Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI
Joseph Alberto
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
Klasifikasi Jenis Burung Menggunakan Metode CNN dan Arsitektur ResNet-50 Joseph Alberto; Dedy Hermanto
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 10 No 3 (2023): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v10i3.4558

Abstract

Birds are members of a group of vertebrate animals that have feathers and wings. There is so much diversity of birds in Indonesia that it is difficult to distinguish certain types of birds. However, with the development of technology today, we can now distinguish between types of birds and technology. Classification of birds can be done to distinguish the various types of birds that exist in Indonesia so that to distinguish birds that at first glance look similar will be more effective with this classification. In this study, bird species were classified using the 400 Bird Species – Classification dataset which was filtered only for birds in Indonesia and obtained a dataset of 63 bird species with a total of 9.445 iamges consisting of 8.185 training images and 1.260 test images. The classification of this bird species was carried out using the CNN method, the model was formed using the ResNet-50 architecture. Furthermore, the training process is carried out with ADAM and SGD optimizers to see the maximum results, and obtained an accuracy value of 98% with the SGD optimizer with 10 epoch
Co-Authors Dedy Hermanto