Redefining Agricultural Disease Management using AI and ML

Precision agriculture is a fast growing field that may contemporary issues surrounding agricultural sustainability are increasingly being addressed through innovative technologies. Machine learning, a cutting-edge tool that enhances precision agriculture, enables sophisticated methods for detecting...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 International Conference on Intelligent Computing and Control Systems (ICICCS) S. 720 - 725
Hauptverfasser: B, Venkata Srinivasulu, Dixith, K.Sai, Shivaram, Keerthi, Reddy, Ch.Karthik
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 19.03.2025
Schlagworte:
Advanced detection methods
Agricultural technology
Bounding box-based studies
Cameras
Classification algorithms
Computational efficiency
Computational study
Datasets for plant diseases
Deep learning
Image classification
Machine learning
Machine learning algorithms
MobileNetv2
Object detection algorithms
Object recognition
Plant disease classification
Plant disease detection
Plant diseases
PlantDoc dataset
Precision agriculture
Real-time systems
ResNet50
Sustainability
Sustainable development
Video-based studies
YOLOv5
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Precision agriculture is a fast growing field that may contemporary issues surrounding agricultural sustainability are increasingly being addressed through innovative technologies. Machine learning, a cutting-edge tool that enhances precision agriculture, enables sophisticated methods for detecting and classifying plant diseases. This paper offers a comprehensive review of how ML and DL techniques are applied in precision agriculture, focusing on disease identification and categorization. A novel classification framework is introduced, organizing relevant studies into distinct categories-Method-wise Classification Based Approaches. First, we categorize the studies method wise into classification (e.,g, image, and video-based studies) or object detection (e. g., bounding box-based studies) algorithms. Moreover, we provide existing archives for the classification and tracking of plant infections. By presenting a systematic framework that groups machine learning techniques according to their methodology, this study seeks to close the gap between the current plant disease classification techniques. We offer a comparative study to identify the best methods for disease identification by assessing the effectiveness of cutting-edge classification and object recognition algorithms on the PlantDoc dataset. In addition to streamlining precision agriculture research, the suggested architecture provides a basis for creating plant disease detection models that are more precise and scalable.
DOI:10.1109/ICICCS65191.2025.10984904