Evaluation of mechanical properties of concretes containing coarse recycled concrete aggregates using multivariate adaptive regression splines (MARS), M5 model tree (M5Tree), and least squares support vector regression (LSSVR) models

Gholampour, Aliakbar; Mansouri, Iman; Kişi, Özgür; Ozbakkaloglu, Togay

doi:10.1007/s00521-018-3630-y

Cited by 104 publications

(27 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 14 shows the coefficient of determination and the root mean squared error of models in previous studies that predicted the compressive strength of RAC. It can be observed that models in the present study achieved better accuracy than that of Gholampour et al [ 22 ] and Deshpande et al [ 11 ] who used relatively large data samples. As expected, studies that reported smaller databases reached higher accuracy.…”

Section: Results Discussion and Recommendationscontrasting

confidence: 59%

“…Also, several models which used smaller data sets than that in the present study, including Khademi et al [ 15 ], Duan et al [ 2 ], Deshpande et al [ 11 ], Topçu and Saridemir [ 6 ], Deng et al [ 16 ], and Naderpour et al [ 1 ], have compromised generalization capability. Furthermore, in the case of Gholampour et al [ 22 ], the authors decided to split the available data and create two different models to predict the compressive strength of those samples corresponding to cylindrical specimens and those corresponding to cube specimens. Conversely, the present study considered the specimen type as an input feature, resulting in higher accuracy.…”

Section: Results Discussion and Recommendationsmentioning

confidence: 99%

“…The accuracy of the ANN model was at least 2% higher than that of the other techniques, even when the non-dimensional parameters were considered. Using a larger dataset, Gholampour et al [ 22 ] predicted the compressive strength and other mechanical properties of RAC employing three types of algorithms including multivariate adaptive regression splines, M5 model tree, and least squares support vector regression. They created two different models for each algorithm corresponding to the cube and cylinder compressive strengths, respectively.…”

Section: Introductionmentioning

confidence: 99%

“…In summary, Khademi et al [ 15 ], Naderpour et al [ 1 ], Deng et al [ 16 ], Deshpande et al [ 11 ], Gholampour et al [ 22 ], Duan et al [ 2 ], Topcu and Saridemir [ 6 ], and Dantas et al [ 23 ] used 257, 139, 74, 257, 650, 168, 210, and 1178 data points, respectively, to predict the compressive strength of RAC. In addition to the quality and size of existing datasets, the advent of new and more powerful ML algorithms has stimulated researchers to explore the ability of state-of-the-art methods to enhance the accuracy and robustness of predictive models.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Mixture Optimization of Recycled Aggregate Concrete Using Hybrid Machine Learning Model

2020

View full text Add to dashboard Cite

Recycled aggregate concrete (RAC) contributes to mitigating the depletion of natural aggregates, alleviating the carbon footprint of concrete construction, and averting the landfilling of colossal amounts of construction and demolition waste. However, complexities in the mixture optimization of RAC due to the variability of recycled aggregates and lack of accuracy in estimating its compressive strength require novel and sophisticated techniques. This paper aims at developing state-of-the-art machine learning models to predict the RAC compressive strength and optimize its mixture design. Results show that the developed models including Gaussian processes, deep learning, and gradient boosting regression achieved robust predictive performance, with the gradient boosting regression trees yielding highest prediction accuracy. Furthermore, a particle swarm optimization coupled with gradient boosting regression trees model was developed to optimize the mixture design of RAC for various compressive strength classes. The hybrid model achieved cost-saving RAC mixture designs with lower environmental footprint for different target compressive strength classes. The model could be further harvested to achieve sustainable concrete with optimal recycled aggregate content, least cost, and least environmental footprint.

show abstract

Section: Results Discussion and Recommendationscontrasting

confidence: 59%

Section: Results Discussion and Recommendationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mixture Optimization of Recycled Aggregate Concrete Using Hybrid Machine Learning Model

2020

View full text Add to dashboard Cite

show abstract

“…GUIDE is employed in various sectors like education, sports, and automobiles. MARS and M5 were also used for groundwater level forecasting, solar radiation, in the construction industry for evaluating mechanical properties of concretes containing coarse recycled concrete aggregates [66] and they have outperformed other algorithms in many scenarios. M 5 is used in various application areas like coastal engineering for prediction of wave height in Lake Superior [67], for scour depth prediction [68], in construction industry for predicting modulus elasticity of recycled concrete [63], etc.…”

Section: Application Details Of the Techniques Reviewed Under Dt For mentioning

confidence: 99%

DecisionTree for Classiﬁcation and Regression: A State-of-the Art Review

Jena

Dehuri

2020

IJCAI

View full text Add to dashboard Cite

Estimation of strengths of hybrid FR‐SCC by using deep‐learning and support vector regression models

Kına

Türk

Tanyıldızı

2022

Structural Concrete

View full text Add to dashboard Cite

In this work, to estimate the compressive, splitting tensile, and flexural strength of self‐compacting concrete (SCC) having single fiber and binary, ternary, and quaternary fiber hybridization, the deep‐learning (DL) and support vector regression (SVR) models were devised. The fiber content and coarse aggregate/total aggregate ratio (CA/TA) were the variables for 24 designed mixtures. Four different fibers, which were a macro steel fiber, two types of micro steel fibers with different aspect ratio, and polyvinyl alcohol (PVA) fiber, were used in SCC mixtures. The specimens of each mixture were tested to measure the engineering properties for 7, 28, and 90 days. The amount of cement, fly ash, fine aggregate, CA, high‐range water‐reducing admixture, water, macro steel fiber, PVA fiber, two types of micro steel fibers, and curing time were selected as input layers while the output layers were strength results. The experimental results were compared with the estimation results. The engineering properties were estimated using the SVR model with 95.25%, 87.81%, and 93.89% accuracy, respectively. Furthermore, the DL model estimated compressive strength, tensile strength, and flexural strength with 99.27%, 98.59%, and 99.15% accuracy, respectively. It was found that the DL estimated the engineering properties of hybrid fiber–reinforced SCC with higher accuracy than SVR.

show abstract

Evaluation of mechanical properties of concretes containing coarse recycled concrete aggregates using multivariate adaptive regression splines (MARS), M5 model tree (M5Tree), and least squares support vector regression (LSSVR) models

Cited by 104 publications

References 55 publications

Mixture Optimization of Recycled Aggregate Concrete Using Hybrid Machine Learning Model

Mixture Optimization of Recycled Aggregate Concrete Using Hybrid Machine Learning Model

DecisionTree for Classiﬁcation and Regression: A State-of-the Art Review

Estimation of strengths of hybrid FR‐SCC by using deep‐learning and support vector regression models

Contact Info

Product

Resources

About