Skip to main content
ARS Home » Plains Area » Clay Center, Nebraska » U.S. Meat Animal Research Center » Nutrition, Growth and Physiology » Research » Publications at this Location » Publication #354527
Research Project: Improve Nutrient Management and Efficiency of Beef Cattle and Swine

Location: Nutrition, Growth and Physiology

Title: Development and validation of a low-frequency RFID system for monitoring grow-finish pig feeding and drinking behavior

Author
item Brown-Brandl, Tami
item ADRION, FELIX - University Of Hohenheim
item EIGENBERG, ROGER - Retired ARS Employee
item GALLMANN, EVA - University Of Hohenheim

Submitted to: Meeting Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 7/13/2018
Publication Date: 8/13/2018
Citation: Brown-Brandl, T.M., Adrion, F., Eigenberg, R.A., Gallmann, E. 2018. Development and validation of a low-frequency RFID system for monitoring grow-finish pig feeding and drinking behavior. Proceedings of the 10th International Livestock and Environment Symposium (ILES), September 25-27, 2018, Omaha, NE. Paper No. ILES 18-041. https://doi.org/10.13031/iles.18-041.
DOI: https://doi.org/10.13031/iles.18-041

Interpretive Summary:

Technical Abstract: Feeding and drinking behavior contain valuable information that can be used for various needs including pen design, livestock management, identification of sick animals, and determination of genetic differences. The objective of this paper is to document the development and validation of a new system to record feeding and drinking behavior of grow-finish pigs. The system was designed using low frequency RFID readers, 4- and 8-channel multiplexers, custom-made antennas, and microcomputers. The output of the RFID readers was collected by a microcomputer. The RFID system summarized all readings in a 10-second interval. Validation of the system with video observations was carried out with 10 focus pigs of the 40 pigs in 2 of the 6 pens. Video data was collected and labelled manually for a 12-h period. In average, the accuracy was between 96.6 % and 98.6 % at the feeders and 99.0 % for each of the focus animals at the drinkers. Sensitivity was approximately 89 % and precision approximately 84 % at the feeders. At the drinkers, these measures were only at 52.3 % and 54.0 %, respectively. The coefficients of determination (R²) of the linear regressions between video data and RFID data were similar for the drinker and the feeders. The highest R² was achieved for the regression of DUR between video and RFID events (between 0.95 and 0.99). These results indicate a very accurate detection of the pigs’ individual feeder visits as well as the total duration of the feeder and drinker visits by the RFID system.