The use of multivariable wireless sensor data to early detect lameness in sheep

Al-Rubaye, Z., Al-Sherbaz, A., McCormick, W. D. and Turner, S. J. The use of multivariable wireless sensor data to early detect lameness in sheep. 

Workshop presented to: 
School of Science and Technology Annual Research Conference, 
Newton Building, 
The University of Northampton, 02 March 2016.

Abstract
Lameness is a clinical symptom of the painful disorder, which refers to the locomotion changes in sheep movement. These unbalanced movements result in a deviation from normal gait or posture. The footrot is considered one of the most significant causes of lameness in sheep in Great Britain due to a bacteria grows in a mud soil which transfer to the sheep foot and cause footrot that leads to lameness. Lameness has a negative impact on both sheep welfare and farm economy. The annual loss from the footrot only is estimated by £6 for each ewe in Great Britain according to the statistics from Agriculture and Horticulture Development Board (AHDB) in 2014. Therefore, preclinical detection of lameness at the farm will increase the level of protection regarding sheep health and farm commerce decline. The newly developed sensor technology utilises the idea of automatically monitoring objects either human or animal to determine the physiological and behavioural indicators, which are subsequently used an input to data analysis algorithms. The automated methods to monitor the farm bring many advantages to the farmer in terms of time spending, flock size increasing and sensitivity to detect the lamenessThe type of the collected data from the sensor used for recording animal’s behaviour depend on the sensor’s features and functionality. The sensor that will be used to conduct this research is immensely accurate and sensitive. It provides 3-aix acceleration, 3-aix angular velocity, 3-aix angles (Roll, Pitch, and Heading), longitude, latitude and time of reading which can be set up according to the demanded accuracy. This study will develop an automated model to early detect lameness in sheep by analysing the data that will be retrieved from a mounted sensor on the sheep neck collar. This extensive spatio-temporal data will be classified to infer the associated behaviour to the lame sheep according to an efficient data mining learning techniques. This model will help the shepherd to early detect the lame sheep to prevent the worse situation of trimming or even culling the sheep.

For more details go to http://nectar.northampton.ac.uk/8311/



If you'd like to find out more about Computing at the University of Northampton go to: www.computing.northampton.ac.uk. All views and opinions are the author's and do not necessarily reflected those of any organisation they are associated with