Development of an IoT System for Intelligent Monitoring of Tomato Harvesting and Postharvest Processes Using Data-Driven Decision Making (DDDM)

This study presents the development and functional validation of an Internet of Things (IoT) architecture for data-driven decision-making (DDDM) in the intelligent monitoring of tomato harvest and postharvest processes. The architecture integrates data acquisition, processing, storage, and visualization to transform contextualized measurements into operational states, priority levels, and actionable insights. The methodology comprised a systematic literature review, the design and implementation of the IoT platform, and a controlled functional pilot. A controlled scenario generator produced synthetic measurements representing normal operation, warning, critical, and communication-loss conditions. Eight predefined scenarios were executed twenty times each, resulting in 160 executions. In each execution, the operational state, priority level, and actionable insight generated by the architecture were compared with the expected outputs established by the configured decision rules. The architecture achieved 100% total agreement for the three evaluated outputs across all 160 executions, demonstrating functional consistency within the controlled scenarios. These results are limited to the implemented interpretation process and do not establish agronomic validity, sensor accuracy, or performance under real operating conditions. Future work will evaluate the architecture in real cultivation and postharvest environments using calibrated sensors and direct process measurements, allowing the operational ranges to be verified and adjusted according to context-specific agronomic criteria.