Automatic On-line Monitoring of animal Health and welfare by Precision livestock farming

Livestock production today has become a very complex process since several requirements have to be combined such as: food safety, animal welfare, animal health, environmental impact and sustainability in a wider sense. The consequence is a growing need to balance many of these variables during the production process. In the past farmers were monitoring their animals in their daily work by normal audio-visual observation like ethologists still do in their research. Today however the number of animals per farm has increased so much that this has become impossible. Another problem is that visual observation never can be done continuously during 24 hours a day. One of the objectives of Precision Livestock Farming (PLF) is to develop the technology and the tools for the on-line monitoring of farm animals and this continuously during their life and in a fully automatic way. This technology will never replace the farmer but can support him as a tool that automatically and continuously delivers him quantitative information about the status of his animals. Like other living organisms farm animals are responding to their environment with several behavioural and physiological variables. Many sensors and sensing techniques are under development to measure such behavioural and biological responses of farm animals. This can be done by new sensors or by sound analysis, image analysis etc. A major problem to monitor animals is the fact that animals themselves are complex systems that are individually different and that are so called time varying dynamic systems since their behaviour and health status can change at any time. Another challenge for PLF is to develop reliable monitoring tools for such Complex Individual Time varying Dynamic systems (“CITD” systems). In this paper we will talk about what is PLF and what is the importance of PLF. Next we will explain the basic principles. Further we will show examples of monitoring tools by PLF such as on-line monitor for health status by analysing continuously the sound produced by pigs. Another example shows the on-line automatic identification of the behaviour of individual laying hens by continuous analysis of 2D images from a top view camera. Next we will demonstrate the potential of PLF for more efficient controlling of biological processes. Finally we will discuss how implementation might be realised and what risk and problems are. The technology that is already available and that is under development today can be used for efficient and continuous monitoring if an engineering approach is combined with the expertise of ethologists, physiologist, veterinarians who are familiar with the animal as a living organism.

[1]  J. Aerts,et al.  Active control of the growth trajectory of broiler chickens based on online animal responses. , 2003, Poultry science.

[2]  Daniel Berckmans,et al.  Developing a computer vision system for the on-line quantification of the behaviour of laying hens in furnished cages , 2003 .

[3]  John A. Marchant,et al.  Model based location of pigs in scenes , 1995 .

[4]  T. K. Hamrita,et al.  Monitoring Deep Body Temperature Responses of Broilers Using Biotelemetry , 2000 .

[5]  Jean-Marie Aerts,et al.  Field test of algorithm for automatic cough detection in pig houses , 2008 .

[6]  X Whittaker,et al.  Vocalisations of the adult female domestic pig during a standard human approach test and their relationships with behavioural and heart rate measures. , 2001, Applied animal behaviour science.

[7]  H. H. Kristensen,et al.  Using light to control activity in broiler chickens. , 2004, British poultry science.

[8]  Jean-Marie Aerts,et al.  AP—Animal Production Technology: Recognition System for Pig Cough based on Probabilistic Neural Networks , 2001 .

[9]  T Mottram,et al.  Biosensors in the livestock industry: an automated ovulation prediction system for dairy cows. , 2001, Trends in biotechnology.

[10]  D Berckmans,et al.  Computer-assisted image analysis to quantify daily growth rates of broiler chickens , 2003, British poultry science.

[11]  Jack P. C. Kleijnen,et al.  CASE STUDY: OPTIMAL FACILITY ALLOCATION IN A ROBOTIC MILKING BARN , 2002 .

[12]  Roger A. Eigenberg,et al.  Development of a new respiration rate monitor for cattle. , 2000 .

[13]  Jean-Marie Aerts,et al.  Algorithm for cough detection in pig houses , 2004 .

[14]  David J. Parsons,et al.  Progress towards the development of an integrated management system for broiler chicken production , 2003 .

[15]  D. Weary,et al.  Effects of early separation on the dairy cow and calf. 1. Separation at 6 h, 1 day and 4 days after birth. , 2000, Applied animal behaviour science.

[16]  Jean-Marie Aerts,et al.  Automatic detection of infective pig coughing from continuous recording in field situations , 2004 .

[17]  Jean-Marie Aerts,et al.  Dynamic Data-based Modelling of Heat Production and Growth of Broiler Chickens: Development of an Integrated Management System , 2003 .

[18]  Jack P. C. Kleijnen,et al.  Optimal facilty allocation in a robotic milking barn , 2002 .

[19]  H. A. Elson,et al.  Evaluation of the effects of cage height and stocking density on the behaviour of laying hens in furnished cages , 2007, British poultry science.

[20]  Jean-Marie Aerts,et al.  On-line Cough Recognizer System , 1999 .

[21]  Yael Edan,et al.  An Individual Feed Allocation Decision Support System for the Dairy Farm , 2001 .

[22]  L. Keeling,et al.  The Effect of an Audience on the Gakel-Call and Other Frustration Behaviours in the Laying Hen (Gallus Gallus Domesticus) , 2003, Animal Welfare.

[23]  Daniel Berckmans,et al.  Automated recognition of spontaneous versus voluntary cough , 2001, MAVEBA.

[24]  Daniel Berckmans,et al.  Fuzzy approach for improved recognition of citric acid induced piglet coughing from continuous registration , 2003 .