A new review, published in Animals in April 2019, intended for swine veterinarians and specialists, explores the technology currently available for remote, non-invasive monitoring of swine health and welfare.

The ability to continuously and non-invasively gather data on individual pig (and herd) welfare can provide statistically supported hypotheses for productivity fluctuations, mortality rates and disease occurrence. In turn, this information provides a basis for making any changes in swine units and can also be used to predict productivity and any welfare issues, such as tail-biting outbreaks.

The current review provides an introduction to algorithms and machine learning, summarises current literature on relevant sensors and sensor network systems, and drawing from industry pig welfare audit criteria, explains how these applications can be used to improve swine welfare and meet current pork production stakeholder expectations.

Precision livestock farming

The description for precision livestock farming used in this review is as follows:

“Precision livestock farming implies automated remote detection and monitoring of identified individuals for animal health and welfare using real-time analysis of images, sounds, tracking data, weight and body condition, and biological metrics in livestock.”

The basic technology

2D and 3D cameras

Imaging in pigs has been used to estimate pig weight, aggressive behaviour, walking patterns, sow posture, and behaviour during lactation

There is a broad range of imaging technology available, ranging from basic 2D camera sensors that require adequate ambient lighting to produce useful images and video, to 3D sensors that can provide more detailed, colour imaging. Infrared and depth sensors have become useful for capturing footage in low light and at night, and in determining proximity.

Microphones

Simple microphones and computers can be used to capture and process sound, which has proven useful in classifying and localising specific acoustic events such as indicators of stress or illness. High frequency calls could signal the occurrence of stressful events and an increase in the rate of coughing could indicate respiratory disease.

Thermistors and infrared imaging of temperature

Temperature monitors using a contact measuring media typically utilise thermistors embedded in a data logger or ear tag sensor. The sensor has direct contact with the tissue to take temperature measurements and provide temperature accuracies to 0.1 C.

Infrared cameras measure physiological and pathological processes related to changes in body temperature and as they do not require actual contact with the animal, they can be applied as a non-invasive, instantaneous method of collecting temperature data.

Accelerometers and motion tracking

An accelerometer is an electromechanical device used to measure accelerating forces. Forces can be static (eg, pig is lying down or resting) or acceleration due to movement (eg, pig is walking).

Livestock identification

In order to gain meaningful output from gathering animal data on a large-scale, commercial basis, an accurate method of identifying each animal is essential. This identification system must also be automated and affordable in order to be of value to the typical farmer. Individual identification methods, either currently used in the swine industry or research, include radio frequency identification, optical character recognition, and facial recognition.

How you use your pig data

How you apply this technology on farm and the value its application can provide to producers, veterinarians and swine specialists is entirely dependent on what parameters you wish to monitor and how you use the data collected.

However, with the global population expected to exceed 9 billion by 2050, demand for food will only increase, and therefore the sustainability of all livestock industries is critical to providing a reliable food source. By collecting and analysing vast quantities of data at a rate human observation cannot match, and continued development of precision farming, the possibilities for making long-term, measurable improvements on the transparency and sustainability of the pig industry is certainly attainable.

The full review was published in the journal, Animals on MDPI.