Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI
Juan, Micova
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
KLASIFIKASI PENYAKIT DAUN SINGKONG MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR RESNET-18 Juan, Micova
JATISI Vol 13 No 1 (2026): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v13i1.14000

Abstract

Food crops are plants that produce carbohydrates and proteins, making them a primary source of staple food for the majority of Indonesia's population. Cassava is classified as a food crop because it contains the carbohydrates and proteins needed by the human body. According to data from [1], cassava contributes 28.21% to food consumption in Indonesia. Based on interviews conducted, classifying diseases in cassava leaves is an important step to prevent the spread of infections. However, visual observation-based classification is considered less effective, as it requires expert knowledge, takes a significant amount of time, and is difficult to implement on a large scale. From the results of hyperparameter tuning using the CNN ResNet-18 method, the best model was achieved with 20 epochs, a batch size of 32, and a learning rate of 0.001. This configuration yielded a precision of 94.54%, recall of 94.40%, F1-score of 94.33%, and an accuracy of 94.40%. Additionally, based on the questionnaire results, the average scores for Usefulness were 86.5%, Satisfaction 84.6%, and Ease of Use 88.5%.
Co-Authors