<![CDATA[Animal weighing is an important aspect of livestock farming, as it plays a role in feed determination, growth monitoring, and economic evaluation. However, accuracy is often compromised by animal movement, which causes fluctuations in sensor data and unstable readings, making it difficult to determine the actual weight. To address this, this study proposes an IoT-based animal weighing system equipped with a Kalman Filter algorithm to reduce noise and improve measurement stability. The system utilizes four 200 kg load cells, connected via HX711 and controlled by an ESP32 microcontroller, which is supported by an RFID module for automatic animal identification, an RTC for time logging, and Firebase as a cloud storage platform with real-time visualization capabilities through Node-RED. Experimental for moving object weighing results show that the Kalman Filter reduces measurement errors to less than 2% and maintains the coefficient of variation below 2%, demonstrating high precision and stability. Therefore, this system is proven effective for automatic, accurate, and remote-accessible animal weight monitoring, with strong potential for implementation in modern livestock industries.]]>
Copyrights © 2026
