Article Per Year (5 Year)
p-Index From 2019 - 2024
0.947
P-Index
This Author published in this journals
All Journal JUSIM (Jurnal Sistem Informasi Musirawas) RESOLUSI : REKAYASA TEKNIK INFORMATIKA DAN INFORMASI KLIK: Kajian Ilmiah Informatika dan Komputer BEES: Bulletin of Electrical and Electronics Engineering NUSANTARA: Jurnal Pengabdian Kepada Masyarakat
Rizki, Fido
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : KLIK: Kajian Ilmiah Informatika dan Komputer

 1 
Klasifikasi Penyakit Pada Daun Tanaman Padi Berbasis YoloV5 (You Only Look Once) Aditia Putra Pranjaya; Rizki, Fido; Kurniawan, Rudi; Khairani Daulay, Nelly
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 6 (2024): Juni 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i6.1916

Abstract

The rise of disease attacks on plant leaves causes huge losses for farmers, especially rice farmers. Lack of knowledge in identifying the symptoms of disease in rice plants can cause farmers to have difficulty in dealing with diseases that attack their rice plants, causing errors in handling diseases in rice plants that result in crop failure. When looking at the facts that occur today, it is very necessary to have a technology that can be used to recognise diseases in rice plants, so that it can help rice farmers in recognising a symptom of a disease that attacks their rice plants. With the application of computer vision using the YOLOv5 algorithm, we can create an introduction system related to diseases in rice plants based on the type of disease. In the process of applying the YOLOv5 algorithm, we will collect as many as 1500 images of 2 types of diseases and 1 type of normal rice leaves and each class we collect 500 images, and divide the data into 3 parts, the percentage of which is 70% for train data, 20% for valid data and 10% for test data and this process we do in Roboflow for image labelling and dataset creation. We will process the dataset from roboflow using the YOLOv5 algorithm. Based on the model evaluation results, the highest value of mAP 95%, precision 88%, recall 100% is obtained. The last stage is testing the system in real-time with a webcam and producing a test accuracy value in the Narrow Brown Spot class of 93%, in the Leaf Blight class of 81%, and Normal Rice Leaves 91%.
Co-Authors Aditia Putra Pranjaya AYU LESTARI Elmayati, Elmayati Indra Gunawan Khairani Daulay, Nelly Ninditama, Ilsa Palingga Nopalia Nopalia, Nopalia Rudi Kurniawan Rusdiyanto Rusdiyanto, Rusdiyanto Wulandari, Cindi