Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization Algorithms
To ensure the safety of constructions such as bridge-owned structures, they must be immunized for the operational period. Considering the Pile settlement (PS) factor has to be an important project issue, much attention is paid to prevent damage before construction. Various items are considered to ev...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2023-06-01
|
| Series: | Advances in Engineering and Intelligence Systems |
| Subjects: | |
| Online Access: | https://aeis.bilijipub.com/article_172771_6ab5e00f69fe969ecea2baa066770f92.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856438796091392 |
|---|---|
| author | Argyros Maris |
| author_facet | Argyros Maris |
| author_sort | Argyros Maris |
| collection | DOAJ |
| description | To ensure the safety of constructions such as bridge-owned structures, they must be immunized for the operational period. Considering the Pile settlement (PS) factor has to be an important project issue, much attention is paid to prevent damage before construction. Various items are considered to evaluate the movement of the piles that certainly help to understand a future picture of the project over the loading period. Most intelligent mathematical strategies in calculating the pile motion are operated. In this regard, the present research has used a machine learning technique: support vector regression (SVR). As a novelty of this research, two optimizers were used to find the key variables of SVR at optimum level to fine PS accurately. Biogeography-Based Optimization (BBO) and Flow Direction Algorithm (FDA) were coupled with SVR to create the SVR-FDA and SVR-BBO frameworks. Moreover, several metrics have been used to assess the overall performance of models. The R2 of the training phase for SVR-FDA was found 99.39 percent shows a great modeling process, while the RMSE of this model was calculated 0.4286 mm. The OBJ index as a comprehensive indicator including MAE, RMSE, and R2 was obtained 0.2499 mm. |
| format | Article |
| id | doaj-art-8274df6669c448a89a0ca10ce04ba30d |
| institution | Kabale University |
| issn | 2821-0263 |
| language | English |
| publishDate | 2023-06-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Advances in Engineering and Intelligence Systems |
| spelling | doaj-art-8274df6669c448a89a0ca10ce04ba30d2025-02-12T08:47:10ZengBilijipub publisherAdvances in Engineering and Intelligence Systems2821-02632023-06-010020211210.22034/aeis.2023.382628.1067172771Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization AlgorithmsArgyros Maris0Department of Communication and Digital Media, University of Western Macedonia, Kastoria, 52100, GreeceTo ensure the safety of constructions such as bridge-owned structures, they must be immunized for the operational period. Considering the Pile settlement (PS) factor has to be an important project issue, much attention is paid to prevent damage before construction. Various items are considered to evaluate the movement of the piles that certainly help to understand a future picture of the project over the loading period. Most intelligent mathematical strategies in calculating the pile motion are operated. In this regard, the present research has used a machine learning technique: support vector regression (SVR). As a novelty of this research, two optimizers were used to find the key variables of SVR at optimum level to fine PS accurately. Biogeography-Based Optimization (BBO) and Flow Direction Algorithm (FDA) were coupled with SVR to create the SVR-FDA and SVR-BBO frameworks. Moreover, several metrics have been used to assess the overall performance of models. The R2 of the training phase for SVR-FDA was found 99.39 percent shows a great modeling process, while the RMSE of this model was calculated 0.4286 mm. The OBJ index as a comprehensive indicator including MAE, RMSE, and R2 was obtained 0.2499 mm.https://aeis.bilijipub.com/article_172771_6ab5e00f69fe969ecea2baa066770f92.pdfpile settlementmachine learningsupport vector regressionflow direction algorithmbiogeography-based optimizationrmse |
| spellingShingle | Argyros Maris Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization Algorithms Advances in Engineering and Intelligence Systems pile settlement machine learning support vector regression flow direction algorithm biogeography-based optimization rmse |
| title | Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization Algorithms |
| title_full | Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization Algorithms |
| title_fullStr | Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization Algorithms |
| title_full_unstemmed | Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization Algorithms |
| title_short | Appraising the Pile Settlement Rates by Support Vector Regression Optimized Using the Novel Optimization Algorithms |
| title_sort | appraising the pile settlement rates by support vector regression optimized using the novel optimization algorithms |
| topic | pile settlement machine learning support vector regression flow direction algorithm biogeography-based optimization rmse |
| url | https://aeis.bilijipub.com/article_172771_6ab5e00f69fe969ecea2baa066770f92.pdf |
| work_keys_str_mv | AT argyrosmaris appraisingthepilesettlementratesbysupportvectorregressionoptimizedusingthenoveloptimizationalgorithms |