Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal INFORMATIKA
Fajri Pramana Putra
Universitas Pamulang
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Mechanical Engineering

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

Found 1 Documents
Search

 1 
KLASIFIKASI PENYAKIT DAUN PADI BERBASIS ANDROID MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) DAN TRANSFER LEARNING MOBILENETV3 Fajri Pramana Putra; Niki Ratama
Informatika: Jurnal Teknik Informatika dan Multimedia Vol. 6 No. 1 (2026): MEI : JURNAL INFORMATIKA DAN MULTIMEDIA
Publisher : LPPM Politeknik Pratama Kendal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/informatika.v6i1.1622

Abstract

Early identification of Rice leaf diseases remains a challenge in agricultural practices, as detection is commonly performed through manual visual observation that is time-consuming and prone to misclassification. Diseases such as blast, Bacterial Leaf Blight, tungro, and Brown Spot often exhibit similar visual characteristics, particularly at early stages. To address this problem, an Android-based application was developed to classify Rice leaf diseases using a Convolutional Neural Network (CNN) with a transfer learning approach based on the MobileNetV3 architecture. The model was trained using a labeled Rice leaf image Dataset obtained from Hugging Face, with preprocessing and data augmentation applied to improve generalization performance. The trained model was deployed through Hugging Face Space using an API-based architecture, allowing image classification to be performed without heavy computational requirements on mobile devices. Experimental results demonstrate that the proposed model achieved an accuracy of approximately 90% on the testing Dataset, exceeding the predefined minimum target accuracy of 85%, with precision and recall values above 80% across all disease classes based on confusion matrix evaluation. These results indicate that the MobileNetV3-based transfer learning approach provides reliable classification performance with good computational efficiency, making it suitable for mobile-based Rice leaf disease detection applications.
Co-Authors Niki Ratama