Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method
Copper deposits; Deposits; Geology; Learning algorithms; Mineralogy; Static Var compensators; Support vector machines; Three dimensional computer graphics; Alteration zones; Grid search; Grid-search method; Mineralization zone; Model Selection; Particle swarm optimization algorithm; Penalty paramete...
Saved in:
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Elsevier Ltd
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Tenaga Nasional |
| id |
my.uniten.dspace-26815 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-268152023-05-29T17:36:55Z Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method Abbaszadeh M. Soltani-Mohammadi S. Ahmed A.N. 54419507900 54929872400 57214837520 Copper deposits; Deposits; Geology; Learning algorithms; Mineralogy; Static Var compensators; Support vector machines; Three dimensional computer graphics; Alteration zones; Grid search; Grid-search method; Mineralization zone; Model Selection; Particle swarm optimization algorithm; Penalty parameters; Performance; Support vector classifiers; Support vectors machine; Particle swarm optimization (PSO); accuracy assessment; algorithm; classification; computer simulation; copper; geological survey; mineral alteration; mineralization; numerical model; ore deposit; parameterization; performance assessment; porphyry; resource assessment; support vector machine; three-dimensional modeling; Iran The support vector classifier (SVC) is one of the most powerful machine learning algorithms. This algorithm has been accepted as an effective method in three-dimensional geological modeling. Although the model selection has a great impact on the performance of SVC algorithm, most of mining studies have neglected it and used the grid search method. Therefore, in this study, a new approach is proposed for improving the selection of SVC models. This approach uses particle swarm optimization (PSO) to determine the important parameters of SCV such as penalty and kernel parameters. The proposed approach was applied in the modeling process of the Iju porphyry copper deposit to delineate alteration and mineralization zones. The optimal penalty and kernel parameters were found to be 27.2 and 2?4.75 for alteration zone, and 22.72 and 2?6.23 for mineralization zone, respectively. With 97.4% and 97.01% rates of accuracy for mineralization and alteration zones, the PSO results showed reasonable performance in classification. The proposed approach had better accuracy than grid search method. Therefore, because of its better performance, the geological models were developed using the PSO method to be used as a basis for future resource evaluation. � 2022 Elsevier Ltd Final 2023-05-29T09:36:55Z 2023-05-29T09:36:55Z 2022 Article 10.1016/j.cageo.2022.105140 2-s2.0-85130520033 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85130520033&doi=10.1016%2fj.cageo.2022.105140&partnerID=40&md5=20de9ab6cb5e11df0ac08cddcc5b0d49 https://irepository.uniten.edu.my/handle/123456789/26815 165 105140 Elsevier Ltd Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Copper deposits; Deposits; Geology; Learning algorithms; Mineralogy; Static Var compensators; Support vector machines; Three dimensional computer graphics; Alteration zones; Grid search; Grid-search method; Mineralization zone; Model Selection; Particle swarm optimization algorithm; Penalty parameters; Performance; Support vector classifiers; Support vectors machine; Particle swarm optimization (PSO); accuracy assessment; algorithm; classification; computer simulation; copper; geological survey; mineral alteration; mineralization; numerical model; ore deposit; parameterization; performance assessment; porphyry; resource assessment; support vector machine; three-dimensional modeling; Iran |
| author2 |
54419507900 |
| author_facet |
54419507900 Abbaszadeh M. Soltani-Mohammadi S. Ahmed A.N. |
| format |
Article |
| author |
Abbaszadeh M. Soltani-Mohammadi S. Ahmed A.N. |
| spellingShingle |
Abbaszadeh M. Soltani-Mohammadi S. Ahmed A.N. Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method |
| author_sort |
Abbaszadeh M. |
| title |
Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method |
| title_short |
Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method |
| title_full |
Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method |
| title_fullStr |
Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method |
| title_full_unstemmed |
Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method |
| title_sort |
optimization of support vector machine parameters in modeling of iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method |
| publisher |
Elsevier Ltd |
| publishDate |
2023 |
| _version_ |
1806424524549259264 |