FL-ToLeD: An Improved Lightweight Attention Convolutional Neural Network Model for Tomato Leaf Diseases Classification for Low-End Devices

Project Code :TEMBMA3655

Objective

This study introduces FL-ToLeD, a lightweight attention convolutional neural network model designed for efficient classification of tomato leaf diseases, optimized for use on low-end devices.

Abstract

This project presents FL-ToLeD, a lightweight attention-based convolutional neural network (CNN) model designed for tomato leaf disease classification using images captured by a camera module. The system is integrated with soil moisture and DHT11 temperature/humidity sensors to monitor environmental conditions, providing valuable data to optimize irrigation and climate control for tomato plants. When a disease is detected, the system calculates the required chemical treatment formula and sends an SMS alert with the disease details and treatment instructions via a GSM module to farmers or agricultural experts. The lightweight model, optimized for low-end devices like Raspberry Pi or microcontrollers, ensures efficient processing with low computational requirements, making it ideal for deployment in remote areas with limited infrastructure. By combining image classification, environmental monitoring, and real-time SMS alerts, FL-ToLeD provides an integrated solution for managing tomato crop health, enabling early disease detection, better decision-making, and reducing crop losses.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Block Diagram

Specifications

- Raspberry Pi
- DHT11 sensor
- LCD
- Soil moisture sensor
- Camera
- GSM

Learning Outcomes

Disease Detection: Learn to use CNN for classifying tomato leaf diseases.
Model Optimization: Optimize deep learning models for low-end devices like Raspberry Pi.
Sensor Integration: Integrate soil moisture and temperature sensors for crop management.
SMS Alerts: Implement GSM systems for sending real-time alerts via SMS.
Image Processing: Extract features from images for improved disease classification.
Sustainable Farming: Understand how technology supports sustainable farming practices.
AI in Agriculture: Apply AI to solve real-world agricultural challenges.