Prediction of Compaction and Strength Properties of Amended Soil Using Machine Learning

Taffese, Woubishet Zewdu; Abegaz, Kassahun Admassu

doi:10.3390/buildings12050613

Cited by 29 publications

(8 citation statements)

References 26 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, DT and DT-based ensemble learning methods are utilized, including Random Forest from bagging, GBDT, XGBoost, LightGBM, and CatBoost from boosting [27,[29][30][31][32][33]. These methods are adopted for solving complex civil engineering problems [34,35].…”

Section: Ensemble Learningmentioning

confidence: 99%

Accurate Prediction of Punching Shear Strength of Steel Fiber-Reinforced Concrete Slabs: A Machine Learning Approach with Data Augmentation and Explainability

Cheng,

Taffese,

2024

Buildings

Self Cite

View full text Add to dashboard Cite

Reinforced concrete slabs are widely used in building structures due to their economic, durable, and aesthetic advantages. The determination of their ultimate strength often hinges on punching shear strength. Presently, methods such as closed hoops, steel bending, and fiber reinforcement are employed to enhance punching shear strength, with fiber reinforcement gaining popularity due to its ease of implementation and efficacy in improving concrete durability. This study introduces a novel approach employing six machine learning algorithms rooted in decision trees and decision tree-based ensemble learning to predict punching shear strength in steel fiber-reinforced concrete slabs. To overcome experimental data limitations, a data augmentation approach based on the Gaussian mixture model is employed. The validation of the data augmentation is conducted through “synthetic training—real testing” and “real training—real testing”. Additionally, the best machine learning model is analyzed for explainability using Shapley Additive exPlanation (SHAP). Results demonstrate that the proposed data augmentation method effectively captures the original data distribution, enhancing the robustness and accuracy of the machine learning model. Moreover, SHAP provides better insights into the features influencing punching shear strength. Thus, the proposed data enhancement model offers a reliable approach for modeling small experimental datasets in structural engineering.

show abstract

Section: Ensemble Learningmentioning

confidence: 99%

Accurate Prediction of Punching Shear Strength of Steel Fiber-Reinforced Concrete Slabs: A Machine Learning Approach with Data Augmentation and Explainability

Cheng,

Taffese,

2024

Buildings

Self Cite

View full text Add to dashboard Cite

show abstract

“…ML has emerged as a powerful tool for enhancing data processing efficiency. In the field of IC, researchers have utilized ML techniques, particularly artificial neural network models, to address geotechnical engineering challenges [92,93]. For instance, Isik and Ozden [94] developed an artificial neural network model to estimate compaction parameters for a wide range of soil mixtures, demonstrating the applicability and effectiveness of their approach.…”

Section: Machine Learningmentioning

confidence: 99%

Recent Development in Intelligent Compaction for Asphalt Pavement Construction: Leveraging Smart Sensors and Machine Learning

Wang,

Li,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

Intelligent compaction (IC) has emerged as a breakthrough technology that utilizes advanced sensing, data transmission, and control systems to optimize asphalt pavement compaction quality and efficiency. However, accurate assessment of compaction status remains challenging under real construction conditions. This paper reviewed recent progress and applications of smart sensors and machine learning (ML) to address existing limitations in IC. The principles and components of various advanced sensors deployed in IC systems were introduced, including SmartRock, fiber Bragg grating, and integrated circuit piezoelectric acceleration sensors. Case studies on utilizing these sensors for particle behavior monitoring, strain measurement, and impact data collection were reviewed. Meanwhile, common ML algorithms including regression, classification, clustering, and artificial neural networks were discussed. Practical examples of applying ML to estimate mechanical properties, evaluate overall compaction quality, and predict soil firmness through supervised and unsupervised models were examined. Results indicated smart sensors have enhanced compaction monitoring capabilities but require robustness improvements. ML provides a data-driven approach to complement traditional empirical methods but necessitates extensive field validation. Potential integration with digital construction technologies such as building information modeling and augmented reality was also explored. In conclusion, leveraging emerging sensing and artificial intelligence presents opportunities to optimize the IC process and address key challenges. However, cooperation across disciplines will be vital to test and refine technologies under real-world conditions. This study serves to advance understanding and highlight priority areas for future research toward the realization of IC’s full potential.

show abstract

“…To address this issue, the interquartile range (IQR) method was employed to identify and remove outliers from these two parameters. The interquartile range is a robust measure of scale that is not influenced by outliers [61]. It is calculated as the difference between the 75th percentile (Q3) and the 25th percentile (Q1) of the data:…”

Section: Data Collection and Preparationmentioning

confidence: 99%

“…For the SP and CP parameters, the IQR was calculated, and any data point that fell outside the range of [Q1 − 1.5 × (IQR), Q3 + 1.5 × (IQR)] was identified as an outlier and removed from the dataset [61]. After removing the outliers from the SP and CP, the remaining data points in the dataset were used for further analysis and modeling.…”

Section: Data Collection and Preparationmentioning

confidence: 99%

Effect of Data Augmentation Using Deep Learning on Predictive Models for Geopolymer Compressive Strength

Nguyen,

Pham,

Ahn

2024

Applied Sciences

View full text Add to dashboard Cite

In recent years, machine learning models have become a potential approach in accurately predicting the concrete compressive strength, which is essential for the real-world application of geopolymer concrete. However, the precursor system of geopolymer concrete is known to be more heterogeneous compared to Ordinary Portland Cement (OPC) concrete, adversely affecting the data generated and the performance of the models. To its advantage, data enrichment through deep learning can effectively enhance the performance of prediction models. Therefore, this study investigates the capability of tabular generative adversarial networks (TGANs) to generate data on mixtures and compressive strength of geopolymer concrete. It assesses the impact of using synthetic data with various models, including tree-based, support vector machines, and neural networks. For this purpose, 930 instances with 11 variables were collected from the open literature. In particular, 10 variables including content of fly ash, slag, sodium silicate, sodium hydroxide, superplasticizer, fine aggregate, coarse aggregate, added water, curing temperature, and specimen age are considered as inputs, while compressive strength is the output of the models. A TGAN was employed to generate an additional 1000 data points based on the original dataset for training new predictive models. These models were evaluated on real data test sets and compared with models trained on the original data. The results indicate that the developed models significantly improve performance, particularly neural networks, followed by tree-based models and support vector machines. Moreover, data characteristics greatly influence model performance, both before and after data augmentation.

show abstract

Prediction of Compaction and Strength Properties of Amended Soil Using Machine Learning

Cited by 29 publications

References 26 publications

Accurate Prediction of Punching Shear Strength of Steel Fiber-Reinforced Concrete Slabs: A Machine Learning Approach with Data Augmentation and Explainability

Accurate Prediction of Punching Shear Strength of Steel Fiber-Reinforced Concrete Slabs: A Machine Learning Approach with Data Augmentation and Explainability

Recent Development in Intelligent Compaction for Asphalt Pavement Construction: Leveraging Smart Sensors and Machine Learning

Effect of Data Augmentation Using Deep Learning on Predictive Models for Geopolymer Compressive Strength

Contact Info

Product

Resources

About