Work

AI-Driven Approach for Digital Agriculture: A Case Study on Coffee Leaf Disease

Year: 2025

Type: conference-paper

Abstract: This study presents an AI-driven approach to coffee leaf disease classification by integrating deep learning and computer vision. Using DenseNet, MobileNet, and ResNet with transfer learning and data augmentation, the system achieved high accuracy, with DenseNet consistently performing the best. The experimental results highlight the influence of learning rate and class distribution on model performance. Model conversion ensures efficient deployment and supports real-time diagnosis. The proposed solution bridges AI research and practical agriculture, enhancing disease management while paving the way for scalable adaptive precision farming.

DOI: 10.5753/wcama.2025.6606

Authors: Luiz Felipe de Castro Vilas Boas, Leonardo Gabriel Ferreira Rodrigues, Rafael Marinho e Silva, Danielli Araújo Lima, Larissa Ferreira Rodrigues Moreira

Institutions: Universidad Francisco de Vitoria, Universidade Federal de Uberlândia, Centro Universitário de Patos de Minas, Instituto Federal de Educação, Ciência e Tecnologia do Triângulo Mineiro

Language: English

Topic: Smart Agriculture and AI

Subfield: Plant Science

Field: Agricultural and Biological Sciences

Domain: Life Sciences

SDGs: Zero hunger, Industry, innovation and infrastructure

Open Access status: gold

Funders: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Fundação de Amparo à Pesquisa do Estado de Minas Gerais

Award: HABILITANDO A ENTREGA DE SERVIÇOS COGNITIVOS EM REDES B5G ATRAVÉS DE NET-AI-APPS