variable and coefficient adjustment algorithms that can address current limitations in the manufacturing field. Results of industrial case studies demonstrate the efficacy of SRM, especially in terms of the robustness and usability of model-based control. We believe that the proposed method can optimize the overall manufacturing process, such that high-yield production is always possible.
- 21 April 2026
- Published by Springer Nature in Research Square
Open AccessStochastic Response Analysis for Multivariate Manufacturing Processes
In modern manufacturing, artificial intelligence and data analytics techniques are frequently used and developed for various industrial applications. The final purpose of the smart-factory problem is to automatically control the process recipe so that the manufacturer can obtain the desired standard or yield of the production processes. A datadriven model predictive control (D-MPC) strategy is widely used to quantitatively improve control systems. In this study, we introduce a novel modeling and control method termed stochastic response modeling (SRM). The method performs properly when a target variable has zero-inflated, intermittent, and time-invariant patterns. The proposed method comprises two main concepts: stochastic transformation of the response variable and coefficient adjustment algorithms that can address current limitations in the manufacturing field. Results of industrial case studies demonstrate the efficacy of SRM, especially in terms of the robustness and usability of model-based control. We believe that the proposed method can optimize the overall manufacturing process, such that high-yield production is always possible.
- Open Access
- 31 December 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (6) , 700
Corrigendum to: Random Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
Corrigendum to: Random Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
- 31 December 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (6) , 700
Open AccessCorrigendum to: Random Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
Corrigendum to: Random Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
- Open Access
- 31 December 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (6) , 699
Corrigendum to: Optimization of Input Variables for Salinity Modeling in the Nakdong River Estuary Using Exploratory Data Analysis
Corrigendum to: Optimization of Input Variables for Salinity Modeling in the Nakdong River Estuary Using Exploratory Data Analysis
- 31 December 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (6) , 699
Open AccessCorrigendum to: Optimization of Input Variables for Salinity Modeling in the Nakdong River Estuary Using Exploratory Data Analysis
Corrigendum to: Optimization of Input Variables for Salinity Modeling in the Nakdong River Estuary Using Exploratory Data Analysis
- Open Access
- 31 October 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (5) , 503-511
Design and Application of a Physics-Informed Machine Learning Model for Salinity Prediction in the Nakdong River Estuary
This paper proposes a hybrid framework to predict salinity in the Nakdong River Estuary by combining physics-based modeling with machine learning. Motivated by the increasing complexity in salinity intrusion owing to frequent barrage operations and nonlinear hydrological changes, we developed a physics-informed machine learning (PIML) model. The model integrates a physical salinity intrusion curve with a long short-term memory (LSTM) network, using a customized loss function that dynamically balances each component. Validation was performed using observation data from January to June 2022 at multiple hydrological stations. A moving window method was applied for sequential training, and a genetic algorithm was used to optimize physical parameters. The results showed that during sharp salinity surges, the physical model provided more accurate predictions, whereas the data-driven model performed better during stable periods. Overall, the PIML approach achieved the lowest mean squared error (MSE) and demonstrated robust and generalized performance. These results highlight the model’s ability to enhance prediction reliability by selectively emphasizing physical or data-driven components, which is particularly useful in estuarine environments with variable tidal and inflow dynamics.
- 31 October 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (5) , 503-511
Open AccessDesign and Application of a Physics-Informed Machine Learning Model for Salinity Prediction in the Nakdong River Estuary
This paper proposes a hybrid framework to predict salinity in the Nakdong River Estuary by combining physics-based modeling with machine learning. Motivated by the increasing complexity in salinity intrusion owing to frequent barrage operations and nonlinear hydrological changes, we developed a physics-informed machine learning (PIML) model. The model integrates a physical salinity intrusion curve with a long short-term memory (LSTM) network, using a customized loss function that dynamically balances each component. Validation was performed using observation data from January to June 2022 at multiple hydrological stations. A moving window method was applied for sequential training, and a genetic algorithm was used to optimize physical parameters. The results showed that during sharp salinity surges, the physical model provided more accurate predictions, whereas the data-driven model performed better during stable periods. Overall, the PIML approach achieved the lowest mean squared error (MSE) and demonstrated robust and generalized performance. These results highlight the model’s ability to enhance prediction reliability by selectively emphasizing physical or data-driven components, which is particularly useful in estuarine environments with variable tidal and inflow dynamics.
- Open Access
- 31 August 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (4) , 379-393
Optimization of Input Variables for Salinity Modeling in the Nakdong River Estuary Using Exploratory Data Analysis
The Nakdong River Estuary is a vital ecological and water resource facing management challenges due to seawater intrusion and seasonal hydrological changes. The continuous opening of the estuarine bank since 2022 has increased the need for accurate salinity prediction to support ecosystem restoration and water-resource management. This study aims to improve the reliability and efficiency of salinity prediction models by optimizing the input variables using exploratory data analysis. Multidimensional observational data collected from January 2019 to June 2022 were analyzed to identify the statistical characteristics and seasonal variability of key factors. Principal component analysis was used to select critical variables, and a data-driven variable selection process was implemented. Experiments using a long short-term memory deep learning model showed that the optimized variable set improved the prediction performance by approximately 4.5% compared to models using all available variables. These results demonstrate that a data-centric approach enables the development of robust and interpretable prediction models that can be utilized by non-specialists in environmental hydraulics. The findings are expected to expand the practical application of artificial intelligence technologies in environmental management and contribute to the development of data-driven decision-support systems in estuarine environments.
- 31 August 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 39 (4) , 379-393
Open AccessOptimization of Input Variables for Salinity Modeling in the Nakdong River Estuary Using Exploratory Data Analysis
The Nakdong River Estuary is a vital ecological and water resource facing management challenges due to seawater intrusion and seasonal hydrological changes. The continuous opening of the estuarine bank since 2022 has increased the need for accurate salinity prediction to support ecosystem restoration and water-resource management. This study aims to improve the reliability and efficiency of salinity prediction models by optimizing the input variables using exploratory data analysis. Multidimensional observational data collected from January 2019 to June 2022 were analyzed to identify the statistical characteristics and seasonal variability of key factors. Principal component analysis was used to select critical variables, and a data-driven variable selection process was implemented. Experiments using a long short-term memory deep learning model showed that the optimized variable set improved the prediction performance by approximately 4.5% compared to models using all available variables. These results demonstrate that a data-centric approach enables the development of robust and interpretable prediction models that can be utilized by non-specialists in environmental hydraulics. The findings are expected to expand the practical application of artificial intelligence technologies in environmental management and contribute to the development of data-driven decision-support systems in estuarine environments.
- Open Access
- 26 August 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
Random Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
Random Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
- 26 August 2025
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
Open AccessRandom Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
Random Forest Model for Salinity Prediction in the Nakdong River Estuary Reflecting Spatio-temporal Lag Effects
- 28 February 2024
- Published by Korean Institute of Information Technology in The Journal of Korean Institute of Information Technology
- Vol. 22 (2) , 21-33
Multivariate Prediction of Socio-Economic Indicators using Recursive Bayesian Ensemble Model
코로나 펜데믹 이후로 국내외 사회경제의 불확실성이 증가하고 있으며, 이에 효과적인 대응을 위한 사회경제지표 예측은 필수적인 상황이다. 기존에는 사회경제지표 예측 방법으로 방정식, 시계열, 머신러닝 모델 등이 주로 사용되었으나 사회경제지표의 특징과 예측모델의 한계점 등으로 인해 저조한 예측성능을 보이고 있다. 이에, 본 연구에서는 재귀적 베이지안 앙상블 모델을 토대로 시간 흐름에 따른 불확실성이 큰 사회경제 지표를 안정적으로 예측하는 방법론을 제안한다. 제안모델은 예측원리가 다른 시계열, 머신러닝 등의 다양한 예측모델을 확률적으로 조합하고, 베이지안 업데이트 기법을 통해 모델을 순차적으로 업데이트한다. 본 연구는 사회경제지표 예측을 통해 제안모델의 예측 성능과 안정성의 우수함을 입증하였다.
- 28 February 2024
- Published by Korean Institute of Information Technology in The Journal of Korean Institute of Information Technology
- Vol. 22 (2) , 21-33
Multivariate Prediction of Socio-Economic Indicators using Recursive Bayesian Ensemble Model
코로나 펜데믹 이후로 국내외 사회경제의 불확실성이 증가하고 있으며, 이에 효과적인 대응을 위한 사회경제지표 예측은 필수적인 상황이다. 기존에는 사회경제지표 예측 방법으로 방정식, 시계열, 머신러닝 모델 등이 주로 사용되었으나 사회경제지표의 특징과 예측모델의 한계점 등으로 인해 저조한 예측성능을 보이고 있다. 이에, 본 연구에서는 재귀적 베이지안 앙상블 모델을 토대로 시간 흐름에 따른 불확실성이 큰 사회경제 지표를 안정적으로 예측하는 방법론을 제안한다. 제안모델은 예측원리가 다른 시계열, 머신러닝 등의 다양한 예측모델을 확률적으로 조합하고, 베이지안 업데이트 기법을 통해 모델을 순차적으로 업데이트한다. 본 연구는 사회경제지표 예측을 통해 제안모델의 예측 성능과 안정성의 우수함을 입증하였다.
- Open Access
- 21 July 2023
- Published by PHM Society in International Journal of Prognostics and Health Management
- Vol. 14 (2)
RUL Prognostics
With the rising complexity of manufacturing processes, resulting from rapid industrial development, the utilization of remaining useful lifecycle (RUL) prediction, based on failure physics and traditional reliability, has remained limited. Although data-driven approaches of RUL prediction were developed using machine learning algorithms, uncertainty-induced challenges have emerged, such as sensor noise and modeling error. To address these uncertainty-induced problems, this study proposes a stochastic ensemble-modeling concept for improving the RUL prediction result. The proposed ensemble model combines artificial degradation patterns and fitness weights, which incorporate formulas reflecting failure patterns and various reliability function data with the observed degradation factor. Furthermore, a recursive Bayesian updating technique, reflecting the difference between expected and observed remaining life sequentially, was leveraged to reduce the prediction uncertainty. Moreover, we comparatively studied the predictive performance of the proposed model (recursive Bayesian ensemble model) against an existing baseline method (exponentially weighted linear regression model). Through simulation and case datasets, this experiment demonstrated the robustness and utility of the proposed algorithm.
- 21 July 2023
- Published by PHM Society in International Journal of Prognostics and Health Management
- Vol. 14 (2)
Open AccessRUL Prognostics
With the rising complexity of manufacturing processes, resulting from rapid industrial development, the utilization of remaining useful lifecycle (RUL) prediction, based on failure physics and traditional reliability, has remained limited. Although data-driven approaches of RUL prediction were developed using machine learning algorithms, uncertainty-induced challenges have emerged, such as sensor noise and modeling error. To address these uncertainty-induced problems, this study proposes a stochastic ensemble-modeling concept for improving the RUL prediction result. The proposed ensemble model combines artificial degradation patterns and fitness weights, which incorporate formulas reflecting failure patterns and various reliability function data with the observed degradation factor. Furthermore, a recursive Bayesian updating technique, reflecting the difference between expected and observed remaining life sequentially, was leveraged to reduce the prediction uncertainty. Moreover, we comparatively studied the predictive performance of the proposed model (recursive Bayesian ensemble model) against an existing baseline method (exponentially weighted linear regression model). Through simulation and case datasets, this experiment demonstrated the robustness and utility of the proposed algorithm.
- 24 March 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 121
Clustering ensemble-based novelty score for outlier detection
- 24 March 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 121
Clustering ensemble-based novelty score for outlier detection
- 22 June 2022
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 121 (5-6) , 3439-3451
Recognition of unknown wafer defect via optimal bin embedding technique
- 22 June 2022
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 121 (5-6) , 3439-3451
Recognition of unknown wafer defect via optimal bin embedding technique