Abstract #M132

# M132
An evaluation of precision dairy farming technologies monitoring rumination, feeding, and lying behaviors.
Matthew R. Borchers*1, I-Ching Tsai1, Barbara A. Wadsworth1, Jeffrey M. Bewley1, 1University of Kentucky, Lexington, KY.

The objective of this study was to evaluate commercially available precision dairy farming technologies against direct visual observations for feeding, rumination, and lying behaviors. Primiparous (n = 24) and multiparous (n = 24) lactating Holstein dairy cattle (mean ± SD; 223.4 ± 117.8 d in milk, producing 29.2 ± 8.2 kg milk/d) were fitted with 6 triaxial accelerometer technologies to evaluate cow behavior. Technologies recording feeding behavior were the CowManager SensOor (Agis, Harmelen, Netherlands) and the Track a Cow (ENGS, Israel). Technologies recording rumination behavior were the CowManager SensOor and the Smartbow (MKW electronics GmbH, Jutogasse, Austria). Lying behavior was recorded by the AfiAct Pedometer Plus (Afimilk, Kibbutz Afikim, Israel), HOBO Data Logger (HOBO Pendant G Acceleration Data Logger, Onset Computer Corporation, Pocasset, MA), CowAlert IceQube (IceRobotics Ltd., Edinburgh, UK), and Track a Cow. Over 8 d in October 2014, 6 cows per day were visually observed for feeding, rumination, and lying behavior for 2 h after morning and evening milking. The CORR procedure of SAS Version 9.3 (SAS Institute Inc., Cary, NC) was used to evaluate agreement between visual observations and technology-recorded behaviors. Visually recorded feeding behavior was strongly correlated with CowManager SensOor (r = 0.97; P = 0.03) and Track a Cow (r = 0.91; P = 0.09). Between the CowManager SensOor and Track a Cow, a strong correlation (r = 0.91; P = 0.09) was found. Visually recorded rumination was strongly correlated with the Smartbow (r = 0.99; P < 0.01) and CowManager SensOor (r = 0.96; P < 0.01). Between the Smartbow and CowManager SensOor, a strong correlation (r = 0.94; P = 0.06) was found. Visually recorded lying behavior was highly correlated with the AfiAct Pedometer Plus (r = 0.97; P < 0.01), HOBO Data Loggers (r = 0.98; P < 0.01), CowAlert IceQube (r = 0.99; P < 0.01), and Track a Cow (r = 0.99, P < 0.01). Results indicate these precision dairy farming technologies to be accurate dairy cattle behavioral monitors.

Key Words: precision dairy farming technologies, dairy cow behavioral monitoring, accuracy evaluation