Automatic measurements of feeding behaviour of group-housed growing-finishing pigs can be used for research or on farms. Using these measurements, automatic detection of feeding related problems becomes possible, as changes in the feeding behaviour of a pig may indicate disease or welfare issues and can also be strongly related to productivity changes. In this paper, a high frequency (HF) Radio Frequency Identification (RFID) system was used to register feeding pigs at a commercial feed trough. The raw RFID registrations had to be translated into feeding visits, as there were irregular time gaps between the registrations that were inherent to the system for this application. Data of two experiments were used, one experiment with observations for six pigs during three days was used to find the best method for visit construction (E2), whilst the other experiment with observations for 20 pigs on one day was used as an independent validation data-set (E1). Three methods for visit construction were proposed: (1) visit criteria (a bout criterion and a minimum duration criterion), (2) a digital filter (using a well-defined time delay and a threshold for feeding) and (3) erosion and dilation operations from mathematical morphology. The best results were obtained using a bout criterion equal to 10 s for two tags per pig or 20 s for one tag per pig. Removal of short visits was found to be unnecessary. This optimal method is equal to a closing operation (a dilation followed by an erosion). For the RFID system with the optimal bout criterion, using two tags per pig, average sensitivity was 83 %, specificity 98 %, accuracy 97 % and precision was 75 % for E2. Application of the same bout criterion on the independent test set E1, resulted in an average sensitivity of 80 %, a specificity of 99 %, an accuracy of 98 % and a precision of 78 %. Performance tended to be lower when using one tag per pig. Regression analysis revealed that the observed feeding duration was well-correlated with RFID-based duration of visits (R² = 0.86 for two tags per pig, E1+E2). Other observed variables were harder to predict by the RFID system. From these results, it was concluded that feeding patterns can be observed accurately in an automatic way if the registrations from the RFID system are analysed with the selected bout criterion.
For sustainable pork production and maximum pig welfare, all health, welfare and productivity problems in the barn should be detected as early as possible. In this paper, an automated monitoring and warning system is proposed. Based on measurements of the feeding pattern, it is able to generate daily alerts for individual fattening pigs. Using historical data, the following types of warning systems were developed: (1) fixed limits that treat all pigs and all days equally; and (2) time-varying individual limits using the concept of Synergistic Control. These types of limits were constructed either for the number of registrations per pig or the average interval between feeding visits of a pig, leading to four warning systems in total. These warning systems were used to generate alerts during an online validation period. During an entire fattening period, all pigs were individually monitored to establish true alerts, false alerts and missed problems. The best performance was achieved for the Synergistic Control method on the number of registrations, with a sensitivity of 58.0 %, specificity of 98.7 %, accuracy of 96.7 % and precision of 71.1 %. Severe problems were detected on average within 1.3 days from the start of the problem. These are promising results that provide a solid basis for the development of a system for individual pigs but further improvements are warranted to make the system more practical.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.