Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Performance Comparison of Convolutional Neural Network and MobileNetV2 for Chili Diseases Classification

Rektorat UDINUS 2023 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2023
Goals
Record
af2a8f53-2d28-4b7d-97d5-575b3660d100
Published
2026-10-30

Universitas Dian Nuswantoro conducted research on the classification of chili plant diseases by comparing the performance of a Convolutional Neural Network algorithm with a pre-trained MobileNetV2-based model. The activity involved Ramadhani, Achmad Naila Muna; Saraswati, Galuh Wilujeng; Agung, Rama Tri; and Santoso, Heru Agus as research participants.

The research addressed the importance of chili as an agricultural commodity in Indonesia and its role in the nation's economic growth. The source states that demand from households and industries reaches up to 61%. This demand means that monitoring efforts need to be intensified, particularly for chili plant diseases that can greatly impact yields. If diseases are not promptly addressed, they can lead to decreased production levels, which can negatively affect the economy.

The activity examined automatic monitoring using image processing. The source identifies Chili leaf yellowing disease, Chili leaf curling disease, cercospora leaf spots, and Magnesium Deficiency among common chili plant diseases. Symptoms can be observed through the shape and color of the leaves. The research compared a CNN algorithm and a pre-trained MobileNetV2-based model for disease classification, using a confusion matrix to assess performance.

The study reported that the MobileNetV2 model, trained with a learning rate of 0.001, produced a more optimal model. It achieved an accuracy of 90%. Based on the calculation of the confusion matrix, the average percentage values for recall, precision, and F1 score were 92%. These findings highlight the potential of image processing and pre-trained models to support efforts to monitor plant diseases and improve chili production. The activity frames institutional research around agricultural monitoring through image-based classification.

Reference https://www.scopus.com/pages/publications/105003064163?origin=resultslist