Tran Quang Khiem

Scopus Publications

An explainable hybrid TLBO–ANN approach for accurate shear resistance prediction in steel fiber–reinforced concrete beams
Nga Thanh Duong, Nga Quynh Nguyen Tra, Linh Hoang Tran, Hong My Thi Tran, Khiem Quang Tran
Structures, 2026
A transformer encoder-only framework for multi-horizon wave forecasting with physical and window-length interpretability
Nga Thanh Duong, Nga Quynh Nguyen Tra, Linh Hoang Tran, Hong My Thi Tran, Khiem Quang Tran
Ocean Engineering, 2026
Hybrid Metaheuristic–ANN for accurate, stable, and generalized breaking wave height prediction
Khiem Quang Tran, Nga Quynh Nguyen Tra, Linh Hoang Tran, Loc Xuan Luu, Nga Thanh Duong
Ocean Engineering, 2026
TPE-Optimized Neural Network Framework for Predicting Settlement of Nodular Pile Foundations
Hung La, Tan Nguyen, Khiem Quang Tran
Lecture Notes in Civil Engineering, 2026
Hyperparameter-tuned Light Gradient Boosting Machine model for predicting breaking wave height
Khiem Quang Tran, Nga Quynh Nguyen Tra, Linh Hoang Tran, Loc Xuan Luu, Nga Thanh Duong
Coastal Engineering Journal, 2026
This study proposes a new model using Light Gradient Boosting Machine (LightGBM) to predict breaking wave height based on input wave parameters. To determine optimal hyperparameter, Optuna is employed and conducts 100 independent runs with 10-fold cross-validation. Additionally, SHapley Additive exPlanations (SHAP) analysis is applied to investigate behavior of model. Results show that LightGBM model optimized with Optuna shows excellent performance for estimating breaker height. Root mean square error of model is 1.861 cm (for training dataset) and 3.518 cm (for testing dataset). Coefficients of determination are also high with 0.998 and 0.992 for training and testing datasets, respectively. This accuracy is remarkably higher than previous existing breaking wave height models. Besides, SHAP analysis highlights that deep-water wave height and water depth have the greatest impact on breaker height prediction. The results demonstrate that combination of Optuna and LightGBM enhances robustness and generalization of model for predicting breaking wave height.
Investigation of mechanical properties and slope restoration potential of landslide sludge reinforced with palm oil plantation
Delima Canny Valentine Simarmata, Khiem Quang Tran, Nga Thanh Duong, Tomoaki Satomi, Hiroshi Takahashi
Engineering Geology, 2025
This study focuses on the use of empty fruit bunch (EFB) as a fiber material in fiber-cement stabilized soil method to recycle landslide sludge and reuse the output as cover material for failed slope restorations in Indonesia. The mechanical properties of modified sludge are investigated by conducting tension test on fiber, durability test, and shear box test to determine tensile strength of EFB, soil strength , shear strength , cohesion, and internal friction angle. In addition, the application of modified sludge is analyzed through slope stability analysis for terrain modeling and factor of safety determination. The experiments are carried out under a wide range of mixing conditions including water contents of 60 %, 80 %, and 100 %, cement contents of 50, 60, and 70 kg/m 3 , fiber contents of 0, 10, 20, and 30 kg/m 3 , and fiber lengths of 10 and 20 mm. The tension tests indicate that tensile strength decreases with increasing gauge length from 10 to 30 mm. Durability tests show that EFB inclusion improves compressive strength and soundness of specimens during drying and wetting cycles. Moreover, modified sludge with 30 mm EFB achieves higher failure strength and resists cracking more effectively than 10 mm EFB. Shear box tests display optimal cohesion at 10 kg/m 3 for water content of 60 % and at 20 kg/m 3 for water contents of 80 % and 100 %. Furthermore, GIS-integrated slope stability analysis demonstrates an improvement in the factor of safety when using EFB-cement stabilized sludge as cover material for slope rehabilitation of landslide-prone area.
Application of Weibull distribution and stable energy concept for numerical solutions of random wave heights
Nga Thanh Duong, Loc Xuan Luu, Linh Hoang Tran, Khiem Quang Tran
Dynamics of Atmospheres and Oceans, 2025
Irregular wave height transformation prediction based on weighted Rayleigh distribution and bore concept
Khiem Quang Tran, Nga Thanh Duong, Linh Hoang Tran, Loc Xuan Luu
Coastal Engineering Journal, 2025
Unconfined compressive strength of geopolymers based soil: Model development using gene expression programming and a comparison with other computer-based approaches
Khiem Quang Tran, Nga Thanh Duong, Loc Xuan Luu, Linh Hoang Tran
Mechanics of Advanced Materials and Structures, 2025
The present work aims to propose a model for calculating unconfined compressive strength (UCS) of soil stabilized by geopolymer based on gene expression programming (GEP). The new model is compared with earlier models developed from artificial neural networks (ANN), multivariable regression analysis (MVR), multi-gene genetic programming (MGGP), and support vector machines (SVM) models. The results indicate that the GEP model is superior to MVR and MGGP models and quite comparable to ANN and SVM models. The study demonstrates the robustness of the GEP model through parametric analysis. Additionally, this model is simpler and easier to use in practice.
Development of novel parametric wave model for irregular wave height transformation
Khiem Quang Tran, Nga Thanh Duong, Loc Xuan Luu, Linh Hoang Tran, Winyu Rattanapitikon
Ocean Engineering, 2023
Wave height transformation is one of the most crucial parameters in studying coastal engineering as well as designing coastal structures. In this study, a wave energy dissipation model for predicting the transformation of root-mean-square wave height is proposed by using a parametric wave approach over enormous measured data. Additionally, 12 existing energy dissipation models are selected in order to verify their reliability in wave height prediction and compared with a novel formula in terms of error indices, standard deviation, capacity prediction, and root-mean-square relative error. Compiled experimental data with 5783 data are collected for examination and development. The results present that the root-mean-square relative error of existing formulas is in a range from 6.4% to 10.9%. The best existing formulas predict wave height pretty well with a root-mean-square relative error of 6.4% and a standard deviation of 11.0%. Regarding the new model, the best novel model which uses breaking wave height formula of Miche (1944) displays a lower value of root-mean-square error (6.1%) and standard deviation (8.8%) in comparison with the best existing formulas. To confirm the superior performance of the proposed model, all existing models and the best developed model are verified and compared with additional data. The accuracy of the proposed formula over verified data is still better than all existing formulas. Therefore, the novel model is strongly recommended for estimating the transformation of root-mean-square wave height. • A new parametric wave model of energy dissipation is proposed. • The reliability of new and existing formulas for wave height prediction is evaluated. • The error of novel model is lower than all existing models. • The prediction capacity of developed formula is the most stable.
Prediction of breaking wave height by using artificial neural network-based approach
Nga Thanh Duong, Khiem Quang Tran, Loc Xuan Luu, Linh Hoang Tran
Ocean Modelling, 2023
Estimation of seepage velocity and piping resistance of fiber-reinforced soil by using artificial neural network-based approach
Nga Thanh Duong, Khiem Quang Tran
Neural Computing and Applications, 2023
Effects of agricultural by-product on mechanical properties of cemented waste soil
Nga Thanh Duong, Khiem Quang Tran, Tomoaki Satomi, Hiroshi Takahashi
Journal of Cleaner Production, 2022
Tensile behaviors of natural fiber and cement reinforced soil subjected to direct tensile test
Khiem Quang Tran, Tomoaki Satomi, Hiroshi Takahashi
Journal of Building Engineering, 2019
Effect of waste cornsilk fiber reinforcement on mechanical properties of soft soils
Khiem Quang Tran, Tomoaki Satomi, Hiroshi Takahashi
Transportation Geotechnics, 2018
Improvement of mechanical behavior of cemented soil reinforced with waste cornsilk fibers
Khiem Quang Tran, Tomoaki Satomi, Hiroshi Takahashi
Construction and Building Materials, 2018
Study on effect of cornsilk fiber in cemented soil stabilization
Khiem Quang Tran, Tomoaki Satomi, Hiroshi Takahashi
Lecture Notes in Civil Engineering, 2018
Study on strength behavior of cement stabilized sludge reinforced with waste cornsilk fiber
Khiem Quang Tran
International Journal of Geomate, 2017
Estimation of maximum possible wave heights in surf zone
Winyu Rattanapitikon, Khiem Quang Tran, Tomoya Shibayama
Coastal Engineering Journal, 2015