scholarly journals Evaluating Slope Deformation of Earth Dams Due to Earthquake Shaking Using MARS and GMDH Techniques

2020 ◽  
Vol 10 (4) ◽  
pp. 1486 ◽  
Author(s):  
Mingxiang Cai ◽  
Mohammadreza Koopialipoor ◽  
Danial Jahed Armaghani ◽  
Binh Thai Pham
Keyword(s):  
Slope Deformation ◽  
Multivariate Adaptive Regression Splines ◽  
Machine Learning Techniques ◽  
Group Method ◽  
Earth Dams ◽  
Simulation Techniques ◽  
New Models ◽  
Adaptive Regression ◽  
Real Earthquake ◽  
Yield Acceleration

Assessing the behavior of earth dams under dynamic loads is one of the most significant problems with the design of such large structures. The purpose of this study is to provide new models for predicting dam dispersion in real earthquake conditions. In the first phase, 103 real cases of deformation in earth dams were collected and analyzed due to earthquakes that occurred over recent years. Using nonlinear and machine learning techniques, i.e., group method of data handling (GMDH) and multivariate adaptive regression splines (MARS), two models for prediction of the slope deformation in earth dams under the various types of earthquakes were applied and developed. The main parameters used in these simulation techniques were earthquake magnitude (Mw), fundamental period ratio (Td/Tp), yield acceleration ratio (ay/amax) as inputs and value of slope deformation (Dave) as output. Finally, in order to check the accuracy of the results of the new models, a comparison was made with the previous relations and models in seismic conditions for the slope deformation in earth dams. The results showed that the MARS model, which is able to provide a mathematical equation, has a better result than the GMDH model. These new models are recommended to be used for future analyses based on their flexible capabilities.

scholarly journals Prediction of Geosmin at Different Depths of Lake Using Machine Learning Techniques

2021 ◽  
Vol 18 (19) ◽  
pp. 10303
Author(s):  
Yong-Su Kwon ◽  
In-Hwan Cho ◽  
Ha-Kyung Kim ◽  
Jeong-Hwan Byun ◽  
Mi-Jung Bae ◽  
...  
Keyword(s):  
Environmental Variables ◽  
Bottom Layer ◽  
Multivariate Adaptive Regression Splines ◽  
Machine Learning Techniques ◽  
Phytoplankton Abundance ◽  
Learning Techniques ◽  
Water Layers ◽  
Adaptive Regression ◽  
Different Depths ◽  
Adaptive Regression Splines

Geosmin is a major concern in the management of water sources worldwide. Thus, we predicted concentration categories of geosmin at three different depths of lakes (i.e., surface, middle, and bottom), and analyzed relationships between geosmin concentration and factors such as phytoplankton abundance and environmental variables. Data were collected monthly from three major lakes (Uiam, Cheongpyeong, and Paldang lakes) in Korea from May 2014 to December 2015. Before predicting geosmin concentration, we categorized it into four groups based on the boxplot method, and multivariate adaptive regression splines, classification and regression trees, and random forest (RF) were applied to identify the most appropriate modelling to predict geosmin concentration. Overall, using environmental variables was more accurate than using phytoplankton abundance to predict the four categories of geosmin concentration based on AUC and accuracy in all three models as well as each layer. The RF model had the highest predictive power among the three SDMs. When predicting geosmin in the three water layers, the relative importance of environmental variables and phytoplankton abundance in the sensitivity analysis was different for each layer. Water temperature and abundance of Cyanophyceae were the most important factors for predicting geosmin concentration categories in the surface layer, whereas total abundance of phytoplankton exhibited relatively higher importance in the bottom layer.

Application of Machine Learning Techniques to Predict Software Reliability

2012 ◽  
pp. 237-253
Author(s):  
Ramakanta Mohanty ◽  
V. Ravi ◽  
M. R. Patra
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Software Reliability ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Multivariate Adaptive Regression Splines ◽  
Machine Learning Techniques ◽  
Group Method ◽  
Learning Techniques ◽  
Trained Neural Network

In this paper, the authors employed machine learning techniques, specifically, Back propagation trained neural network (BPNN), Group method of data handling (GMDH), Counter propagation neural network (CPNN), Dynamic evolving neuro–fuzzy inference system (DENFIS), Genetic Programming (GP), TreeNet, statistical multiple linear regression (MLR), and multivariate adaptive regression splines (MARS), to accurately forecast software reliability. Their effectiveness is demonstrated on three datasets taken from literature, where performance is compared in terms of normalized root mean square error (NRMSE) obtained in the test set. From rigorous experiments conducted, it was observed that GP outperformed all techniques in all datasets, with GMDH coming a close second.

Application of Machine Learning Techniques to Predict Software Reliability

2010 ◽  
Vol 1 (3) ◽  
pp. 70-86 ◽  
Author(s):  
Ramakanta Mohanty ◽  
V. Ravi ◽  
M. R. Patra
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Software Reliability ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Multivariate Adaptive Regression Splines ◽  
Machine Learning Techniques ◽  
Group Method ◽  
Inference System ◽  
Learning Techniques

In this paper, the authors employed machine learning techniques, specifically, Back propagation trained neural network (BPNN), Group method of data handling (GMDH), Counter propagation neural network (CPNN), Dynamic evolving neuro–fuzzy inference system (DENFIS), Genetic Programming (GP), TreeNet, statistical multiple linear regression (MLR), and multivariate adaptive regression splines (MARS), to accurately forecast software reliability. Their effectiveness is demonstrated on three datasets taken from literature, where performance is compared in terms of normalized root mean square error (NRMSE) obtained in the test set. From rigorous experiments conducted, it was observed that GP outperformed all techniques in all datasets, with GMDH coming a close second.

scholarly journals Prediction of aeration efficiency of parshall and modified venturi flumes: application of soft computing versus regression models

2021 ◽  
Author(s):  
Parveen Sihag ◽  
Omer Faruk Dursun ◽  
Saad Shauket Sammen ◽  
Anurag Malik ◽  
Anita Chauhan
Keyword(s):  
Soft Computing ◽  
Multivariate Adaptive Regression Splines ◽  
Oxygen Deficit ◽  
Group Method ◽  
Mars Model ◽  
Soft Computing Techniques ◽  
Aeration Efficiency ◽  
Adaptive Regression ◽  
Input Variables ◽  
Adaptive Regression Splines

Abstract In this study, the potential of soft computing techniques namely Random Forest (RF), M5P, Multivariate Adaptive Regression Splines (MARS), and Group Method of Data Handling (GMDH) was evaluated to predict the aeration efficiency (AE20) at Parshall and Modified Venturi flumes. Experiments were conducted for 26 various Modified Venturi flumes and one Parshall flume. A total of 99 observations were obtained from experiments. The results of soft computing models were compared with regression-based models (i.e., MLR: multiple linear regression, and MNLR: multiple nonlinear regression). Results of the analysis revealed that the MARS model outperformed other soft computing and regression-based models for predicting the AE20 at Parshall and Modified Venturi flumes with Pearson's correlation coefficient (CC) = 0.9997, and 0.9992, and root mean square error (RMSE) = 0.0015, and 0.0045 during calibration and validation periods. Sensitivity analysis was also carried out by using the best executing MARS model to assess the effect of individual input variables on AE20 of both flumes. Obtained results on sensitivity examination indicate that the oxygen deficit ratio (r) was the most effective input variable in predicting the AE20 at Parshall and Modified Venturi flumes.

Application of Machine Learning Techniques to Predict Software Reliability

2012 ◽  
pp. 354-370
Author(s):  
Ramakanta Mohanty ◽  
V. Ravi ◽  
M. R. Patra
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Software Reliability ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Multivariate Adaptive Regression Splines ◽  
Machine Learning Techniques ◽  
Group Method ◽  
Learning Techniques ◽  
Trained Neural Network

In this paper, the authors employed machine learning techniques, specifically, Back propagation trained neural network (BPNN), Group method of data handling (GMDH), Counter propagation neural network (CPNN), Dynamic evolving neuro–fuzzy inference system (DENFIS), Genetic Programming (GP), TreeNet, statistical multiple linear regression (MLR), and multivariate adaptive regression splines (MARS), to accurately forecast software reliability. Their effectiveness is demonstrated on three datasets taken from literature, where performance is compared in terms of normalized root mean square error (NRMSE) obtained in the test set. From rigorous experiments conducted, it was observed that GP outperformed all techniques in all datasets, with GMDH coming a close second.

scholarly journals Prediction of the critical temperature of a superconductor by using the WOA/MARS, Ridge, Lasso and Elastic-net machine learning techniques

2021 ◽  
Author(s):  
Paulino José García-Nieto ◽  
Esperanza García-Gonzalo ◽  
José Pablo Paredes-Sánchez
Keyword(s):  
Critical Temperature ◽  
Optimization Algorithm ◽  
Regression Models ◽  
Chemical Properties ◽  
Atomic Radius ◽  
Elastic Net ◽  
Multivariate Adaptive Regression Splines ◽  
Machine Learning Techniques ◽  
Humpback Whales ◽  
Whale Optimization

AbstractThis study builds a predictive model capable of estimating the critical temperature of a superconductor from experimentally determined physico-chemical properties of the material (input variables): features extracted from the thermal conductivity, atomic radius, valence, electron affinity and atomic mass. This original model is built using a novel hybrid algorithm relied on the multivariate adaptive regression splines (MARS) technique in combination with a nature-inspired meta-heuristic optimization algorithm termed the whale optimization algorithm (WOA) that mimics the social behavior of humpback whales. Additionally, the Ridge, Lasso and Elastic-net regression models were fitted to the same experimental data for comparison purposes. The results of the current investigation indicate that the critical temperature of a superconductor can be successfully predicted using this proposed hybrid WOA/MARS-based model. Furthermore, the results obtained with the Ridge, Lasso and Elastic-net regression models are clearly worse than those obtained with the WOA/MARS-based model.

Prediction of transportation energy demand: Multivariate Adaptive Regression Splines

Energy ◽  
2021 ◽  
Vol 224 ◽  
pp. 120090
Author(s):  
Mohammad Ali Sahraei ◽  
Hakan Duman ◽  
Muhammed Yasin Çodur ◽  
Ecevit Eyduran
Keyword(s):  
Energy Demand ◽  
Multivariate Adaptive Regression Splines ◽  
Regression Splines ◽  
Transportation Energy ◽  
Adaptive Regression ◽  
Adaptive Regression Splines
Sign in / Sign up

Export Citation Format

Share Document