Dunne, R and Henry, D and Rawnsley, R and Rahman, A, Behavior classification of dairy cows fitted with GPS collars, Lecture Notes in Computer Science, 10526 pp. 15-25. ISSN 0302-9743 (2017) [Refereed Article]
Precision management systems for livestock offer the potential to monitor and manage animals on an individual basis. A key component of these sensor based systems are the analytical models that automatically translate sensor data into different behavioral categories.
Here we consider the use of GPS data for modelling the behaviour of dairy cows. The performance of this approach is validated across a study involving 24 Holstein-Friesian dairy cows that were each fitted with a GPS unit on a neck collar. The behavior of the cows are classified into 4 general classes: grazing; moving from paddock to paddock; milking; and resting. Using simple rules derived from prior information about the behavior of dairy cows, and information about the layout of the farm, the classification was substantially improved.
The utility of a log of animal behaviour will increase when joined with other data (milk yield, for example) and has the potential to provide useful in animal management, obtained at little cost
|Item Type:||Refereed Article|
|Keywords:||GPS, geographical positioning system, behavior classification, machine learning, livestock, precision management|
|Research Division:||Agricultural, Veterinary and Food Sciences|
|Research Group:||Animal production|
|Research Field:||Animal management|
|Objective Division:||Animal Production and Animal Primary Products|
|Objective Group:||Livestock raising|
|Objective Field:||Dairy cattle|
|UTAS Author:||Rawnsley, R (Dr Richard Rawnsley)|
|Deposited By:||TIA - Research Institute|
Repository Staff Only: item control page