Prediction of Lateral Deflection of Small-Scale Piles Using Hybrid PSO–ANN Model

Khari, Mahdy; Armaghani, Danial Jahed; Dehghanbanadaki, Ali

doi:10.1007/s13369-019-04134-9

Cited by 28 publications

(13 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present study used five performance indices to assess the performance of the models developed. These included coefficient of determination (R 2 ), mean absolute error (MAE), root-mean-square error (RMSE), variance accounted for (VAF), and a20-index [32,[40][41][42]44,[94][95][96][97]. These indices were widely used in previous studies for the performance assessment of ML models.…”

Section: Assessment Of the Proposed Modelsmentioning

confidence: 99%

A Combination of Feature Selection and Random Forest Techniques to Solve a Problem Related to Blast-Induced Ground Vibration

et al. 2020

Self Cite

View full text Add to dashboard Cite

In mining and civil engineering applications, a reliable and proper analysis of ground vibration due to quarry blasting is an extremely important task. While advances in machine learning led to numerous powerful regression models, the usefulness of these models for modeling the peak particle velocity (PPV) remains largely unexplored. Using an extensive database comprising quarry site datasets enriched with vibration variables, this article compares the predictive performance of five selected machine learning classifiers, including classification and regression trees (CART), chi-squared automatic interaction detection (CHAID), random forest (RF), artificial neural network (ANN), and support vector machine (SVM) for PPV analysis. Before conducting these model developments, feature selection was applied in order to select the most important input parameters for PPV. The results of this study show that RF performed substantially better than any of the other investigated regression models, including the frequently used SVM and ANN models. The results and process analysis of this study can be utilized by other researchers/designers in similar fields.

show abstract

Section: Assessment Of the Proposed Modelsmentioning

confidence: 99%

A Combination of Feature Selection and Random Forest Techniques to Solve a Problem Related to Blast-Induced Ground Vibration

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Note that, for the references listed in Table 1, the dataset in various cases ranged between 75 and 150. Similarly, some papers predicted the ultimate bearing capacity and settlement of the piles using experimental data with help from different soft computing techniques (Nazir, Momeni, Marsono, and Sohaie, 2013;Nazir et al 2015b;Momeni et al 2015a;Harandizadeh, Armaghani, and Khari, 2019;Chen et al 2020;Khari et al 2020;Yong et al 2020). Furthermore, the results obtained from all the studies above indicated that ANN-based predictive models could be satisfactorily used in predicting the bearing capacity and the settlement of regular shaped footings.…”

Section: Introductionmentioning

confidence: 97%

Bearing capacity and settlement prediction of multi-edge skirted footings resting on sand

Gnananandarao

Khatri

Dutta³

2020

Ing. Inv.

View full text Add to dashboard Cite

This paper presents the application of artificial neural networks (ANN) and multivariable regression analysis (MRA) to predict the bearing capacity and the settlement of multi-edge skirted footings on sand. Respectively, these parameters are defined in terms of the bearing capacity ratio (BCR) of skirted to unskirted footing and the settlement reduction factor (SRF), the ratio of the difference in settlement of unskirted and skirted footing to the settlement of unskirted footing at a given pressure. The model equations for the prediction of the BCR and the SRF of the regular shaped footing were first developed using the available data collected from the literature. These equations were later modified to predict the BCR and the SRF of the multi-edge skirted footing, for which the data were generated by conducting a small scale laboratory test. The input parameters chosen to develop ANN models were the angle of internal friction (ϕ) and skirt depth (Ds) to the width of the footing (B) ratio for the prediction of the BCR; as for the SRF one additional input parameter was considered: normal stress (𝛔). The architecture for the developed ANN models was 2-2-1 and 3-2-1 for the BCR and the SRF, respectively. The R2 for the multi-edge skirted footings was in the range of 0,940-0,977 for the ANN model and 0,827-0,934 for the regression analysis. Similarly, the R2 for the SRF prediction might have been 0,913-0,985 for the ANN model and 0,739-0,932 for the regression analysis. It was revealed that the predicted BCR and SRF for the multi-edge skirted footings with the use of ANN is superior to MRA. Furthermore, the results of the sensitivity analysis indicate that both the BCR and the SRF of the multi-edge skirted footings are mostly affected by skirt depth, followed by the friction angle of the sand.

show abstract

“…But, MLP-GWO model provided better results in terms of R 2 -value 0.991 for test data. Khari et al [44] used hybrid neuro-swarm method to forecast the lateral defection of piles. In the lateral deflection prediction process, the suggested PSO-ANN model was proven to be capable of giving high accuracy while also having a low system error.…”

Section: Introductionmentioning

confidence: 99%

An Optimized Neuro-Bee Algorithm Approach to Predict the FRP-Concrete Bond Strength of RC Beams

et al. 2022

View full text Add to dashboard Cite

Over the world, there is growing worry about the corrosion of reinforced concrete structures. Structure repair, rehabilitation, replacement, and new structures all require cost-effective and long-lasting technologies. Fiber Reinforced Polymer (FRP) has been widely employed in both retrofitting existing structures and building new ones. Due to its varied qualities in reinforced concrete and masonry constructions as a repair composite material, FRP have seen a rise in use over the last decade. This material have several advantages such as high stiffness-to-weight and strength-to-weight ratios, light weight, possibly high longevity, and relative ease of usage in the field. Among all the parameters the bond between concrete and FRP composite play an important role in the strengthening of structures. However, the bond behaviour of the FRP-concrete interface is complex, with several failure modes, making the bond strength difficult to forecast, resulting in the FRP strengthened concrete structure. To overcome such kind of issues machine learning models are sufficient to forecast the bond strength of FRP-concrete. In this article Artificial Neural Network (ANN), optimized Artificial Bee Colony (ABC)-ANN and Gaussian Process Regression (GPR) algorithms are deployed to predict the bond strength. The R-value of ABC-ANN and GPR models are 0.9514 and 0.9618 respectively. This research aids researchers in estimating bond strength in less time, at a lower cost, and with less experimental work.INDEX TERMS ABC-ANN, ANN, Bond strength, FRP-concrete bond, FRP, Machine leaning.

show abstract

Prediction of Lateral Deflection of Small-Scale Piles Using Hybrid PSO–ANN Model

Cited by 28 publications

References 73 publications

A Combination of Feature Selection and Random Forest Techniques to Solve a Problem Related to Blast-Induced Ground Vibration

A Combination of Feature Selection and Random Forest Techniques to Solve a Problem Related to Blast-Induced Ground Vibration

Bearing capacity and settlement prediction of multi-edge skirted footings resting on sand

An Optimized Neuro-Bee Algorithm Approach to Predict the FRP-Concrete Bond Strength of RC Beams

Contact Info

Product

Resources

About