|Krebs, Nadege - TEXAS TECH UNIVERSITY|
|Mcglone, John - TEXAS TECH UNIVERSITY|
Submitted to: American Society of Animal Science Southern Section Meeting
Publication Type: Abstract Only
Publication Acceptance Date: October 31, 2005
Publication Date: July 9, 2006
Citation: Dailey, J.W., Krebs, N., Carroll, J.A., McGlone, J., 2006. Validation of an automated tracking system to quantify overall activity and maintenance behaviors of individually housed nursery pigs [abstract]. Journal of Animal Science. 84:27(Suppl. 2). Abstract #82. Technical Abstract: Commercial automated tracking systems quantify animal behavior by assigning an X,Y coordinate for an animal's location at a given time. The objective of this study was to compare a human observer using the Observer 5.0 (OBS) to an automated tracking system (AUT), Ethovision, using the 'grey scaling' tracking method. Nursery pigs (n = 19) were individually housed in metabolism crates (1.55 m x 0.66 m). The pigs were exposed to a 12 h photo period and were fed ad libitum. The pigs were recorded continuously for 12 h with black and white cameras. The video was then scored for a 3 h period for the following mutually exclusive behaviors: 'in the feeder zone', 'standing/moving', 'in the defecation zone', 'in the drinking zone', and 'inactive'. The behaviors were first analyzed as 'inactive' (equivalent to 'inactive' in the OBS dataset) versus 'active' (all other behaviors). Zones were then created within the AUT dataset that matched those in the OBS dataset. The variables of the software were set as 'averaging 99 samples' and 'movement 27.94 cm/s'. Results are presented in Table 1. P-values >0.05 were considered not significant. Results (reported as % of observation period) indicate that overall activity and 'in the feeder zone' are the only behaviors which were accurately scored by the AUT. Future studies will evaluate if a colored tracking system will improve the results since a more specific coordinate location would be plotted for every data point.