Abstract:
Manual latex weighing and attendance recording in the rubber plantation industry often lead to inconsistencies, inefficiencies, and frequent human errors. These outdated methods negatively impact data quality, decision-making, and overall productivity, especially within large-scale plantation operations. To address these challenges, the development of a computerized and automated system has become essential, enabling streamlined weighing and attendance processes with minimal human involvement.
This study presents a Bluetooth-enabled mobile application, developed using Kotlin and Bluetooth Low Energy (BLE), designed to automate and enhance field operations. The application records employee attendance in real time, automates latex weighing, and calculates Dry Rubber Content (DRC) with improved accuracy. Additionally, a machine learning module powered by a Random Forest model is integrated to predict high-performing employees based on historical performance data. The user interface is designed to be intuitive and user friendly, ensuring smooth adoption by field workers. For secure and synchronized data management, Firebase is utilized as the backend service.
System evaluations indicate significant improvements across multiple areas, including data accuracy, device responsiveness, and user satisfaction. Feedback gathered through activity logging and user acceptability testing shows that the automated processes greatly reduce errors and manual workload. Machine learning predictions demonstrated high accuracy in identifying top-performing employees, while BLE connectivity proved stable and reliable throughout field operations.
Overall, this solution provides a modern, efficient, and scalable approach to rubber plantation management. By integrating automation, wireless communication, and predictive analytics, the system contributes to increased productivity and supports the digital transformation of the rubber industry.
