Scholarlink

In the field of agriculture, accurate disease categorization is crucial to maximizing productivity and preserving plant health. The goal of this study is to forecast coffee leaf illnesses by utilizing MobileNetV2, a deep learning model that is both lightweight and effective. With the increasing focus on precision agriculture, we aim to develop a robust and resource-efficient method for diagnosing and treating diseases affecting coffee leaves. MobileNetV2 is a great option for on-device deployment because of its effective design and small architecture, which enable real-time inference without compromising accuracy. Our complete validation and optimization process demonstrates the model’s sensitivity to the distinct features of coffee leaf diseases. For mobile device implementation, the proposed approach is a best choice because it overcomes shortages of resources and increases forecast accuracy. The results we find prove how MobileNetV2 can change the way diseases are predicted in coffee plants, giving farmers and other agricultural stakeholders quick, easy, and private-protecting solutions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integration of MobileNetV2 for Efficient Prediction of Coffee Leaf Disease in Precision Agriculture

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • S. Naganjaneyulu,
  • Amaraneni Geethika,
  • Bandila Tejaswini,
  • Palanki Shreyasi,
  • Raavi Giridhar Reddy,
  • Mallipam Tony Lakshmi Satya Praveena

摘要

In the field of agriculture, accurate disease categorization is crucial to maximizing productivity and preserving plant health. The goal of this study is to forecast coffee leaf illnesses by utilizing MobileNetV2, a deep learning model that is both lightweight and effective. With the increasing focus on precision agriculture, we aim to develop a robust and resource-efficient method for diagnosing and treating diseases affecting coffee leaves. MobileNetV2 is a great option for on-device deployment because of its effective design and small architecture, which enable real-time inference without compromising accuracy. Our complete validation and optimization process demonstrates the model’s sensitivity to the distinct features of coffee leaf diseases. For mobile device implementation, the proposed approach is a best choice because it overcomes shortages of resources and increases forecast accuracy. The results we find prove how MobileNetV2 can change the way diseases are predicted in coffee plants, giving farmers and other agricultural stakeholders quick, easy, and private-protecting solutions.