Ensemble machine learning-based models for estimating the transfer length of strands in PSC beams

Tran, Viet‐Linh; Kim, Jin-Kook

doi:10.1016/j.eswa.2023.119768

Cited by 15 publications

(4 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hyperparameter value can be set by default in the ML package or adjusted by the user. However, ML models with default parameters have the major disadvantage of overfitting or underfitting because they introduce bias and variance [64][65][66]. Therefore, hyperparameter selection becomes an important criterion in every ML model.…”

Section: Hyperparameter Tuningmentioning

confidence: 99%

Failure Mode Identification and Shear Strength Prediction of Rectangular Hollow RC Columns Using Novel Hybrid Machine Learning Models

Tran,

Lee,

Nguyen

et al. 2023

Buildings

Self Cite

View full text Add to dashboard Cite

Failure mode identification and shear strength prediction are critical issues in designing reinforced concrete (RC) structures. Nevertheless, specific guidelines for identifying the failure modes and for accurate predictions of the shear strength of rectangular hollow RC columns are not provided in design codes. This study develops hybrid machine learning (ML) models to accurately identify the failure modes and precisely predict the shear strength of rectangular hollow RC columns. For this purpose, 121 experimental results of such columns are collected from the literature. Eight widely used ML models are employed to identify the failure modes and predict the shear strength of the column. The moth-flame optimization (MFO) algorithm and five-fold cross-validation are utilized to fine-tune the hyperparameters of the ML models. Additionally, seven empirical formulas are adopted to evaluate the performance of regression ML models in predicting the shear strength. The results reveal that the hybrid MFO-extreme gradient boosting (XGB) model outperforms others in both classifying the failure modes (accuracy of 93%) and predicting the shear strength (R2 = 0.996) of hollow RC columns. Additionally, the results indicate that the MFO-XGB model is more accurate than the empirical models for shear strength prediction. Moreover, the effect of input parameters on the failure modes and shear strength is investigated using the Shapley Additive exPlanations method. Finally, an efficient web application is developed for users who want to use the results of this study or update a new dataset.

show abstract

Section: Hyperparameter Tuningmentioning

confidence: 99%

Failure Mode Identification and Shear Strength Prediction of Rectangular Hollow RC Columns Using Novel Hybrid Machine Learning Models

Tran,

Lee,

Nguyen

et al. 2023

Buildings

Self Cite

View full text Add to dashboard Cite

show abstract

“…Se ha comprobado que el modelo realiza una clasificación eficiente, para lo cual se ha calculado la matriz de confusión, y se ha optimizado el rendimiento del modelo, realizando un ajuste a la validación cruzada. Se evaluó el rendimiento de los modelos de aprendizaje automático en conjunto utilizando la métrica Kappa de Kohen y la matriz de confusión (Tran y Kim, 2023).…”

Section: Evaluación Y Validaciónunclassified

Modelo de ensamble para predecir el diagnóstico de pacientes con sospecha de Covid-19

2023

RCS

View full text Add to dashboard Cite

The Covid-19 pandemic has affected millions of people around the world, being described by the World Health Organization as a crisis of global concern. This has generated the need to perform a timely prediction of the diagnosis of patients with high risk of clinical deterioration in medical establishments. The aim of this study is to design and compare the performance of machine-assembly-based machine learning models to predict patients with suspected Covid-19. The research follows the positivist paradigm, quantitative approach, observational design without intervention, predictive level. To carry out this study, 1,000 patient records from two health facilities in Peru were collected. The construction of the models was based on assembly algorithms, such as Random Forest, Extra Trees, Gradient Boosting and AdaBoosting. When comparing the models in terms of accuracy, which measures the percentage of cases correctly classified as patients with suspected Covid-19, a 97% accuracy was obtained for the models based on Random Forest and Gradient Boosting. In addition, Cohen's Kappa value was 0.95, which indicates a very good agreement between the model prediction result and the actual data.

show abstract

“…In the 95% AMS method, a horizontal line corresponding to the 95% of the average maximum strain points is drawn and the distance from the end of the beam to the intersection of this horizontal line with the smoothed strain profile is specified as the transfer length. Numerous studies have addressed the investigation of transfer length in prestressed concrete members [14][15][16][17][18][19][20][21]. For example, Russell and Burns [22] conducted a comprehensive study on transfer length in pretensioned concrete elements.…”

Section: Introductionmentioning

confidence: 99%

Experimental Investigation on the Effect of Time on Transfer Length in Pre-Stressed Concrete Beams

Naghipour,

Daronkolae,

Yousefpour

et al. 2024

Preprint

View full text Add to dashboard Cite

The effect of time on of transfer length variations in prestressed concrete elements has not been addressed in the current design codes of practice. The present investigation examines the effect of different parameters on transfer length over time. Therefore, a number of 13 pretensioned concrete beams were made in the laboratory with differences in beam cross-section and length, strand number and arrangement, concrete cover, and strand eccentricity. The 95% AMS technique was used to calculate transfer length. The results showed that transfer length of all beams increases over time, the highest measure was experienced between 14 and 28 days after strand detensioning. This value ranged between 2 and 5% in single-strand beams, and 12 to 14% in 10-strand beams. It was concluded that strand eccentricity has no considerable effect on the transfer length variations. The beam live end captured higher transfer lengths in most of the beams; however, strand arrangement and the amount of concrete cover were found to have the potential to shift higher transfer lengths to beam dead end. It was also revealed that beam length plays a significant role on transfer length, while longer beams featured larger transfer lengths. The percentage of increase in the transfer length in 10-strand beams after 14 days reached approximately twice that of the single-strand counterparts. The reason was associated with the number of strands, cross-sectional dimensions, and strand arrangement.

show abstract

Ensemble machine learning-based models for estimating the transfer length of strands in PSC beams

Cited by 15 publications

References 79 publications

Failure Mode Identification and Shear Strength Prediction of Rectangular Hollow RC Columns Using Novel Hybrid Machine Learning Models

Failure Mode Identification and Shear Strength Prediction of Rectangular Hollow RC Columns Using Novel Hybrid Machine Learning Models

Modelo de ensamble para predecir el diagnóstico de pacientes con sospecha de Covid-19

Experimental Investigation on the Effect of Time on Transfer Length in Pre-Stressed Concrete Beams

Contact Info

Product

Resources

About