EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNING
Automated fish identification system has a beneficial role in various fields. Fish species can usually be identified based on visual observation and human experiences. False appreciation can cause food poisoning. The proposed system aims to efficiently and effectively identify edible fish from poiso...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
University of Information Technology and Communications
2023-12-01
|
| Series: | Iraqi Journal for Computers and Informatics |
| Subjects: | |
| Online Access: | https://ijci.uoitc.edu.iq/index.php/ijci/article/view/455 |
| _version_ | 1797371494057115648 |
|---|---|
| author | Israa Mohammed Hassoon Shaymaa Akram Hantoosh |
| author_facet | Israa Mohammed Hassoon Shaymaa Akram Hantoosh |
| author_sort | Israa Mohammed Hassoon |
| collection | DOAJ |
| description | Automated fish identification system has a beneficial role in various fields. Fish species can usually be identified based on visual observation and human experiences. False appreciation can cause food poisoning. The proposed system aims to efficiently and effectively identify edible fish from poisonous ones based on three machine learning (ML) techniques. A total of 300 fish images are used, collected from 20 species with differences in shapes, sizes, and colors. Hybrid features were extracted and then fed to three types of ML techniques: k-nearest neighbor (K-NN), support vector machine (SVM), and neural networks (NN). The 300 fish images are divided into two: 70% for training and 30% for testing. The accuracy rates for the presented system were 91.1%, 92.2%, and 94.4% for KNN, SVM, and NNs, respectively. The proposed system is evaluated using four terms: precision, sensitivity, F1-score, and accuracy. Results show that the proposed approach achieved higher accuracy compared with other recent pertinent studies. |
| first_indexed | 2024-03-08T18:21:03Z |
| format | Article |
| id | doaj.art-70366bf0861e4032a54bab5d51aca95b |
| institution | Directory Open Access Journal |
| issn | 2313-190X 2520-4912 |
| language | Arabic |
| last_indexed | 2024-03-08T18:21:03Z |
| publishDate | 2023-12-01 |
| publisher | University of Information Technology and Communications |
| record_format | Article |
| series | Iraqi Journal for Computers and Informatics |
| spelling | doaj.art-70366bf0861e4032a54bab5d51aca95b2023-12-30T22:09:18ZaraUniversity of Information Technology and CommunicationsIraqi Journal for Computers and Informatics2313-190X2520-49122023-12-014926272418EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNINGIsraa Mohammed Hassoon0Shaymaa Akram Hantoosh1University of MustansiriyahMiddle Technical UniversityAutomated fish identification system has a beneficial role in various fields. Fish species can usually be identified based on visual observation and human experiences. False appreciation can cause food poisoning. The proposed system aims to efficiently and effectively identify edible fish from poisonous ones based on three machine learning (ML) techniques. A total of 300 fish images are used, collected from 20 species with differences in shapes, sizes, and colors. Hybrid features were extracted and then fed to three types of ML techniques: k-nearest neighbor (K-NN), support vector machine (SVM), and neural networks (NN). The 300 fish images are divided into two: 70% for training and 30% for testing. The accuracy rates for the presented system were 91.1%, 92.2%, and 94.4% for KNN, SVM, and NNs, respectively. The proposed system is evaluated using four terms: precision, sensitivity, F1-score, and accuracy. Results show that the proposed approach achieved higher accuracy compared with other recent pertinent studies.https://ijci.uoitc.edu.iq/index.php/ijci/article/view/455edible fishhigh order statistical featuresmachine learningpoisonous fishsecond order statistical features |
| spellingShingle | Israa Mohammed Hassoon Shaymaa Akram Hantoosh EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNING Iraqi Journal for Computers and Informatics edible fish high order statistical features machine learning poisonous fish second order statistical features |
| title | EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNING |
| title_full | EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNING |
| title_fullStr | EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNING |
| title_full_unstemmed | EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNING |
| title_short | EDIBLE FISH IDENTIFICATION BASED ON MACHINE LEARNING |
| title_sort | edible fish identification based on machine learning |
| topic | edible fish high order statistical features machine learning poisonous fish second order statistical features |
| url | https://ijci.uoitc.edu.iq/index.php/ijci/article/view/455 |
| work_keys_str_mv | AT israamohammedhassoon ediblefishidentificationbasedonmachinelearning AT shaymaaakramhantoosh ediblefishidentificationbasedonmachinelearning |