Tae-Woong Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tae-Woong Park has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Hyeong-Joo Kim
Kunsan National Univ
4 shared publications - Hyeong-Soo Kim
Renewable Energy Research Institute, Kunsan National University, Gunsan 573-701, Republic of Korea
3 shared publications - Kevin Bagas Arifki Mawuntu
Department of Civil Engineering, Kunsan National University, Gunsan, Korea, Republic of
2 shared publications - Peter Rey Dinoy
Researcher, Renewable Energy Research Institute/Department of Civil and Environmental Engineering, Kunsan National University, Gunsan, Republic of Korea
2 shared publications - Christine Patinga Langcuyan
Department of Civil Engineering, Kunsan National University, 558 Daehakro, Gunsan 54150, Korea
1 shared publication - Hee-Seong Choi
Department of Civil and Environmental Engineering, Kunsan National University, Gunsan 573-701, Republic of Korea
1 shared publication
Latest Publications
- 3 November 2025
- Published by Springer Nature in Transportation Infrastructure Geotechnology
- Vol. 12 (8) , 1-29
Estimation of Bearing Capacity of Shallow Foundations on Cohesionless Soil Using Backpropagation Neural Networks and LSSVM Models
- 3 November 2025
- Published by Springer Nature in Transportation Infrastructure Geotechnology
- Vol. 12 (8) , 1-29
Estimation of Bearing Capacity of Shallow Foundations on Cohesionless Soil Using Backpropagation Neural Networks and LSSVM Models
- Open Access
- 1 April 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (7) , 4497
Spatial Autocorrelation Incorporated Machine Learning Model for Geotechnical Subsurface Modeling
Machine learning models for spatial prediction have been applied in various types of research. However, spatial relation has not been fully considered in modeling, since the Cartesian coordinates of the observed points are directly employed as the location information for machine learning features. This study presents a machine learning modeling process which incorporates spatial autocorrelation for geotechnical subsurface modeling. A new set of features called the Euclidean distance field (EDF) was generated based on the distance between the query points and the observed boreholes in order to incorporate spatial autocorrelation into the machine learning model. Principal component analysis (PCA) was performed to reduce the increasing dimensionality of the dataset caused by the EDF features. Optimized machine learning models based on several popular algorithms (Support Vector Machine, Gaussian Process Regression, Artificial Neural Network, and k-Nearest Neighbor) were employed for predicting several geotechnical information as the targets. The results showed that the optimized machine learning models constructed with the EDF modeling approach generate a slightly lower Root Mean Square Error (RMSE) score compared to the model with the direct XY coordinate approach by 0.041, 0.046, 1.302, and 1.561 for ground surface elevation, groundwater level, SPT-N value, and percent finer than 0.075 mm sieve, respectively. Both modeling approaches performed well for USCS-based soil classification with the EDF model having slightly improved classification accuracy by 0.72%. Furthermore, the model can perform balance multiclass classification as indicated by the >95% precision, recall, f1-score, and balanced accuracy score. These results indicate that spatial autocorrelation has a noticeable effect. Hence, it needs to be considered to improve the overall performance of spatial machine learning modeling. Comparison of geotechnical subsurface predictions generated based on different machine learning algorithms showed that the selection of the best-performing model based only on the lowest prediction error is not appropriate for spatial prediction modeling. Therefore, thorough analysis of the predicted data by visualization is necessary in the selection process for spatial prediction modeling.
- 1 April 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (7) , 4497
Open AccessSpatial Autocorrelation Incorporated Machine Learning Model for Geotechnical Subsurface Modeling
Machine learning models for spatial prediction have been applied in various types of research. However, spatial relation has not been fully considered in modeling, since the Cartesian coordinates of the observed points are directly employed as the location information for machine learning features. This study presents a machine learning modeling process which incorporates spatial autocorrelation for geotechnical subsurface modeling. A new set of features called the Euclidean distance field (EDF) was generated based on the distance between the query points and the observed boreholes in order to incorporate spatial autocorrelation into the machine learning model. Principal component analysis (PCA) was performed to reduce the increasing dimensionality of the dataset caused by the EDF features. Optimized machine learning models based on several popular algorithms (Support Vector Machine, Gaussian Process Regression, Artificial Neural Network, and k-Nearest Neighbor) were employed for predicting several geotechnical information as the targets. The results showed that the optimized machine learning models constructed with the EDF modeling approach generate a slightly lower Root Mean Square Error (RMSE) score compared to the model with the direct XY coordinate approach by 0.041, 0.046, 1.302, and 1.561 for ground surface elevation, groundwater level, SPT-N value, and percent finer than 0.075 mm sieve, respectively. Both modeling approaches performed well for USCS-based soil classification with the EDF model having slightly improved classification accuracy by 0.72%. Furthermore, the model can perform balance multiclass classification as indicated by the >95% precision, recall, f1-score, and balanced accuracy score. These results indicate that spatial autocorrelation has a noticeable effect. Hence, it needs to be considered to improve the overall performance of spatial machine learning modeling. Comparison of geotechnical subsurface predictions generated based on different machine learning algorithms showed that the selection of the best-performing model based only on the lowest prediction error is not appropriate for spatial prediction modeling. Therefore, thorough analysis of the predicted data by visualization is necessary in the selection process for spatial prediction modeling.
- Open Access
- 5 January 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (2) , 785
Seismic Characteristics of a Geotextile Tube-Reinforced Embankment and Shallow Foundations Laid on Liquefiable Soil
The ground in Saemangeum has a high water level and is mostly composed of silty soil and sand, which makes it susceptible to liquefaction and seepage effects. To investigate the seismic response of a geotextile tube-reinforced embankment and shallow foundations laid on a liquefiable soil, a simple spring type shaking table apparatus was developed. The variation in the response acceleration and shear stress-strain relationship were investigated, and the effect of soil improvement and reinforcement were explored, wherein one of the shallow foundations was laid on a coarse sand layer and reinforced by a polyester geotextile. The results showed that the main cause of damage to the embankment was seepage-induced liquefaction. Excessive surface accelerations were observed in the embankment soil due to lateral spreading, indicating the importance of analyzing the liquefaction potential of soils not only at the site area but also near embankments. Lastly, the inclusion of geotextile reinforcement and soil improvement only resulted in the slight reduction of shallow foundation settlement.
- 5 January 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (2) , 785
Open AccessSeismic Characteristics of a Geotextile Tube-Reinforced Embankment and Shallow Foundations Laid on Liquefiable Soil
The ground in Saemangeum has a high water level and is mostly composed of silty soil and sand, which makes it susceptible to liquefaction and seepage effects. To investigate the seismic response of a geotextile tube-reinforced embankment and shallow foundations laid on a liquefiable soil, a simple spring type shaking table apparatus was developed. The variation in the response acceleration and shear stress-strain relationship were investigated, and the effect of soil improvement and reinforcement were explored, wherein one of the shallow foundations was laid on a coarse sand layer and reinforced by a polyester geotextile. The results showed that the main cause of damage to the embankment was seepage-induced liquefaction. Excessive surface accelerations were observed in the embankment soil due to lateral spreading, indicating the importance of analyzing the liquefaction potential of soils not only at the site area but also near embankments. Lastly, the inclusion of geotextile reinforcement and soil improvement only resulted in the slight reduction of shallow foundation settlement.
- Open Access
- 1 January 2023
- Published by Walter de Gruyter GmbH in Open Geosciences
- Vol. 15 (1)
Dynamic analysis of MSE wall subjected to surface vibration loading
Extensively used Mechanically Stabilized Earth (MSE) walls in Rail Transportation System (RTS) are vulnerable to surface vibrations generated by moving vehicles. Hence, it is necessary to consider the effects of surface vibrations during the design of MSE walls for RTS. Steel-reinforced panel-type MSE walls are shown to perform well during vibration loading, but costly steel materials have led to greater reliance on affordable and readily available geosynthetics for reinforcement. Limited research exists on the behavior of panel-type MSE walls with geosynthetics considering RTS-induced vibrations frequencies. Thus, this study employs Finite Element software PLAXIS 3D to simulate the impact of surface vibration frequencies on panel-type MSE walls. The qualitative study encompasses two reinforcement cases (geogrids and steel strips) of 4 m MSE wall height and four harmonic loading frequencies representing RTS-induced surface vibrations for simulation. The dynamic responses of MSE wall are presented in terms of lateral wall displacements and lateral earth pressure distributions. Furthermore, the distributions of tensile strain and the identification of potential slip surface locations are presented. The findings indicated that MSE wall and reinforcement responses are governed by RTS-induced vibrations and fundamental frequency of backfill soil. This highlights the need for consideration of both the fundamental frequency of the backfill soil and RTS-induced vibrations in the design of MSE walls.
- 1 January 2023
- Published by Walter de Gruyter GmbH in Open Geosciences
- Vol. 15 (1)
Open AccessDynamic analysis of MSE wall subjected to surface vibration loading
Extensively used Mechanically Stabilized Earth (MSE) walls in Rail Transportation System (RTS) are vulnerable to surface vibrations generated by moving vehicles. Hence, it is necessary to consider the effects of surface vibrations during the design of MSE walls for RTS. Steel-reinforced panel-type MSE walls are shown to perform well during vibration loading, but costly steel materials have led to greater reliance on affordable and readily available geosynthetics for reinforcement. Limited research exists on the behavior of panel-type MSE walls with geosynthetics considering RTS-induced vibrations frequencies. Thus, this study employs Finite Element software PLAXIS 3D to simulate the impact of surface vibration frequencies on panel-type MSE walls. The qualitative study encompasses two reinforcement cases (geogrids and steel strips) of 4 m MSE wall height and four harmonic loading frequencies representing RTS-induced surface vibrations for simulation. The dynamic responses of MSE wall are presented in terms of lateral wall displacements and lateral earth pressure distributions. Furthermore, the distributions of tensile strain and the identification of potential slip surface locations are presented. The findings indicated that MSE wall and reinforcement responses are governed by RTS-induced vibrations and fundamental frequency of backfill soil. This highlights the need for consideration of both the fundamental frequency of the backfill soil and RTS-induced vibrations in the design of MSE walls.
- Open Access
- 10 April 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7) , 2633
Guidelines for Impact Echo Test Signal Interpretation Based on Wavelet Packet Transform for the Detection of Pile Defects
Nonlinear amplification is typically done on velocity signals from low-strain pile integrity tests to enhance weak echoes and superimpose any peak reflections. This conventional method may sometimes fail to untangle the hidden information within the signal that is obscured by the presence of noise. In this study, a pile defect identification system based on the conventional nonlinear amplification method and the wavelet packet transform (WPT) was proposed to easily detect the presence of any geometric or material defects by identifying feature parameters. Diagnostic rules, which have been lacking in the literature, were presented to serve as a guide in interpreting decomposed signals and in analyzing various characteristics of peak waveforms that are associated with certain types of defects. In this study, the finite element method was used to simulate the impact echo test of nine cases of defective piles. To verify the proposed scheme, six data sets of the nine cases of defective piles were made, in which a total of 54 piles were analyzed. The results of the study showed that the identification method based on WPT could detect defects 87.04% of the time compared to the conventional method, which only detected defects 64.81% of the time.
- 10 April 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7) , 2633
Open AccessGuidelines for Impact Echo Test Signal Interpretation Based on Wavelet Packet Transform for the Detection of Pile Defects
Nonlinear amplification is typically done on velocity signals from low-strain pile integrity tests to enhance weak echoes and superimpose any peak reflections. This conventional method may sometimes fail to untangle the hidden information within the signal that is obscured by the presence of noise. In this study, a pile defect identification system based on the conventional nonlinear amplification method and the wavelet packet transform (WPT) was proposed to easily detect the presence of any geometric or material defects by identifying feature parameters. Diagnostic rules, which have been lacking in the literature, were presented to serve as a guide in interpreting decomposed signals and in analyzing various characteristics of peak waveforms that are associated with certain types of defects. In this study, the finite element method was used to simulate the impact echo test of nine cases of defective piles. To verify the proposed scheme, six data sets of the nine cases of defective piles were made, in which a total of 54 piles were analyzed. The results of the study showed that the identification method based on WPT could detect defects 87.04% of the time compared to the conventional method, which only detected defects 64.81% of the time.