Year: 2024
Type: article
Abstract: This study focuses on training and testing various convolutional neural network (CNN) models, including Basic CNN, AlexNet, VGG16, and EfficientNet B0, for efficient plant disease detection. Each model was evaluated using the New Plant Diseases Dataset from Kaggle, covering a variety of plant species and diseases, to analyze performance, accuracy, and efficiency. The trained models were then integrated into a Marathi language chatbot to enable real-time disease identification and provide agricultural guidance. This research offers insights into the strengths and limitations of different models for precision agriculture, particularly in applications that support regional languages to promote accessible, sustainable farming practices. Key Words: Precision Agriculture, Embedded Systems, IoT, Deep Learning, Model Comparison, Real-time Detection, Disease Classification, NLP, Chatbot Integration, Marathi Chatbot.
DOI: 10.55041/ijsrem40360
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: bronze
OpenAlex ID: W4406001701