Analysis of feeding behavior of group housed growing–finishing pigs

Abstract

Feeding behavior and time spent eating contains valuable information that can be used for managing livestock, identifying sick animals, and determining genetic differences within a herd. Individual animal feeding behavior, in a commercial-sized pen, was recorded using radio-frequency identification (RFID) technology and a series of multiplexers. Data were collected on 960 pigs (mixed barrows, 406 and gilts, 600) over 4 grow-out periods. The animals entered the facility at 24.6 ± 5.4 kg (mean ± standard deviation) at approximately 65 days of age and exited the facility at 101.4 ± 13.8 kg (between 116 and 133 days later). Time spent at the feeder was analyzed for the effects of days on feed, sex, weight gain, and health effects. The amount of time spent at the feeder averaged 68.8 min day À1 pig À1 over the grow-out period, and increased from the day the pigs enter the facility (24.0 ± 1.6 min day À1 pig À1 ; mean ± standard error) until plateauing at approximately 40 days later (76.7 ± 2.4 min day À1 pig À1 ; age $ 105 days). After the plateau, barrows spent 13.6 more minutes per day at the feeder than gilts. Pigs classified as 'high gaining' (79.2 ± 5.1 min day À1 pig À1) spent more time at the feeder than pigs classified as either 'normal' (72.6 ± 2.6 min day À1 pig À1) or 'low gaining' (67.6 ± 5.3 min day À1 pig À1). This initial manuscript demonstrates the potential of utilizing feeding behavior or time spent eating as a method of managing animals.

Validation of a High Frequency Radio Frequency Identification (HF RFID) system for registering feeding patterns of growing-finishing pigs

“…High variability in the feeding patterns of individual, healthy pigs was found (Table 1) and is in agreement with the observations of other researchers (Brown-Brandl et al, 2013;Hessel and Van den Weghe, 2011).…”

“…They also reported that in 64 % of the cases, the piglets were identified with a slight time delay between RFID and video. Brown-Brandl et al (2013) developed and validated an LF RFID system for monitoring feeding behaviour of cattle and swine and mention that the cattle system was in agreement with the video 98.3 % of the time, and the swine system was in agreement 98.7 % of the time. This agreement corresponds to the percentage of 20 s (swine system) or 30 s (cattle system) intervals where video and RFID system were identical (either both feeding or both not feeding).…”

“…This makes that automatic registration of pigs' feeding patterns could support pig farmers in their daily management routine (Wathes et al, 2008). As feeding patterns can differ amongst pigs in the same pen, even in homogenous groups, automatic registration shows the most potential when applied to individual pigs (Brown-Brandl et al, 2013;Hessel and Van den Weghe, 2011).…”

“…Brown-Brandl et al (2013) solved this problem by installing one LF antenna per feeding access point in an industrial rectangular feeder and achieved good results in determining individual animal feeding patterns. For many other types of commercial feeders where the feeding points are not physically separated it is, however, not possible to install one antenna per feeding access point.…”

Automatic recognition of lactating sow behaviors through depth image processing

“…They contain important information that can enable producers to better manage livestock (Brown-Brandl et al, 2013). For instance, research has shown that changes in feeding behavior can occur in response to thermal conditions of growing-finishing swine (Nienaber and Hahn, 2000), health status of sow and feedlot cattle (Cornou et al, 2008;Griffin, 2001), and diet of dairy goats (Adijaoude et al, 2000).…”