Developing random forest hybridization models for estimating the axial bearing capacity of pile.
Accurate determination of the axial load capacity of the pile is of utmost importance when designing the pile foundation. However, the methods of determining the axial load capacity of the pile in the field are often costly and time-consuming. Therefore, the purpose of this study is to develop a hyb...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0265747 |
| _version_ | 1811306011911258112 |
|---|---|
| author | Tuan Anh Pham Van Quan Tran |
| author_facet | Tuan Anh Pham Van Quan Tran |
| author_sort | Tuan Anh Pham |
| collection | DOAJ |
| description | Accurate determination of the axial load capacity of the pile is of utmost importance when designing the pile foundation. However, the methods of determining the axial load capacity of the pile in the field are often costly and time-consuming. Therefore, the purpose of this study is to develop a hybrid machine-learning to predict the axial load capacity of the pile. In particular, two powerful optimization algorithms named Herd Optimization (PSO) and Genetic Algorithm (GA) were used to evolve the Random Forest (RF) model architecture. For the research, the data set including 472 results of pile load tests in Ha Nam province-Vietnam was used to build and test the machine-learning models. The data set was divided into training and testing parts with ratio of 80% and 20%, respectively. Various performance indicators, namely absolute mean error (MAE), mean square root error (RMSE), and coefficient of determination (R2) are used to evaluate the performance of RF models. The results showed that, between the two optimization algorithms, GA gave superior performance compared to PSO in finding the best RF model architecture. In addition, the RF-GA model is also compared with the default RF model, the results show that the RF-GA model gives the best performance, with the balance on training and testing set, meaning avoiding the phenomenon of overfitting. The results of the study suggest a potential direction in the development of machine learning models in engineering in general and geotechnical engineering in particular. |
| first_indexed | 2024-04-13T08:36:42Z |
| format | Article |
| id | doaj.art-723e101a23ae4671bfae3ce539e34048 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-13T08:36:42Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-723e101a23ae4671bfae3ce539e340482022-12-22T02:54:03ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01173e026574710.1371/journal.pone.0265747Developing random forest hybridization models for estimating the axial bearing capacity of pile.Tuan Anh PhamVan Quan TranAccurate determination of the axial load capacity of the pile is of utmost importance when designing the pile foundation. However, the methods of determining the axial load capacity of the pile in the field are often costly and time-consuming. Therefore, the purpose of this study is to develop a hybrid machine-learning to predict the axial load capacity of the pile. In particular, two powerful optimization algorithms named Herd Optimization (PSO) and Genetic Algorithm (GA) were used to evolve the Random Forest (RF) model architecture. For the research, the data set including 472 results of pile load tests in Ha Nam province-Vietnam was used to build and test the machine-learning models. The data set was divided into training and testing parts with ratio of 80% and 20%, respectively. Various performance indicators, namely absolute mean error (MAE), mean square root error (RMSE), and coefficient of determination (R2) are used to evaluate the performance of RF models. The results showed that, between the two optimization algorithms, GA gave superior performance compared to PSO in finding the best RF model architecture. In addition, the RF-GA model is also compared with the default RF model, the results show that the RF-GA model gives the best performance, with the balance on training and testing set, meaning avoiding the phenomenon of overfitting. The results of the study suggest a potential direction in the development of machine learning models in engineering in general and geotechnical engineering in particular.https://doi.org/10.1371/journal.pone.0265747 |
| spellingShingle | Tuan Anh Pham Van Quan Tran Developing random forest hybridization models for estimating the axial bearing capacity of pile. PLoS ONE |
| title | Developing random forest hybridization models for estimating the axial bearing capacity of pile. |
| title_full | Developing random forest hybridization models for estimating the axial bearing capacity of pile. |
| title_fullStr | Developing random forest hybridization models for estimating the axial bearing capacity of pile. |
| title_full_unstemmed | Developing random forest hybridization models for estimating the axial bearing capacity of pile. |
| title_short | Developing random forest hybridization models for estimating the axial bearing capacity of pile. |
| title_sort | developing random forest hybridization models for estimating the axial bearing capacity of pile |
| url | https://doi.org/10.1371/journal.pone.0265747 |
| work_keys_str_mv | AT tuananhpham developingrandomforesthybridizationmodelsforestimatingtheaxialbearingcapacityofpile AT vanquantran developingrandomforesthybridizationmodelsforestimatingtheaxialbearingcapacityofpile |