Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Tech-E
Al-Fatih, Gilang Fajar
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
Optimasi Hyperparameter Convolutional Neural Network untuk Klasifikasi Jenis Penyakit Daun Jagung menggunakan CLAHE Al-Fatih, Gilang Fajar; Pulung Nurtantio Andono; M. Arief Soeleman
Tech-E Vol. 9 No. 1 (2025): The Tech-E Journal Vol. 9 No. 1 publishes research papers in such informatics:
Publisher : Fakultas Sains dan Teknologi-Universitas Buddhi Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31253/te.v9i1.3541

Abstract

Corn plays an important role as one of the main food sources in Indonesia and around the world. Diseases in corn plants are often visible through their leaves. However, problems arise when farmers have difficulty detecting diseases that attack corn plants, making it difficult to take appropriate action to control them. Diseases in corn plants can lead to reduced photosynthesis, disrupt agricultural productivity, and cause financial losses for farmers. Therefore, a digital approach that can detect various types of diseases in corn plants is highly needed. In recent years, the emergence of machine learning algorithms has provided support systems for classifying corn leaf diseases. This research aims to classify types of corn leaf diseases using the Optimization of Convolutional Neural Network (CNN) Method for Classifying Types of Corn Leaf Diseases Using Contrast Limited Adaptive Histogram Equalization (CLAHE). The research stages include data collection, image enhancement with CLAHE, data augmentation, data preprocessing, classification, and evaluation. The Optimization of the CNN Method for Classifying Types of Corn Leaf Diseases Using CLAHE resulted in an accuracy of 94%, indicating that this experiment is capable of classifying corn leaf diseases effectively.
Co-Authors M. Arief Soeleman Pulung Nurtantio Andono