Uplift Capacity of Suction Caisson in Clay Using Artificial Intelligence Techniques

Muduli, Pradyut Kumar; Das, M. M.; Samui, Pijush; Das, Sarat Kumar

doi:10.1080/1064119x.2012.690827

Cited by 37 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The models were executed on Intel Core i5 @3.2GHz processor with 4 GB RAM. The computational e ciencies of the other methods were not available in the literature for comparison [37,44].…”

Section: Resultsmentioning

confidence: 99%

“…The database consists of 62 experimental test results from 12 independent studies. Out of the 62 data, 51 data are selected for training, and the remaining 11 are used for testing the GP, ANN, SVM, RVM, and FEM models as per Muduli et al [37] and ELM model as per Muduli et al [44]. For FN prediction model, Kenstone algorithm, based on Kennard and Stone [59], has been used to select training and testing data.…”

Section: Experimental Database and Data Preprocessingmentioning

confidence: 99%

“…another group of AI techniques, are based on statistical learning theory [30,31]; they are found to be better than the ANN model for some geotechnical engineering problems [32]. In the recent past, Genetic Programming (GP), which is a biologically inspired AI method, has been used as an AI technique to model di cult geotechnical engineering problems [33][34][35][36][37][38]. Alavi et al [39] found that a hybrid computational model (coupling of GP and simulated annealing) provided a better prediction performance than GP did, by predicting the uplift capacity of suction caisson using the above database (Rahman et al [26]).…”

Section: Introductionmentioning

confidence: 99%

“…Di erent statistical criteria, such as correlation coefcient (R), Nash-Sutcli e coe cient of e ciency (E), Root Mean Square Error (RMSE), Average Absolute Error (AAE), and Maximum Absolute Error (MAE), are used to compare the FN model with the presently developed MARS model and with GP, FEM, ANN, SVM, RVM, and ELM models as available in literature [37,44]. A ranking system (according to AbuFarsakh and Titi [54]) based on the following four criteria has been also used to compare di erent models:…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Prediction of Uplift Capacity of Suction Caisson in Clay Using Functional Network and Multivariate Adaptive Regression Spline

2017

View full text Add to dashboard Cite

Abstract. Suction caissons are extensively used as anchors for o shore foundation structures. The uplift capacity of suction caisson is an important factor with respect to e ective design. In this paper, two recently developed AI techniques, i.e. Functional Network (FN) and Multivariate Adaptive Regression Spline (MARS), have been used to predict the uplift capacity of suction caisson in clay. The performances of the developed models are compared with those of other AI techniques: arti cial neural network, support vector machine, relevance vector machine, genetic programming, extreme learning machine, and Group Method of Data Handling with Harmony Search (GMDH-HS). The model's inputs include the aspect ratio of the caisson, undrained shear strength of soil at the depth of the caisson tip, relative depth of the lug to which the caisson force is applied, load inclination angle, and load rate parameter. The results of the above AI techniques are comparatively analysed via di erent statistical performance criteria: correlation coe cient (R), root mean square error, Nash-Sutcli e coe cient of e ciency, and log-normal distribution of ratio of the predicted load capacity to observed load capacity, with a ranking system to determine the best predictive model. The FN and MARS models are found to be comparably e cient which can outperform other AI techniques.

show abstract

“…The models were executed on Intel Core i5 @3.2GHz processor with 4 GB RAM. The computational e ciencies of the other methods were not available in the literature for comparison [37,44].…”

Section: Resultsmentioning

confidence: 99%

Section: Experimental Database and Data Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of Uplift Capacity of Suction Caisson in Clay Using Functional Network and Multivariate Adaptive Regression Spline

2017

View full text Add to dashboard Cite

show abstract

“…Though, SVM has better generalization (Samui 2008) compared to ANN, error parameter 'C' and 'e' are to be found out by trial and error. Using the above database, Muduli et al (2013) observed that prediction model using genetic programming (GP) is more efficient compared to ANN and SVM model. It may be mentioned here that unlike ANN, GP is a 'grey box' model (Giustolisi et al 2007), but the model parameters are found out by nontraditional optimization method, genetic algorithm and it is very difficult to explain the development of model.…”

Section: Introductionmentioning

confidence: 99%

Prediction of uplift capacity of suction caisson in clay using extreme learning machine

Muduli¹,

Das²,

Samui³

et al. 2015

Ocean Systems Engineering

Self Cite

View full text Add to dashboard Cite

This study presents the development of predictive models for uplift capacity of suction caisson in clay using an artificial intelligence technique, extreme learning machine (ELM). Other artificial intelligence models like artificial neural network (ANN), support vector machine (SVM), relevance vector machine (RVM) models are also developed to compare the ELM model with above models and available numerical models in terms of different statistical criteria. A ranking system is presented to evaluate present models in identifying the 'best' model. Sensitivity analyses are made to identify important inputs contributing to the developed models.

show abstract

Evaluation of Liquefaction Potential of Soil Based on Shear Wave Velocity Using Multi-Gene Genetic Programming

Muduli

Das

2015

Handbook of Genetic Programming Applications

View full text Add to dashboard Cite

Uplift Capacity of Suction Caisson in Clay Using Artificial Intelligence Techniques

Cited by 37 publications

References 30 publications

Prediction of Uplift Capacity of Suction Caisson in Clay Using Functional Network and Multivariate Adaptive Regression Spline

Prediction of Uplift Capacity of Suction Caisson in Clay Using Functional Network and Multivariate Adaptive Regression Spline

Prediction of uplift capacity of suction caisson in clay using extreme learning machine

Evaluation of Liquefaction Potential of Soil Based on Shear Wave Velocity Using Multi-Gene Genetic Programming

Contact Info

Product

Resources

About