Aviv Yuniar Rahman
Indonesia is ranked first in the world in terms of bird species. One of the various kinds of birds in Indonesia is the starling because it has multiple types from almost every region. It is difficult for ordinary people to choose the kind of starling, so many of them are deceived for high profits. For this reason, this study uses the Artificial Neural Network method in the process of classifying starling images. It can be seen from the results that have been tested that texture features get an accuracy of 68% learning rate of 0.5, shape features 75% learning rate 0.3, and color features 100% learning rate of 0.5. Then for the second level, texture and shape features 82% learning rate of 0.2, textures and colors 100% learning rate of 0.9, and colors and shapes 100% learning rate of 0.8. The third level, namely the texture, shape, and color features with an accuracy of 100% learning rate of 0.7. In the results of the tests and evaluations that have been carried out, it can be said that at 1 feature level, the best accuracy value can be obtained according to the resulting learning rate. © 2021 ACM.
Universitas Widyagama Malang, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock