MSU Extension Pork

Livestock producers and stakeholder industries will be challenged to meet the rising demand for animal protein derived from a growing global population. By 2050, the global population is projected to be over 9 billion, consuming 50-60% more food (based on today’s consumption patterns), according to Food and Agriculture Organization (FAO) of the United Nations 2009 report ¹. One solution to this global food security issue is to produce more food while equaling the current level of input or intensifying sustainability. This demand will require further intensification, which raises ethical questions, including animal welfare concerns over animal living space. As such, animal welfare may be one potential trade-off in favor of sustainable intensification².

One would be hard-pressed to find many similarities between the entertainment room of the typical North American home and improvements in swine welfare. However, through the use of sensors, artificial intelligence and animal behavior research, the very technology that is helping to bring video games to life for the average American is used by engineers and researchers to develop automate monitoring technologies, forming the concept of Precision Livestock Farming ^3,4. The microphones, infrared cameras, pressure sensors, and other technology used in gaming systems such as Sony PlayStation^®️, Microsoft XBox^®️, and Nintendo Wii^™ are being explored as possible assistants to veterinarians and producers in the care of their livestock. Cameras capable of capturing images of 3-dimensional objects for enhanced gameplay may make it possible to automatically detect illness in swine and other livestock. Movement trackers and sensors designed to immerse players in the fantasy world of gaming could play a role in collecting information about the quality of movement and welfare of pigs. For example, facial recognition software that identifies one human from another, is sophisticated enough to identify individual animals⁵. As the possibilities continue to increase, the experts responsible for the health and welfare of their swine can draw inspiration for the use of technology from their counterparts in human medicine; In this area, similar technology is being coupled with artificial intelligence to recognize patterns and predict outcomes, assisting doctors in the recognition of at-risk patients and the making of diagnoses. Veterinarians may be able to use very similar techniques for the improvement of animal welfare in swine production, but before all of these advancements can be implemented there must be greater understanding of the technology itself. This article is the first in a series of four Precision Livestock Farming publications for the Michigan Pork Producers Association magazine, Pork Quarterly: 1) a general introduction to PLF, machine learning and algorithms 2) potential applications of remote monitoring and 3) the implications for farmers and their veterinarians, and finally 4) areas of future research.

A general introduction to Precision Livestock Farming

Precision Livestock Farming (PLF) also known as Precision Animal Management, is defined by Wathes as “the management of livestock production using the principles and technology of process engineering to monitor, model and manage animal production” ⁶. PLF applies technological advances to the monitoring of and data collection from individual animals within large herds with the hope of optimizing the welfare and contribution of each animal. While PLF for swine farming relies on new technology, it cannot be considered a new science. For example, in 1988, DeShazer et al.⁷ reported over 90 applications for image analysis in pig production. Applications and availability of precision livestock farming tools have greatly increased making it a field that should catch the attention of veterinarians and stock people alike.  This increase is not limited to the livestock sector and across a wide variety of fields; the rate of technological advancement of the last two decades leaves even the most committed enthusiast in the dust. When we consider Moore’s Law⁸ - the principle that the number of transistors on an integrated circuit chip doubles approximately every two years - it is no wonder staying up-to-date seems to be a Sisyphean task. In 1971, a microprocessor housed approximately 2,308 transistors, while at the time of writing a microprocessor comfortably fits 19.2 billion. Perhaps a more relevant example based on the earlier discussion of machine learning, would be that of supercomputers’ computational ability; currently, the most powerful supercomputers can complete 93 trillion computations per second ⁸. Suddenly, with figures such as these in our minds it becomes increasingly easy to see how powerful machine learning is and how it could be a highly beneficial component of PLF.

While principally a review of scientific literature of PLF between 2012 to present, this series will review information gleaned from proprietary data, institutional input, market conditions and scholarly ethical assessments. It is provided as information targeting an emphasis of food animal welfare including (but not limited to) health, productivity, behavior, and physiological responses and as defined by American Veterinary Medical Association (AVMA) Welfare Principles⁹. Mention of trade names, products, commercial practices or organizations does not imply endorsement by the authors.  

Analysis and decision making for agriculture - It is all in the algorithm.

An algorithm is a formula, or step-by-step set of operations, utilized to solve a specific problem or class of problems. A programming algorithm is a computer procedure that tells the computer precisely what steps to take to solve a problem utilizing inputs to determine the outputs. Programmers provide the human initiation of the process by writing the algorithm that instructs the computer how to perform the specific operations necessary to solve a problem. Machine learning, also referred to as deep learning, is a family of computational methods that allows an algorithm to program itself using large sets of examples that demonstrate the desired behavior. Because the computer “learns” from these example sets of existing data, a human is not constantly required to specify steps or rules for the computer to follow¹⁰.  For example, algorithms are often used in research for determining gait kinematic patterns for conditions such as hip osteoarthritis ¹¹, Parkinson’s disease ¹², and multiple sclerosis ¹³ and show potential for future clinical use.

Machines Mimicking the Mind: Machine Learning

Data mining is the process by which useful information and trends are extracted from large databases and datasets, and swine veterinarians are accustomed to using the process to glean information on topics such as sow performance and history. The use of data mining can be observed in “information-provided” database software systems (i.e. PigCHAMP, Swine Management Systems, Cloudfarms, PigKnows, MetaFarms, Farms.com) that are driven by the input of observed data (e.g. days to first estrus, number of piglets born alive). In contrast to this, machine learning differs because it learns from a pool of probability models that best predict unobserved data. Beginning with group or individual patient-level observations, algorithms sift through variables searching for combinations that reliably predict outcomes. One of the greatest benefits of machine learning is its ability to use highly complex data, such as a collection of predictors, to produce vastly richer estimates than would be possible through standard statistical models¹⁰. This capacity allows for the use of new kinds of data, those whose sheer volume or complexity would previously have made analyzing them unimaginable.

Artificial neural networks (ANNs) are systems that can be a component of machine learning. They are modeled off of the design and function of the brain. In these systems, input data in the form of a number enters and is connected by synapses to neurons that perform specific calculations and output a result. ANNs can have many layers of synapses, allowing for complex calculations and even deeper machine learning. When presented with images and video, ANNs are particularly useful because they are capable of extracting many different data points simultaneously and recognizing patterns and trends within the image itself ¹⁴.

Machine learning particularly benefits from the use of open source access, a practice that allows programmers to collaborate to alter and improve algorithms. Open source is similar to a colleague discussion because it functions on the premise that more heads are better than one when it comes to resolving an issue.  Open source allows people to freely access online local versions of algorithms, edit them to complete new tasks, and grow the code beyond its original release.  For example, to train the computer a programmer will classify an item multiple times until the computer can classify it on its own. This particular form of machine learning can be expanded from classifying stationary objects in an image to classifying a moving object through the addition of an image tracking program that follows an item as it continues to classify. One open source program called YOLO (You Only Look Once) utilizes Darknet, an image tracking program. Open sourcing in the development of Darknet has allowed for classification in motion from one image every 20 seconds to an image every 1/20 of a second and improved tracking time by 1000 percent ¹⁵. For more information on object detection and tracking watch https://pjreddie.com/darknet/yolo/.        

With this basic introduction to algorithms, machine learning, and PLF, the focus can now be turned to exploring the different types of technology that makes the essential collection of data possible. In recent years, stock people implementing PLF typically utilize the sensors initially developed for use with gaming systems such as Xbox, Halo TM, and Wii Connect. This off-label utilization of technology for agriculture carries along with it the benefit of widespread availability and consumer-driven lower costs giving livestock farmers easy and inexpensive access to 3-dimensional sensors, cameras, and microphones. Through the following series of articles, we will look at technologies currently in use and some that show potential for implementation in PLF practices.

References

¹ FAO. The State of Food and Agriculture: Livestock in Balance.; 2009. doi:10.1016/S0140-6736(75)92740-3

² Godfray HCJ, Garnett T. Food security and sustainable intensification. Philos Trans R Soc B Biol Sci. 2014;369(1639):20120273-20120273. doi:10.1098/rstb.2012.0273

³ Neethirajan S. Recent advances in wearable sensors for animal health management. Sens Bio-Sensing Res. 2017;12:15-29. doi:10.1016/j.sbsr.2016.11.004

⁴ Berckmans D. Precision livestock farming technologies for welfare management in intensive livestock systems. Rev sci tech Off int Epiz. 2014. doi:10.20506/rst.33.1.2273

⁵ Hansen, MF, Smith ML, Smith LN, Salter MG, Baxter EM, Farish M., Grieve B. (2018). Towards on-farm pig face recognition using convolutional neural networks. Computers in Industry, 2018; 98:145–152. doi:10.1016/J.COMPIND.2018.02.016.

⁶ Wathes CM. Precision livestock farming for animal health, welfare and production. In: Aland A, Madec F, eds. Sustainable Animal Production. Wageningen Academic Publishers; 2009:411-419.

⁷ DeShazer JA, Moran P, Onyango CM, Randall JM, Schofield CP. Imaging Systems to Improve Stockmanship in Pig Production. AFRC Institute of Engineering Research: 1988.

⁸ Fueling innovation we love and depend on: Over 50 Years of Moore’s Law. https://www.intel.com/content/www/us/en/silicon-innovations/moores-law-technology.html. Accessed August 31, 2019.

⁹ AVMA. Animal Welfare: What Is It? https://www.avma.org/KB/Resources/Reference/AnimalWelfare/Pages/what-is-animal-welfare.aspx. Accessed August 31, 2019.

¹⁰ Obermeyer Z, Emanuel EJ. HHS Public Access. N Engl J Med. 2016;375(13):1216-1219. doi:10.1056/NEJMp1606181. Predicting the Future — Big Data, Machine Learning, and Clinical Medicine. The New Eng J Med. 2016;375(13):1216-1219. doi:10.1056/NEJMp1606181.

¹¹ Allison K, Hall M, Wrigley TV, Pua Y-H, Metcalf B, Bennell KL. Sex-specific walking kinematics and kinetics in individuals with unilateral, symptomatic hip osteoarthritis: A cross sectional study. Gait Posture. 2018;65:234-239. doi:10.1016/j.gaitpost.2018.07.179.

¹² Creaby MW, Cole MH. Gait characteristics and falls in Parkinson's disease: A systematic review and meta-analysis. Parkinsonism Relat D. 2018. doi:10.1016/j.parkreldis.2018.07.008.

¹³ Sosnoff JJ, Sandroff BM, Motl RW. Quantifying gait abnormalities in persons with multiple sclerosis with minimal disability. Gait Posture. 2012;36(1):154-156. doi:10.1016/j.gaitpost.2011.11.027.

¹⁴ Puri M, Solanki A, Padawer T, Tipparaju SM, Moreno WA, Pathak Y. Introduction to Artificial Neural Network (ANN) as a Predictive Tool for Drug Design, Discovery, Delivery, and Disposition: Basic Concepts and Modeling. Basic Concepts and Modeling. Elsevier Inc.; 2015. doi:10.1016/B978-0-12-801559-9.00001-6

¹⁵ Ren P, Fang W, Djahel S. A novel YOLO-Based real-Time people counting approach. 2017 Int Smart Cities Conf ISC2 2017. 2017;243:3-4. doi:10.1109/ISC2.2017.8090864.