Cloud Data-Driven Intelligent Monitoring System for Interactive Smart Farming

Area of Science:

• Agricultural Technology
• Data Science
• Cloud Computing

Background:

• Smart farms generate vast amounts of IoT data, often stored locally and unused for intelligent monitoring.
• Lack of data utilization hinders transparency, accountability, and farmer motivation to invest in advanced systems.
• Existing systems often fail to provide actionable insights from collected farm data.

Purpose of the Study:

• To propose a data-driven intelligent monitoring system in a cloud environment for smart farms.
• To enable comprehensive data extraction, preprocessing, storage, feature engineering, modeling, and visualization.
• To provide farmers with accessible tools for monitoring farm progress and improving decision-making.

Main Methods:

• Designed a cloud-based architecture for seamless IoT data integration and processing.
• Implemented machine learning models for data analysis and periodic updates.
• Developed an interactive, dynamic dashboard for real-time data visualization and trend analysis.

Main Results:

• The system effectively streams data from IoT devices to live reports and interactive dashboards.
• Machine learning models provide insights into farm parameters, trends, and deviations.
• Performance and durability tests confirmed the system's reliability and efficiency.

Conclusions:

• The proposed system acts as a technological bridge, making farm monitoring easy, affordable, and understandable for farmers.
• It enhances farmers' ability to examine, organize, and represent farm data for better management.
• Facilitates easy integration with existing IoT systems, promoting technological development in agriculture.