Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal MULTINETICS
Farid Restu Pujianto
Universitas Negeri Jakarta
Computer Science & IT

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

Found 1 Documents
Search

 1 
Deteksi Penyakit Pada Daun Padi Berbasis Pengolahan Citra Menggunakan Metode Convolutional Neural Network (CNN) Syenira Sheila; Irma Permata Sari; Adrie Bagas Saputra; Muhammad Kharil Anwar; Farid Restu Pujianto
MULTINETICS Vol. 9 No. 1 (2023): MULTINETICS Mei (2023)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v9i1.5255

Abstract

Abstract - Rice, produced by rice plants, is a staple food for the people of Asia, especially Indonesia. The amount of rice consumption is increasing along with the increase in population. Therefore, it is essential to keep rice production stable so that demand can be fulfilled. Leaf disease of rice plants is the biggest cause of crop failure which can lead to production instability. This study aims to detect disease in rice plant leaves based on their type using the Convolutional Neural Network (CNN) with the VGG16 architecture base model. In this study, a dataset of rice plant leaf images was collected using the secondary data collection method. The dataset was obtained from the Kaggle dataset repository in .csv format published by Vbookshelf. The image dataset consists of 120 data which is divided into 3 classes based on the type of rice leaf disease namely bacterial leaf bright, brown spot, and leaf smut with each class consisting of 40 image data. In this study, the resizing process was carried out on image data with a size of 224x224 pixels and image data augmentation. The training and testing results in this study showed that the training accuracy value reached 0.9861 and the validation accuracy value reached 1.0. By using the accuracy value in the Confusion Matrix which is equal to 100%, it is obtained that the results of applying the Convolutional Neural Network (CNN) have perfect accuracy.
Co-Authors Adrie Bagas Saputra Irma Permata Sari Muhammad Kharil Anwar Syenira Sheila