Sun Ho Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sun Ho Kim has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Dong-Wan Seo
College of Pharmacy, Dankook University, Cheonan 31116, Republic of Korea
3 shared publications - Myung Joo Kang
College of Pharmacy, Dankook University, 119 Dandae-ro, Dongnam-gu, Cheonan 31116, Chungnam, Republic of Korea
3 shared publications - Su Hyeon Han
Department of Mechanical Engineering, Kongju National University, 1223-24, Cheonan-daero, Seobuk-gu, Cheonan-si 31080, Republic of Korea
3 shared publications - Jong-Seok Oh
Department of Future Automotive Engineering, Kongju National University, Cheonan, Republic of Korea
1 shared publication - Jung Han Kook
KS TECH, 1223-24, Cheonan-daero, Seobuk-gu, Cheonan-si 31080, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 24 March 2025
- Published by MDPI AG in Pharmaceutics
- Vol. 17 (4) , 406
Development of an Intelligent Tablet Press Machine for the In-Line Detection of Defective Tablets Using Machine Learning and Deep Learning Models
Objectives: This study aims to develop a tablet press machine (TPM) integrated with machine learning (ML) and deep learning (DL) models for in-line detection of defective tablets as a Process Analytical Technology (PAT) tool. This study aimed to predict tablet defects, including capping occurrence and inappropriate tablet breaking force (TBF), using real-time processing data. Methods: Free-flowing metformin HCl (MF) granules produced using the granulation method were compressed into tablets using a TPM. Commercial-scale experiments were conducted to determine the MF tablets’ defect criteria. Random Forest (RF) and Artificial Neural Network (ANN) models were designed and trained using sensed in-line data, including compression force, ejection force, and compression speed, to predict tablet quality defects. Subsequently, the TPM was designed and manufactured for in-line PAT using an RF model. The TPM was verified by sorting defective tablets in-line using a pretrained defect-detection algorithm. Results: The RF model demonstrated the highest predictive accuracy at 93.7% with an Area Under the Curve (AUC) of 0.895, while the ANN model achieved an accuracy of 92.6% with an AUC of 0.878. The TPM successfully sorted defective tablets in real time, achieving 99.43% sorting accuracy and a defective tablet detection accuracy of 93.71%. Conclusions: These results suggest that a ML-based TPM applied during the tableting process can detect defects non-destructively during the scale-up of wet granulation. In particular, it can serve as the base TPM model for an in-line PAT process during a scale-up process that produces small batches of multiple products, thereby reducing additional labor, time, and API consumption, and decreasing environmental pollution.
- 24 March 2025
- Published by MDPI AG in Pharmaceutics
- Vol. 17 (4) , 406
Open AccessDevelopment of an Intelligent Tablet Press Machine for the In-Line Detection of Defective Tablets Using Machine Learning and Deep Learning Models
Objectives: This study aims to develop a tablet press machine (TPM) integrated with machine learning (ML) and deep learning (DL) models for in-line detection of defective tablets as a Process Analytical Technology (PAT) tool. This study aimed to predict tablet defects, including capping occurrence and inappropriate tablet breaking force (TBF), using real-time processing data. Methods: Free-flowing metformin HCl (MF) granules produced using the granulation method were compressed into tablets using a TPM. Commercial-scale experiments were conducted to determine the MF tablets’ defect criteria. Random Forest (RF) and Artificial Neural Network (ANN) models were designed and trained using sensed in-line data, including compression force, ejection force, and compression speed, to predict tablet quality defects. Subsequently, the TPM was designed and manufactured for in-line PAT using an RF model. The TPM was verified by sorting defective tablets in-line using a pretrained defect-detection algorithm. Results: The RF model demonstrated the highest predictive accuracy at 93.7% with an Area Under the Curve (AUC) of 0.895, while the ANN model achieved an accuracy of 92.6% with an AUC of 0.878. The TPM successfully sorted defective tablets in real time, achieving 99.43% sorting accuracy and a defective tablet detection accuracy of 93.71%. Conclusions: These results suggest that a ML-based TPM applied during the tableting process can detect defects non-destructively during the scale-up of wet granulation. In particular, it can serve as the base TPM model for an in-line PAT process during a scale-up process that produces small batches of multiple products, thereby reducing additional labor, time, and API consumption, and decreasing environmental pollution.
- Open Access
- 27 December 2024
- Published by MDPI AG in Pharmaceuticals
- Vol. 18 (1) , 23
Evaluation of Prediction Models for the Capping and Breaking Force of Tablets Using Machine Learning Tools in Wet Granulation Commercial-Scale Pharmaceutical Manufacturing
Background/Objectives: This study aimed to establish a predictive model for critical quality attributes (CQAs) related to tablet integrity, including tablet breaking force (TBF), friability, and capping occurrence, using machine learning-based models and nondestructive experimental data. Methods: The machine learning-based models were trained on data to predict the CQAs of metformin HCl (MF)-containing tablets using a commercial-scale wet granulation process, and five models were each compared for regression and classification. We identified eight input variables associated with the process and material parameters that control the tableting outcome using feature importance analysis. Results: Among the models, the Gaussian Process regression model provided the most successful results, with R2 values of 0.959 and 0.949 for TBF and friability, respectively. Capping occurrence was accurately predicted by all models, with the Boosted Trees model achieving a 97.80% accuracy. Feature importance analysis revealed that the compression force and magnesium stearate fraction were the most influential parameters in CQA prediction and are input variables that could be used in CQA prediction. Conclusions: These findings indicate that TBF, friability, and capping occurrence were successfully modeled using machine learning with a large dataset by constructing regression and classification models. Applying these models before tablet manufacturing can enhance product quality during wet granulation scale-up, particularly by preventing capping during the manufacturing process without damaging the tablets.
- 27 December 2024
- Published by MDPI AG in Pharmaceuticals
- Vol. 18 (1) , 23
Open AccessEvaluation of Prediction Models for the Capping and Breaking Force of Tablets Using Machine Learning Tools in Wet Granulation Commercial-Scale Pharmaceutical Manufacturing
Background/Objectives: This study aimed to establish a predictive model for critical quality attributes (CQAs) related to tablet integrity, including tablet breaking force (TBF), friability, and capping occurrence, using machine learning-based models and nondestructive experimental data. Methods: The machine learning-based models were trained on data to predict the CQAs of metformin HCl (MF)-containing tablets using a commercial-scale wet granulation process, and five models were each compared for regression and classification. We identified eight input variables associated with the process and material parameters that control the tableting outcome using feature importance analysis. Results: Among the models, the Gaussian Process regression model provided the most successful results, with R2 values of 0.959 and 0.949 for TBF and friability, respectively. Capping occurrence was accurately predicted by all models, with the Boosted Trees model achieving a 97.80% accuracy. Feature importance analysis revealed that the compression force and magnesium stearate fraction were the most influential parameters in CQA prediction and are input variables that could be used in CQA prediction. Conclusions: These findings indicate that TBF, friability, and capping occurrence were successfully modeled using machine learning with a large dataset by constructing regression and classification models. Applying these models before tablet manufacturing can enhance product quality during wet granulation scale-up, particularly by preventing capping during the manufacturing process without damaging the tablets.
- Open Access
- 2 March 2024
- Published by MDPI AG in Pharmaceuticals
- Vol. 17 (3) , 330
Evaluation of the Ejection Pressure for Tracking Internal Cracks during Compaction in Bilayer Tablet Formulations Using Experimental and Finite Element Methods
This study aimed to evaluate the ejection pressure and the correlation of the findings with the occurrence of internal cracks within bilayer tablets (BLTs) consisting of metformin HCl (MF) and evogliptin tartrate (EG). Then, the mechanism of tablet failure was provided by the finite element method (FEM). The ejection pressure and the difference in diameter depending on MAIN-P were evaluated to understand the correlation between ejection pressure and change in the BLT internal structure. The ejection pressure and the difference in diameter increased as the MAIN-P increased, then steeply decreased from 350 MPa to 375 MPa of MAIN-P, despite there being no pattern in compaction breaking force and porosity. The mechanical integrity at the BLT interface was weakened by internal cracks, reducing ejection pressure. The stress distribution analysis during the compression revealed that crack formation caused by entrapped air located at the center of the BLT interface may not propagate due to concentrated stress, which promotes a tight bond at the edge of the BLT. Furthermore, complete delamination can occur in the ejection process due to localized and intensive shear stresses at the BLT interface. These findings indicate that the mechanisms of internal cracking and delamination were successfully confirmed by FEM simulation. Moreover, measuring ejection pressure before BLT manufacturing can prevent invisible tablet cracks without damaging the tablets.
- 2 March 2024
- Published by MDPI AG in Pharmaceuticals
- Vol. 17 (3) , 330
Open AccessEvaluation of the Ejection Pressure for Tracking Internal Cracks during Compaction in Bilayer Tablet Formulations Using Experimental and Finite Element Methods
This study aimed to evaluate the ejection pressure and the correlation of the findings with the occurrence of internal cracks within bilayer tablets (BLTs) consisting of metformin HCl (MF) and evogliptin tartrate (EG). Then, the mechanism of tablet failure was provided by the finite element method (FEM). The ejection pressure and the difference in diameter depending on MAIN-P were evaluated to understand the correlation between ejection pressure and change in the BLT internal structure. The ejection pressure and the difference in diameter increased as the MAIN-P increased, then steeply decreased from 350 MPa to 375 MPa of MAIN-P, despite there being no pattern in compaction breaking force and porosity. The mechanical integrity at the BLT interface was weakened by internal cracks, reducing ejection pressure. The stress distribution analysis during the compression revealed that crack formation caused by entrapped air located at the center of the BLT interface may not propagate due to concentrated stress, which promotes a tight bond at the edge of the BLT. Furthermore, complete delamination can occur in the ejection process due to localized and intensive shear stresses at the BLT interface. These findings indicate that the mechanisms of internal cracking and delamination were successfully confirmed by FEM simulation. Moreover, measuring ejection pressure before BLT manufacturing can prevent invisible tablet cracks without damaging the tablets.
- Open Access
- 26 October 2023
- Published by MDPI AG in Pharmaceuticals
- Vol. 16 (11) , 1523
The Effect of Compression Pressure on the First Layer Surface Roughness and Delamination of Metformin and Evogliptin Bilayer and Trilayer Tablets
The objectives of this study were to evaluate the delamination of convex-shaped metformin HCl (MF) and evogliptin tartrate (EG) multi-layer tablets depending on the pre-compression and main compression pressures and simultaneously correlate these results with those of a surface roughness analysis. Free-flowing MF and EG (median diameters of 38.3 and 44.7 μm, respectively) granules prepared using the wet granulation method were pre-compressed and subsequently compressed into bilayer and trilayer tablets using a universal testing machine. The compaction force required to break the tablets increased linearly as the main compression pressure increased (30–150 MPa). Conversely, the interfacial strength and compaction breaking force decreased as the pre-compression pressure increased (10–110 MPa). A surface roughness analysis employing a profilometer revealed that the first layer (MF) roughness drastically decreased from 5.89 to 0.51 μm (Ra, arithmetic average of profile height deviations from the mean line) as the pre-compression pressure increased from 10 to 150 MPa in the bilayer tablet. Accordingly, the decrease in the roughness of the first layer reduced the inter-penetration at the interface, as observed via energy dispersive spectrometer (EDS)-equipped scanning electron microscopy, decreasing the interfacial bonding strength and causing delamination of the MF/EG multi-layer tablets. These findings indicate the significance of roughness control in the actual preparation of multi-layer tablets and the usefulness of profilometer- and EDS-based surface analyses for interpreting the delamination of multi-layer tablets.
- 26 October 2023
- Published by MDPI AG in Pharmaceuticals
- Vol. 16 (11) , 1523
Open AccessThe Effect of Compression Pressure on the First Layer Surface Roughness and Delamination of Metformin and Evogliptin Bilayer and Trilayer Tablets
The objectives of this study were to evaluate the delamination of convex-shaped metformin HCl (MF) and evogliptin tartrate (EG) multi-layer tablets depending on the pre-compression and main compression pressures and simultaneously correlate these results with those of a surface roughness analysis. Free-flowing MF and EG (median diameters of 38.3 and 44.7 μm, respectively) granules prepared using the wet granulation method were pre-compressed and subsequently compressed into bilayer and trilayer tablets using a universal testing machine. The compaction force required to break the tablets increased linearly as the main compression pressure increased (30–150 MPa). Conversely, the interfacial strength and compaction breaking force decreased as the pre-compression pressure increased (10–110 MPa). A surface roughness analysis employing a profilometer revealed that the first layer (MF) roughness drastically decreased from 5.89 to 0.51 μm (Ra, arithmetic average of profile height deviations from the mean line) as the pre-compression pressure increased from 10 to 150 MPa in the bilayer tablet. Accordingly, the decrease in the roughness of the first layer reduced the inter-penetration at the interface, as observed via energy dispersive spectrometer (EDS)-equipped scanning electron microscopy, decreasing the interfacial bonding strength and causing delamination of the MF/EG multi-layer tablets. These findings indicate the significance of roughness control in the actual preparation of multi-layer tablets and the usefulness of profilometer- and EDS-based surface analyses for interpreting the delamination of multi-layer tablets.