Dinh Son Nguyen
Research Subjects
Dinh Son Nguyen has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Frédéric Vignat
Univ. Grenoble Alpes, CNRS, Grenoble INP*, G-SCOP, Grenoble, France
9 shared publications Daniel Brissaud
4 shared publications- Nguyen Duy Minh Phan
Faculty of Mechanical Engineering, The University of Danang - University of Technology and Education, Danang, Viet Nam
2 shared publications - Abdul Hadi Azman
Universiti Kebangsaan Malaysia (UKM)
1 shared publication - Cung Le
Faculty of Transportation Mechanical Engineering, University of Science and Technology, University of Danang, Postal address 54 Nguyen Luong Bang Street, Lien Chieu District, Danang City, Vietnam
1 shared publication D. Kien Le
University of Science and Technology - The University of Danang, Danang, Viet Nam
1 shared publication
Latest Publications
- Open Access
- 1 January 2027
- Published by International Digital Organization for Scientific Information (IDOSI) in International Journal of Engineering
- Vol. 40 (1) , 72-87
A Data-driven XGBoost Model for Robust Prediction of Compressive Strength in Fly Ash-based Concrete
This study presents a data-driven framework for predicting the compressive strength of fly ash concrete using the Extreme Gradient Boosting (XGBoost) algorithm. A dataset of 1,030 experimental samples was used for model development, and an additional 198 independent samples from external studies were employed for validation. Seven key input parameters—cement, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and curing age—were considered as predictors. To ensure robustness, a leakage-free preprocessing strategy and randomized search (RandomizedSearchCV) for hyperparameter tuning were applied for hyperparameter tuning. The optimized model achieved excellent predictive accuracy with R^2=0.9949 and RMSE = 1.20 MPa on the training set, and R^2=0.9390 with RMSE = 3.96 MPa on the testing set. When evaluated on the independent validation dataset, the model maintained acceptable accuracy (R^2=0.6745; 73.7% within ±20% tolerance). Feature importance analysis identified curing age and cement content as dominant factors influencing compressive strength. The results demonstrate that while machine learning models can achieve near-perfect accuracy internally, external validation is essential for assessing real-world generalization. The proposed XGBoost framework offers a reliable, interpretable, and efficient tool for data-driven mix design and sustainable concrete optimization.
- 1 January 2027
- Published by International Digital Organization for Scientific Information (IDOSI) in International Journal of Engineering
- Vol. 40 (1) , 72-87
Open AccessA Data-driven XGBoost Model for Robust Prediction of Compressive Strength in Fly Ash-based Concrete
This study presents a data-driven framework for predicting the compressive strength of fly ash concrete using the Extreme Gradient Boosting (XGBoost) algorithm. A dataset of 1,030 experimental samples was used for model development, and an additional 198 independent samples from external studies were employed for validation. Seven key input parameters—cement, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and curing age—were considered as predictors. To ensure robustness, a leakage-free preprocessing strategy and randomized search (RandomizedSearchCV) for hyperparameter tuning were applied for hyperparameter tuning. The optimized model achieved excellent predictive accuracy with R^2=0.9949 and RMSE = 1.20 MPa on the training set, and R^2=0.9390 with RMSE = 3.96 MPa on the testing set. When evaluated on the independent validation dataset, the model maintained acceptable accuracy (R^2=0.6745; 73.7% within ±20% tolerance). Feature importance analysis identified curing age and cement content as dominant factors influencing compressive strength. The results demonstrate that while machine learning models can achieve near-perfect accuracy internally, external validation is essential for assessing real-world generalization. The proposed XGBoost framework offers a reliable, interpretable, and efficient tool for data-driven mix design and sustainable concrete optimization.
- 12 November 2026
- Published by IOP Publishing in Engineering Research Express
Data Redundancy, Train-Test Leakage, and Cross-Source Generalisation in Machine-Learning Prediction of Fly Ash Concrete Compressive Strength
Machine-learning models for fly ash concrete are commonly developed from literature-assembled databases and evaluated using random train–test splits, which may overstate performance on previously unseen collection sources. This study examines how record redundancy, train–test contamination, and source heterogeneity affect reported performance in compressive-strength prediction. A database of 5,218 records from 14 collection sources was examined using record-level redundancy screening, operational domain screening, and 12 regression models. Of the combined operational total of 1,680 records (32.2%), 915 were reported as exact-value removals and are documented only at source-count level, whereas 765 near-duplicates were identified reproducibly from D1 at record level. In conventional random splits, 27.5% of test records had a near-duplicate counterpart in the training set. For these records, mean absolute error was 1.66 MPa for extreme gradient boosting (XGBoost) and 0.17 MPa for k-nearest neighbours, compared with 4.33 and 5.07 MPa, respectively, for uncontaminated records. After redundancy screening and source-eligibility filtering, 3,247 records from 11 collection sources remained. XGBoost achieved a macro-source coefficient of determination (R²) of 0.860 under source-stratified random splitting but only 0.369 under leave-one-source-cluster-out validation. Pairwise testing placed the five highest-ranked ensemble models within one Nemenyi group. The ten source-cluster blocks limit the strength of equivalence claims. The results indicate that data provenance, redundancy control, and source-aware validation affect apparent accuracy more strongly than model choice among the leading ensembles. Six minimum reporting requirements are proposed for machine-learning benchmarks assembled from concrete datasets.
- 12 November 2026
- Published by IOP Publishing in Engineering Research Express
Data Redundancy, Train-Test Leakage, and Cross-Source Generalisation in Machine-Learning Prediction of Fly Ash Concrete Compressive Strength
Machine-learning models for fly ash concrete are commonly developed from literature-assembled databases and evaluated using random train–test splits, which may overstate performance on previously unseen collection sources. This study examines how record redundancy, train–test contamination, and source heterogeneity affect reported performance in compressive-strength prediction. A database of 5,218 records from 14 collection sources was examined using record-level redundancy screening, operational domain screening, and 12 regression models. Of the combined operational total of 1,680 records (32.2%), 915 were reported as exact-value removals and are documented only at source-count level, whereas 765 near-duplicates were identified reproducibly from D1 at record level. In conventional random splits, 27.5% of test records had a near-duplicate counterpart in the training set. For these records, mean absolute error was 1.66 MPa for extreme gradient boosting (XGBoost) and 0.17 MPa for k-nearest neighbours, compared with 4.33 and 5.07 MPa, respectively, for uncontaminated records. After redundancy screening and source-eligibility filtering, 3,247 records from 11 collection sources remained. XGBoost achieved a macro-source coefficient of determination (R²) of 0.860 under source-stratified random splitting but only 0.369 under leave-one-source-cluster-out validation. Pairwise testing placed the five highest-ranked ensemble models within one Nemenyi group. The ten source-cluster blocks limit the strength of equivalence claims. The results indicate that data provenance, redundancy control, and source-aware validation affect apparent accuracy more strongly than model choice among the leading ensembles. Six minimum reporting requirements are proposed for machine-learning benchmarks assembled from concrete datasets.
- Open Access
- 27 September 2026
- Published by Elsevier in Next Materials
- Vol. 13
Gaussian process regression with physics-guided features for WLAM bead geometry: Repeated validation, algorithmic baselines, and predictive-interval assessment
- 27 September 2026
- Published by Elsevier in Next Materials
- Vol. 13
Open AccessGaussian process regression with physics-guided features for WLAM bead geometry: Repeated validation, algorithmic baselines, and predictive-interval assessment
- Open Access
- 1 January 2025
- Published by International Digital Organization for Scientific Information (IDOSI) in International Journal of Engineering
- Vol. 38 (9) , 2170-2182
Application of 3D Printing Technologies in the Design and Manufacture of Prosthetic Sockets for Low-Middle Income Countries: A Case Study in Vietnam
Prosthetic limbs are critical devices that significantly enhance the quality of life for individuals with limb amputations, enabling them to regain mobility, independence, and participation in daily activities. However, in low- and middle-income countries like Vietnam, access to prosthetics remains a significant challenge due to high costs, limited availability of modern manufacturing technologies, scarce materials, and inadequate healthcare infrastructure. These barriers leave many amputees without suitable solutions, impacting their physical and psychological well-being. This paper introduces an innovative approach to the design and manufacturing of affordable prosthetic sockets tailored specifically for lower-limb amputees in Vietnam. The proposed method replaces traditional labor-intensive and costly manual techniques with a streamlined digital workflow. By integrating 3D scanning for precise stump measurement, CAD software for design customization, and FDM 3D printing for efficient production, this approach significantly reduces costs and production time while ensuring high levels of customization. This digital methodology not only improves accessibility to prosthetics for underserved populations but also provides a scalable, sustainable solution for addressing the growing demand for prosthetic devices in resource-limited settings. It holds great potential for broader implementation in similar contexts worldwide.
- 1 January 2025
- Published by International Digital Organization for Scientific Information (IDOSI) in International Journal of Engineering
- Vol. 38 (9) , 2170-2182
Open AccessApplication of 3D Printing Technologies in the Design and Manufacture of Prosthetic Sockets for Low-Middle Income Countries: A Case Study in Vietnam
Prosthetic limbs are critical devices that significantly enhance the quality of life for individuals with limb amputations, enabling them to regain mobility, independence, and participation in daily activities. However, in low- and middle-income countries like Vietnam, access to prosthetics remains a significant challenge due to high costs, limited availability of modern manufacturing technologies, scarce materials, and inadequate healthcare infrastructure. These barriers leave many amputees without suitable solutions, impacting their physical and psychological well-being. This paper introduces an innovative approach to the design and manufacturing of affordable prosthetic sockets tailored specifically for lower-limb amputees in Vietnam. The proposed method replaces traditional labor-intensive and costly manual techniques with a streamlined digital workflow. By integrating 3D scanning for precise stump measurement, CAD software for design customization, and FDM 3D printing for efficient production, this approach significantly reduces costs and production time while ensuring high levels of customization. This digital methodology not only improves accessibility to prosthetics for underserved populations but also provides a scalable, sustainable solution for addressing the growing demand for prosthetic devices in resource-limited settings. It holds great potential for broader implementation in similar contexts worldwide.
- 6 September 2024
- Published by Springer Nature in International Journal on Interactive Design and Manufacturing (IJIDeM)
- Vol. 19 (7) , 4589-4603
Process of designing and manufacturing prosthetic socket for lower limb amputees: overview, challenges and future perspectives in Vietnam
- 6 September 2024
- Published by Springer Nature in International Journal on Interactive Design and Manufacturing (IJIDeM)
- Vol. 19 (7) , 4589-4603
Process of designing and manufacturing prosthetic socket for lower limb amputees: overview, challenges and future perspectives in Vietnam
- 15 February 2024
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 31 (1) , 79-87
Predicting Concrete Slump using Fly Ash and Stone Powder in Central Vietnam
Fly ash and stone powder, which are abundant wastes in Central Vietnam, are viable alternatives to cement and sand in concrete production. However, this replacement may worsen the compressive strength and slump of concrete. This study deals with the...
- 15 February 2024
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 31 (1) , 79-87
Predicting Concrete Slump using Fly Ash and Stone Powder in Central Vietnam
Fly ash and stone powder, which are abundant wastes in Central Vietnam, are viable alternatives to cement and sand in concrete production. However, this replacement may worsen the compressive strength and slump of concrete. This study deals with the...
- 1 September 2021
- Published by Springer Nature in International Journal on Interactive Design and Manufacturing (IJIDeM)
- Vol. 15 (4) , 381-396
Creation of lattice structures with skeleton model for additive manufacturing
- 1 September 2021
- Published by Springer Nature in International Journal on Interactive Design and Manufacturing (IJIDeM)
- Vol. 15 (4) , 381-396
Creation of lattice structures with skeleton model for additive manufacturing
- 27 March 2021
- Published by Springer Nature
- p. 799-807
Surface Accessibility Detection in CAD Environment for Additive Manufacturing
- 27 March 2021
- Published by Springer Nature
- p. 799-807
Surface Accessibility Detection in CAD Environment for Additive Manufacturing
- 1 April 2020
- Published by Korean Society of Precision Engineering in Journal of the Korean Society for Precision Engineering
- Vol. 37 (4) , 305-318
A Method to Investigate Mechanical Properties of Lattice Structures for Additive Manufacturing
The manufacturing technologies have undergone significant innovation at the beginning of this century from the development of science and technology. One of the most important inventions in manufacturing technologies is the creation of additive manufacturing technology. Additive manufacturing technologies allow building of a 3D object by adding ultra-thin layers of 2D cross-sectional slices of materials upon these previous layers. The most crucial effectiveness of additive manufacturing technologies is to fabricate the complex geometry of products. As a result, the lattice structure is used extensively in industrial product design to minimize usage of materials and reduce the weight of products. However, the simulation to investigate the mechanical properties of the lattice structure in the design space of a product has many issues such as calculation time, memory-consuming, etc. Thus, the paper presents a new method to automatically generate a geometric model of the lattice structure in a computer-aided design environment. This model will be used to make a simulation using the finite element method analysis to investigate the mechanical properties of each configuration of the lattice structure.
- 1 April 2020
- Published by Korean Society of Precision Engineering in Journal of the Korean Society for Precision Engineering
- Vol. 37 (4) , 305-318
A Method to Investigate Mechanical Properties of Lattice Structures for Additive Manufacturing
The manufacturing technologies have undergone significant innovation at the beginning of this century from the development of science and technology. One of the most important inventions in manufacturing technologies is the creation of additive manufacturing technology. Additive manufacturing technologies allow building of a 3D object by adding ultra-thin layers of 2D cross-sectional slices of materials upon these previous layers. The most crucial effectiveness of additive manufacturing technologies is to fabricate the complex geometry of products. As a result, the lattice structure is used extensively in industrial product design to minimize usage of materials and reduce the weight of products. However, the simulation to investigate the mechanical properties of the lattice structure in the design space of a product has many issues such as calculation time, memory-consuming, etc. Thus, the paper presents a new method to automatically generate a geometric model of the lattice structure in a computer-aided design environment. This model will be used to make a simulation using the finite element method analysis to investigate the mechanical properties of each configuration of the lattice structure.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1275-1279
A Method for Generation of Random Lattice Structure for Additive Manufacturing
Additive manufacturing technologies provide us new opportunities to fabricate a product with much more complex geometry and architecture that conventional manufacturing ones such as turning, milling, grinding, casting and molding do not have the ability to implement. Hence, lattice structures are becoming more popular and used extensively in the industrial product design to minimize the usage of materials due to the additive manufacture technologies. Lattice structures are formed by the cellular unit of structure repeated regularly or irregularly in a design area. However, the creation and generation of these structures for additive manufacturing in the current CAD environment have many difficulties. Therefore, the paper will propose a new approach to design the lattice structure, especially the random one. This approach allows helping product designers to design and generate lattice structure randomly based on the Voronoi diagrams.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1275-1279
A Method for Generation of Random Lattice Structure for Additive Manufacturing
Additive manufacturing technologies provide us new opportunities to fabricate a product with much more complex geometry and architecture that conventional manufacturing ones such as turning, milling, grinding, casting and molding do not have the ability to implement. Hence, lattice structures are becoming more popular and used extensively in the industrial product design to minimize the usage of materials due to the additive manufacture technologies. Lattice structures are formed by the cellular unit of structure repeated regularly or irregularly in a design area. However, the creation and generation of these structures for additive manufacturing in the current CAD environment have many difficulties. Therefore, the paper will propose a new approach to design the lattice structure, especially the random one. This approach allows helping product designers to design and generate lattice structure randomly based on the Voronoi diagrams.