Robust optimization of SVM hyper-parameters for spillway type selection
Spillways, which play a vital role in dams, can be built in various types. Although several studies have been conducted on hydraulic calculations of spillways, studies on type selection that require heuristics knowledge were limited. The tuning of the hyperparameters in machine learning algorithms i...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-09-01
|
Series: | Ain Shams Engineering Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447921000423 |
id |
doaj-67268537b5fa4425a32d966b418d55f7 |
---|---|
record_format |
Article |
spelling |
doaj-67268537b5fa4425a32d966b418d55f72021-09-17T04:35:16ZengElsevierAin Shams Engineering Journal2090-44792021-09-0112324132423Robust optimization of SVM hyper-parameters for spillway type selectionEnes Gul0Nuh Alpaslan1M. Emin Emiroglu2Inonu University, Department of Civil Engineering, 44280 Malatya, Turkey; Corresponding author.Bingol University, Department of Computer Engineering, 12000 Bingol, TurkeyFirat University, Department of Civil Engineering, 23100 Elazığ, TurkeySpillways, which play a vital role in dams, can be built in various types. Although several studies have been conducted on hydraulic calculations of spillways, studies on type selection that require heuristics knowledge were limited. The tuning of the hyperparameters in machine learning algorithms is still an open problem. In this paper, a parallel global optimization algorithm is proposed optimizing the hyperparameters of a Support Vector Machine (SVM) classification model for providing accurate spillway type selection (STS). The random forest method is used to obtain the relative importance of input variables. Besides, a novel spillway dataset was introduced and a novel STS software tool has been developed based on different machine learning algorithms. Several experiments are carried out to demonstrate the effectiveness of the proposed tool and the reliability of data. The hyper-parameters optimized SVM was achieved the best results with 93.81% classification accuracy.http://www.sciencedirect.com/science/article/pii/S2090447921000423Energy dissipationDam typeHyper-parameter optimizationSupport vector machineHydraulic structure |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Enes Gul Nuh Alpaslan M. Emin Emiroglu |
spellingShingle |
Enes Gul Nuh Alpaslan M. Emin Emiroglu Robust optimization of SVM hyper-parameters for spillway type selection Ain Shams Engineering Journal Energy dissipation Dam type Hyper-parameter optimization Support vector machine Hydraulic structure |
author_facet |
Enes Gul Nuh Alpaslan M. Emin Emiroglu |
author_sort |
Enes Gul |
title |
Robust optimization of SVM hyper-parameters for spillway type selection |
title_short |
Robust optimization of SVM hyper-parameters for spillway type selection |
title_full |
Robust optimization of SVM hyper-parameters for spillway type selection |
title_fullStr |
Robust optimization of SVM hyper-parameters for spillway type selection |
title_full_unstemmed |
Robust optimization of SVM hyper-parameters for spillway type selection |
title_sort |
robust optimization of svm hyper-parameters for spillway type selection |
publisher |
Elsevier |
series |
Ain Shams Engineering Journal |
issn |
2090-4479 |
publishDate |
2021-09-01 |
description |
Spillways, which play a vital role in dams, can be built in various types. Although several studies have been conducted on hydraulic calculations of spillways, studies on type selection that require heuristics knowledge were limited. The tuning of the hyperparameters in machine learning algorithms is still an open problem. In this paper, a parallel global optimization algorithm is proposed optimizing the hyperparameters of a Support Vector Machine (SVM) classification model for providing accurate spillway type selection (STS). The random forest method is used to obtain the relative importance of input variables. Besides, a novel spillway dataset was introduced and a novel STS software tool has been developed based on different machine learning algorithms. Several experiments are carried out to demonstrate the effectiveness of the proposed tool and the reliability of data. The hyper-parameters optimized SVM was achieved the best results with 93.81% classification accuracy. |
topic |
Energy dissipation Dam type Hyper-parameter optimization Support vector machine Hydraulic structure |
url |
http://www.sciencedirect.com/science/article/pii/S2090447921000423 |
work_keys_str_mv |
AT enesgul robustoptimizationofsvmhyperparametersforspillwaytypeselection AT nuhalpaslan robustoptimizationofsvmhyperparametersforspillwaytypeselection AT meminemiroglu robustoptimizationofsvmhyperparametersforspillwaytypeselection |
_version_ |
1717377730964619264 |