Multi-Stage Data Processing for Enhancing Korean Cattle (Hanwoo) Weight Estimations by Automated Weighing Systems

Weight is the most basic and important indicator in cattle management, and automation of its measurement serves as a fundamental step toward modern smart livestock farming. Automated weighing systems (AWS) capable of continuously measuring cattle weight, even during movement, have been explored as key monitoring components in smart livestock farming. However, owing to the high measurement variability caused by environmental factors, the accuracy of AWSs has been questioned. These factors include real-time fluctuations due to animal activities (e.g., feeding and locomotion), as well as measurement errors caused by residual feed or excreta within the AWS. Therefore, this study aimed to develop an algorithm to enhance the reliability of steer weight measurements using an AWS, ensuring close alignment with actual cattle body weight. Accordingly, daily weight data from 36 Hanwoo steers were processed using a three-stage approach consisting of outlier detection and removal, weight estimation, and post-processing for weight adjustment. The best-performing algorithm that combined Tukey's fences for outlier detection, mean-based estimation, and post-processing based on daily weight gain recommended by the National Institute of Animal Science achieved a root mean square error of 12.35 kg, along with an error margin of less than 10% for individual steers. Overall, the study concluded that the AWS measured steer weight with high reliability through the developed algorithm, thereby contributing to data-driven intelligent precision feeding.