Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels
A vital topic regarding the optimum and economical design of rigid boundary open channels such as sewers and drainage systems is determining the movement of sediment particles. In this study, the incipient motion of sediment is estimated using three datasets from literature, including a wide range...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter Open
2016
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/36890/ http://eprints.usm.my/36890/1/%28Design_of_a_new_hybrid_artificial%29.pdf |
| _version_ | 1848878037875032064 |
|---|---|
| author | Ebtehaj, Isa Bonakdari, Hossein Hossein Zaji, Amir Hin, Charles Joo Bong Ghani, Aminuddin Ab |
| author_facet | Ebtehaj, Isa Bonakdari, Hossein Hossein Zaji, Amir Hin, Charles Joo Bong Ghani, Aminuddin Ab |
| author_sort | Ebtehaj, Isa |
| building | USM Institutional Repository |
| collection | Online Access |
| description | A vital topic regarding the optimum and economical design of rigid boundary open channels such as sewers
and drainage systems is determining the movement of sediment particles. In this study, the incipient motion of sediment is estimated using three datasets from literature, including a wide range of hydraulic parameters. Because existing equationsdo not consider the effect of sediment bed thickness on incipient motion estimation, this parameter is applied in this study along with the multilayer perceptron (MLP), a hybrid method based on decision trees (DT) (MLP-DT), to estimate
incipient motion. According to a comparison with the observed experimental outcome, the proposed method performs well (MARE = 0.048, RMSE = 0.134, SI = 0.06, BIAS = –0.036). The performance of MLP and MLP-DT is compared with that of existing regression-based equations, and significantly higher performance over existing models is observed. Finally, an explicit expression for practical engineering is also provided. |
| first_indexed | 2025-11-15T17:24:58Z |
| format | Article |
| id | usm-36890 |
| institution | Universiti Sains Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T17:24:58Z |
| publishDate | 2016 |
| publisher | De Gruyter Open |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | usm-368902018-08-17T02:53:43Z http://eprints.usm.my/36890/ Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels Ebtehaj, Isa Bonakdari, Hossein Hossein Zaji, Amir Hin, Charles Joo Bong Ghani, Aminuddin Ab TC401-506 River, lake, and water-supply engineering (General) A vital topic regarding the optimum and economical design of rigid boundary open channels such as sewers and drainage systems is determining the movement of sediment particles. In this study, the incipient motion of sediment is estimated using three datasets from literature, including a wide range of hydraulic parameters. Because existing equationsdo not consider the effect of sediment bed thickness on incipient motion estimation, this parameter is applied in this study along with the multilayer perceptron (MLP), a hybrid method based on decision trees (DT) (MLP-DT), to estimate incipient motion. According to a comparison with the observed experimental outcome, the proposed method performs well (MARE = 0.048, RMSE = 0.134, SI = 0.06, BIAS = –0.036). The performance of MLP and MLP-DT is compared with that of existing regression-based equations, and significantly higher performance over existing models is observed. Finally, an explicit expression for practical engineering is also provided. De Gruyter Open 2016-09 Article PeerReviewed application/pdf en http://eprints.usm.my/36890/1/%28Design_of_a_new_hybrid_artificial%29.pdf Ebtehaj, Isa and Bonakdari, Hossein and Hossein Zaji, Amir and Hin, Charles Joo Bong and Ghani, Aminuddin Ab (2016) Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels. Journal of Hydrology and Hydromechanics, 64 (3). pp. 252-260. ISSN 0042-790X https://doi.org/10.1515/johh-2016-0031 |
| spellingShingle | TC401-506 River, lake, and water-supply engineering (General) Ebtehaj, Isa Bonakdari, Hossein Hossein Zaji, Amir Hin, Charles Joo Bong Ghani, Aminuddin Ab Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels |
| title | Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels |
| title_full | Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels |
| title_fullStr | Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels |
| title_full_unstemmed | Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels |
| title_short | Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels |
| title_sort | design of a new hybrid artificial neural network method based on decision trees for calculating the froude number in rigid rectangular channels |
| topic | TC401-506 River, lake, and water-supply engineering (General) |
| url | http://eprints.usm.my/36890/ http://eprints.usm.my/36890/ http://eprints.usm.my/36890/1/%28Design_of_a_new_hybrid_artificial%29.pdf |