A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer
The low quality of the collected fish image data directly from its habitat affects its feature qualities. Previous studies tended to be more concerned with finding the best method rather than the feature quality. This article proposes a new fish classification workflow using a combination of Contras...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BULGARIAN ACADEMY OF SCIENCES
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/278604/1/Santosa_TK.pdf |
| _version_ | 1797037314496528384 |
|---|---|
| author | Santosa, Paulus Insap Pramunendar, Ricardus Anggi |
| author_facet | Santosa, Paulus Insap Pramunendar, Ricardus Anggi |
| author_sort | Santosa, Paulus Insap |
| collection | UGM |
| description | The low quality of the collected fish image data directly from its habitat affects its feature qualities. Previous studies tended to be more concerned with finding the best method rather than the feature quality. This article proposes a new fish classification workflow using a combination of Contrast-Adaptive Color Correction (NCACC) image enhancement and optimization-based feature
construction called Grey Wolf Optimizer (GWO). This approach improves the image feature extraction results to obtain new and more meaningful features. This article compares the GWO-based and other optimization method-based fish classification on the newly generated features. The comparison results show that GWO-based classification had 0.22% lower accuracy than GA-based but 1.13 % higher than PSO. Based on ANOVA tests, the accuracy of GA and GWO were statistically indifferent, and GWO and PSO were statistically different. On the other hand, GWO-based
performed 0.61 times faster than GA-based classification and 1.36 minutes faster than the other. |
| first_indexed | 2024-03-14T00:01:30Z |
| format | Article |
| id | oai:generic.eprints.org:278604 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-14T00:01:30Z |
| publishDate | 2022 |
| publisher | BULGARIAN ACADEMY OF SCIENCES |
| record_format | dspace |
| spelling | oai:generic.eprints.org:2786042023-11-02T02:09:06Z https://repository.ugm.ac.id/278604/ A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer Santosa, Paulus Insap Pramunendar, Ricardus Anggi Electrical and Electronic Engineering Engineering The low quality of the collected fish image data directly from its habitat affects its feature qualities. Previous studies tended to be more concerned with finding the best method rather than the feature quality. This article proposes a new fish classification workflow using a combination of Contrast-Adaptive Color Correction (NCACC) image enhancement and optimization-based feature construction called Grey Wolf Optimizer (GWO). This approach improves the image feature extraction results to obtain new and more meaningful features. This article compares the GWO-based and other optimization method-based fish classification on the newly generated features. The comparison results show that GWO-based classification had 0.22% lower accuracy than GA-based but 1.13 % higher than PSO. Based on ANOVA tests, the accuracy of GA and GWO were statistically indifferent, and GWO and PSO were statistically different. On the other hand, GWO-based performed 0.61 times faster than GA-based classification and 1.36 minutes faster than the other. BULGARIAN ACADEMY OF SCIENCES 2022-11-10 Article PeerReviewed application/pdf en https://repository.ugm.ac.id/278604/1/Santosa_TK.pdf Santosa, Paulus Insap and Pramunendar, Ricardus Anggi (2022) A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer. Cybernetics and Information Technologies, 22 (4). pp. 152-166. ISSN 1314-4081 https://sciendo.com/article/10.2478/cait-2022-0045 10.2478/cait-2022-0045 |
| spellingShingle | Electrical and Electronic Engineering Engineering Santosa, Paulus Insap Pramunendar, Ricardus Anggi A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer |
| title | A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer |
| title_full | A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer |
| title_fullStr | A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer |
| title_full_unstemmed | A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer |
| title_short | A Robust Feature Construction for Fish Classification Using Grey Wolf Optimizer |
| title_sort | robust feature construction for fish classification using grey wolf optimizer |
| topic | Electrical and Electronic Engineering Engineering |
| url | https://repository.ugm.ac.id/278604/1/Santosa_TK.pdf |
| work_keys_str_mv | AT santosapaulusinsap arobustfeatureconstructionforfishclassificationusinggreywolfoptimizer AT pramunendarricardusanggi arobustfeatureconstructionforfishclassificationusinggreywolfoptimizer AT santosapaulusinsap robustfeatureconstructionforfishclassificationusinggreywolfoptimizer AT pramunendarricardusanggi robustfeatureconstructionforfishclassificationusinggreywolfoptimizer |