Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JUSTINDO (Jurnal Sistem dan Teknologi Informasi Indonesia)
Reza, Muammar Reza Pahlawan
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Engineering

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

Found 1 Documents
Search

 1 
Clinical Image Classification of Cattle Foot and Mouth Disease Based on Convolutional Neural Network Reza, Muammar Reza Pahlawan; Sahriani; Shabarul Mukjizat
JUSTINDO (Jurnal Sistem dan Teknologi Informasi Indonesia) Vol. 11 No. 1 (2026): JUSTINDO
Publisher : Universitas Muhammadiyah Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32528/justindo.v11i1.4737

Abstract

Foot-and-Mouth Disease (FMD) is a highly contagious viral outbreak affecting cattle and causes significant economic losses to the national livestock industry. The limited availability of veterinary experts in the field often leads to delayed diagnosis, which contributes to the rapid spread of the virus. This study aims to develop an intelligent computational model capable of automatically diagnosing clinical symptoms of FMD from digital images using a deep learning approach based on Convolutional Neural Networks (CNNs). The research methodology begins with the collection of a dataset consisting of images of cattle mouths and hooves, categorized into two classes: FMD-infected and healthy. The preprocessing stage involves image resizing and pixel normalization, followed by data augmentation techniques such as rotation and flipping to reduce overfitting. The model architecture is designed using a sequence of convolutional layers, pooling layers, and fully connected layers to automatically extract visual features related to lesion characteristics. Based on the experimental results, the proposed model achieves high classification performance, with a validation accuracy of 95%. The dataset used in this study consists of 1,000 image samples, with a data split ratio of 70% for training, 15% for validation, and 15% for testing. In addition to accuracy, the classification performance demonstrates a recall of 96%, F1-score of 94%, and precision of 91%.The findings of this study confirm that a computer vision–based approach can serve as a reliable tool for early diagnostic assistance, offering fast and accurate detection to support better decision-making in livestock health management.
Co-Authors Sahriani Shabarul Mukjizat