Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Ilmu dan Teknologi Kelautan Tropis
Lukman
Program Studi Sistem Informasi Kelautan, Kampus Daerah Serang, Universitas Pendidikan Indonesia, Kota Serang, 42116, Indonesia
Biochemistry, Genetics & Molecular Biology Decision Sciences, Operations Research & Management Library & Information Science

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
KLASIFIKASI TIGA GENUS IKAN KARANG MENGGUNAKAN CONVOLUTION NEURAL NETWORK Ishak Ariawan; Willdan Aprizal Arifin; Ayang Armelita Rosalia; Lukman; Nabila Tufailah
Jurnal Ilmu dan Teknologi Kelautan Tropis Vol. 14 No. 2 (2022): Jurnal Ilmu dan Teknologi Kelautan Tropis
Publisher : Department of Marine Science and Technology, Faculty of Fisheries and Marine Science, IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jitkt.v14i2.33633

Abstract

Reef fish are one of the essential organisms in studying coral reef ecosystems, and it is necessary to carry out an identification process to understand the pattern, structure and distribution of reef fish diversity. In addition, reef fish have a vast number and are almost similar to each other. Therefore, to speed up the process of fish identification can be done computerized. One of the automated techniques that can be done is digital image processing. This study aims to classify the image of the genus Fish (Epinephelus spp., Halichoeres spp., and Lutjanus spp.) as economically significant. Image data was obtained from the site https://www.kaggle.com/. The image classification method used is Convolutional Neural Network (CNN) which consists of two stages. The first stage is training with the backpropagation method, and the second stage is image classification using feedforward—the results of the combination of the two methods obtained an accuracy of 85,31%. In addition, the model built is quite good because the average value between precision and sensitivity is not too significant; precision is 89,92%, and sensitivity is 86,49%. Based on the analysis and evaluation that has been done, it can be concluded that the CNN classification method can be appropriately used in classifying fish images by genus.
Co-Authors Ayang Armelita Ishak Ariawan Nabila Tufailah Willdan Aprizal Arifin