How vp-1234ms/greenintellect works
Project’s Major Components
• AI/ML Module: This includes the trained models (stored in the Models directory for crops and fruits) and the analysis notebooks (under Notebooks). These components are used for disease detection and prediction.
• Data Management: The Project_Data folder holds crop and fruit data alongside Excel datasets for results. This can be connected to the database layer.
• Web Application: The Web_Development folder holds code for the UI (Next.js/React components such as Posts.jsx, SensorGraph.jsx, etc.), API endpoints (e.g., Web_Development/api/route.js), backend logic (Flask detection/prediction modules), and configurations for both frontend and backend (various config files, package.json, etc.).
• Sensor & Hardware Integration: Described in the README (sensor data on air temperature, soil moisture, etc.) – though the sensors aren’t explicitly in the file tree, the referenced hardware integration should be documented.
• Business and Community Engagement: Business_Model and Project_Idea folders provide presentations and PDFs that outline the business strategy and the educational/community aspects of the project.
• External Services and Databases: The tech stack mentions PostgreSQL, MongoDB, and even IoT/MQTT for sensor integration. These backends will need representation.
Architectural Relationships and Interactions
• End users (farmers, researchers, etc.) interact via the frontend to upload plant images and view predictions.
• The Web UI sends image and sensor data to the backend API.
• The Flask modules receive these requests and invoke the corresponding AI model (TensorFlow) for disease detection.
• After processing, results are stored in the database (PostgreSQL/MongoDB) and returned to the client.
• Sensor data from IoT devices is also fed into the database and may be visualized on the web platform.
• The notebooks and ML pipelines allow continuous model improvement and retraining, integrating new data from the Project_Data folder.
• The system also interfaces with third-party APIs for community and educational content as described in the README.
Important Architectural Patterns/Design Principles
• Separation of Concerns: Clear division between user interface (frontend), application logic (backend), and AI model processing.
• Modular Design: Each component (image detection, sensor handling, data visualization) exists as separate, interactable modules – allowing for easier maintenance and scaling.
• Service-Oriented Architecture (SOA): The REST APIs (exposed in Web_Development/api) serve as communication channels between distinct services.
• Extensibility: Notebooks and Models directories indicate a design geared towards continual experimentation and improvement.