Big (pig) data and the internet of the swine things: a new paradigm in the industry

Piñeiro, Carlos; Morales, J.; Rodríguez, María Martín; Aparicio, M; Manzanilla, Edgar García; Koketsu, Yuzo

doi:10.1093/af/vfz002

Cited by 42 publications

(25 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, sow data, sensor data and behavior data that have recently started being collected by digital technologies will provide a large opportunity for producers and veterinarians to monitor and care for individual sows in breeding herds [1,80]. Such big data collected on farms should be transformed into valuable information by farm data analysis to improve the making decision process for maximizing sows' potential, optimizing their lifetime performance and enhancing animal welfare in breeding herds.…”

Section: Discussionmentioning

confidence: 99%

“…However, an observational study with appropriate statistical models can provide practical and readily applicable information to swine veterinarians and producers about real world events and practices that are difficult to investigate using controlled experiments. Also, an observational study is a powerful tool to quantify associations between outcomes and possible risk factors using big data from digital technologies [1].…”

Section: Farm Data Analysis As An Observational Studymentioning

confidence: 99%

“…Farm data are collected and stored on a daily basis by recording software in breeding herds. However, most producers only use the data to generate basic reports such as sow cards, working lists and a brief performance summary, and so do not use their farm data to its full potential [ 1 ]. Herd management based on farm data analysis [ 1 ] can help producers and veterinarians to maximize lifetime reproductive potential of sows to improve economic inefficiency [ 2 – 4 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Farm data analysis for lifetime performance components of sows and their predictors in breeding herds

Koketsu

Iida

2020

Porc Health Manag

Self Cite

View full text Add to dashboard Cite

Our objectives in this review are 1) to define the four components of sow lifetime performance, 2) to organize the four components and other key measures in a lifetime performance tree, and 3) to compile information about sow and herd-level predictors for sow lifetime performance that can help producers or veterinarians improve their decision making. First, we defined the four components of sow lifetime performance: lifetime efficiency, sow longevity, fertility and prolificacy. We propose that lifetime efficiency should be measured as annualized piglets weaned or annualized piglets born alive which is an integrated measure for sow lifetime performance, whereas longevity should be measured as sow life days and herd-life days which are the number of days from birth to removal and the number of days from date of first-mating to removal, respectively. We also propose that fertility should be measured as lifetime non-productive days, whereas prolificacy should be measured as lifetime pigs born alive. Second, we propose two lifetime performance trees for annualized piglets weaned and annualized piglets born alive, respectively, and show inter-relationships between the four components of the lifetime performance in these trees. Third, we describe sow and herd-level predictors for high lifetime performance of sows. An example of a sow-level predictor is that gilts with lower age at first-mating are associated with higher lifetime performance in all four components. Other examples are that no re-service in parity 0 and shorter weaning-to-first-mating interval in parity 1 are associated with higher fertility, whereas more piglets born in parity 1 is associated with higher prolificacy. It appears that fertility and prolificacy are independent each other. Furthermore, sows with high prolificacy and high fertility are more likely to have high longevity and high efficiency. Also, an increased number of stillborn piglets indicates that sows have farrowing difficulty or a herd health problem. Regarding herd-level predictors, large herd size is associated with higher efficiency. Also, herd-level predictors can interact with sow level predictors for sow lifetime performance. For example, sow longevity decreases more in large herds than small-to-mid herds, whereas gilt age at first-mating increases. So, it appears that herd size alters the impact of delayed gilt age at first-mating on sow longevity. Increased knowledge of these four components of sow lifetime performance and their predictors should help producers and veterinarians maximize a sow’s potential and optimize her lifetime productivity in breeding herds.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Farm Data Analysis As An Observational Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Farm data analysis for lifetime performance components of sows and their predictors in breeding herds

Koketsu

Iida

2020

Porc Health Manag

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sensors and big data models can function to combine this information, improving farmer response and decisionmaking. Digitalizing animal agriculture by using animal-and environmental-oriented data will improve overall health management, nutrition, genetics, reproduction, welfare, biosecurity, and emissions (Piñeiro et al, 2019).…”

Section: Big Datamentioning

confidence: 99%

Digitalization of Animal Farming

Neethirajan¹

2020

Preprint

View full text Add to dashboard Cite

As the global human population increases, animal agriculture must adapt to provide more animal products while also addressing concerns about animal welfare, environmental sustainability, and public health. The purpose of this review is to discuss the digitalization of animal farming with Precision Livestock Farming (PLF) technologies, specifically biosensors, big data, and block chain technology. Biosensors are noninvasive or invasive sensors that monitor an animal’s health and behavior in real time, allowing farmers to monitor individual animals and integrate this data for population-level analyses. The data from the sensors is processed using big data-processing techniques such as data modelling. These technologies use algorithms to sort through large, complex data sets to provide farmers with biologically relevant and usable data. Blockchain technology allows for traceability of animal products from farm to table, a key advantage in monitoring disease outbreaks and preventing related economic losses and food-related health pandemics. With these PLF technologies, animal agriculture can become more transparent and regain consumer trust. While the digitalization of animal farming has the potential to address a number of pressing concerns, these technologies are relatively new. The implementation of PLF technologies on farms will require increased collaboration between farmers, animal scientists, and engineers to ensure that technologies can be used in realistic, on-farm conditions. These technologies will call for data models that can sort through large amounts of data while accounting for specific variables and ensuring automation, accessibility, and accuracy of data. Issues with data privacy, security, and integration will need to be addressed before there can be multi-farm databases. Lastly, the usage of blockchain technology in animal agriculture is still in its infancy; blockchain technology has the potential to improve the traceability and transparency of animal products, but more research is needed to realize its full potential. The digitalization of animal farming can supply the necessary tools to provide sustainable animal products on a global scale.

show abstract

“…In the era of big data collection on farms, the digitalization process will generate new knowledge in most of the relevant topics in swine production including nutrition, health management, reproduction, genetics, biosecurity, behavior, welfare, and pollutant emissions (4). New technologies, such as commercially available automatic feeding systems (AFS) capture big data of central phenotypes (intake, feeding time, daily visits and body weight) that, with adequate mathematical tools, can provide a better understanding on animal requirements, increasing efficiency and sustainability.…”

Section: Introductionmentioning

confidence: 99%

Quantifying growth perturbations over the fattening period in swine via mathematical modelling

Revilla

Lenoir

Flatres-Grall³

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Resilience can be defined as the capacity of animals to cope with short-term perturbations in their environment and return rapidly to their pre-challenge status. In a perspective of precision livestock farming, it is key to create informative indicators for general resilience and therefore incorporate this concept in breeding goals. In the modern swine breeding industry, new technologies such as automatic feeding system are increasingly common and can be used to capture useful data to monitor animal phenotypes such as feed efficiency. This automatic and longitudinal data collection integrated with mathematical modelling has a great potential to determine accurate resilience indicators, for example by measuring the deviation from expected production levels over a period of time. Results: This work aimed at developing a modelling approach for facilitating the quantification of pig resilience during the fattening period. A total of 13 093 pigs, belonging to three different genetic lines were monitored, and body weight measures registered with automatic feeding systems. We used the Gompertz model and linear interpolation on body weight data to quantify individual deviations from expected production, thereby creating a resilience index. The approach was able to quantify different degrees of perturbation. Further, we evaluated the heritability of the resilience index in the different lines analyzed. Conclusions: Our model-based approach can be useful to quantify pig responses to perturbations using exclusively the growth curves and should contribute to the improvement of swine productive performance. Keywords: modelling, perturbation, resilience, robustness, body weight, big data, pig, precision livestock farming

show abstract

Big (pig) data and the internet of the swine things: a new paradigm in the industry

Cited by 42 publications

References 21 publications

Farm data analysis for lifetime performance components of sows and their predictors in breeding herds

Farm data analysis for lifetime performance components of sows and their predictors in breeding herds

Digitalization of Animal Farming

Quantifying growth perturbations over the fattening period in swine via mathematical modelling

Contact Info

Product

Resources

About