Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
Huda, Maasyaril Kirom Mi’Rojul
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management

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

Found 1 Documents
Search

 1 
Klasifikasi Ras Kelinci Menggunakan Convolutional Neural Network (CNN) untuk Optimasi Sistem Identifikasi Visual Huda, Maasyaril Kirom Mi’Rojul; Witanti, Arita
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6627

Abstract

Rabbits are mammals that come in many varieties with unique and diverse physical characteristics. Differentiating various types of rabbits, especially those with physical similarities and color patterns, is a challenge for some people because of their similar visual appearance. The purpose of this research is to develop a Convolutional Neural Network (CNN)-based rabbit breed classification system using MobileNetV3 architecture. A dataset of 1,500 images of three rabbit breeds (bligon, hyla, and new zealand white) was processed through resizing, augmentation, and normalization to improve data quality. The model was trained using Adam's optimizer with 97% accuracy on the validation data and 90% on the external dataset, showing good generalization ability. These results confirm the effectiveness of CNNs over manual methods in visual pattern recognition, while overcoming time constraints and human error. However, limitations in dataset variations, such as lighting and image capture angle, affect the generalization of the model. This research not only supports the efficiency of livestock management but also shows the great potential of AI application in Indonesia's livestock sector. Development of more diverse datasets and exploration of other model architectures are recommended for future performance improvements.
Co-Authors Arita Witanti