Advanced search
Start date
Betweenand

Modelling the feeding patterns of growing-finishing pigs reared under precision feeding strategies

Grant number: 16/25157-8
Support Opportunities:Scholarships abroad - Research
Effective date (Start): August 01, 2017
Effective date (End): July 26, 2018
Field of knowledge:Agronomical Sciences - Animal Husbandry - Animal Nutrition and Feeding
Principal Investigator:Luciano Hauschild
Grantee:Luciano Hauschild
Host Investigator: Anders Ringgaard Kristensen
Host Institution: Faculdade de Ciências Agrárias e Veterinárias (FCAV). Universidade Estadual Paulista (UNESP). Campus de Jaboticabal. Jaboticabal , SP, Brazil
Research place: University of Copenhagen, Copenhagen, Denmark  

Abstract

The pig feed intake is determinate for a complex interaction of several factors as diet, environment, social interaction and sanitary challenges. Although empirical approaches do not have biological interpretation it has allows better predictions without the need to represent the mechanisms that regulate the feed intake. In this sense, it was proposed recently an Automatic Intelligent Precision Feeder System (AIPF) that from modelling techniques recursive (empirical method) has allow estimate individual daily feed intake in real time with good accuracy. The integration and modelling of diurnal feeding pattern of the individual pig in this system has high potential to advance to more precise estimates. Furthermore, it could be an excellent tool to distinguish between deviations from the normal feeding pattern caused by a change in the growth rate of the pigs, and deviations caused by a disease that implies increased/decreased feed consumption. However, the current model integrated in AIPF is a simple statistical linear procedure and does not have properties to adequately represent the diurnal feeding pattern of different individuals. In this sense, some techniques as dynamic linear model that allow an automatic and interactive learning with data-set can be an alternative for this problem. Therefore, this study aims to model automatically and interactively the individual daily feeding intake pattern of pigs at a real-time basis through an dynamical linear model. Furthermore, another objective is to develop a method to identify deviations from the normal feeding behavior caused for challenges. For this study data from different populations of growing-finish pigs raised in Brazil (Unesp) using the AIPF will be used. Electronic feeder (AIPF) systems automatically recorded the visits to the feeder, the time of the meals, and the amount of feed consumed per meal. The recorded database will be used to calculate the number of meals per day, intervals between meals (min) and feed consumption rate (feed intake divided by feeding time per meal, expressed in g/min) of each animal. A state space model with cyclic components will developed for modelling the diurnal drinking pattern, measured as hourly sums. Determination of variance structure by use of discount factors will used. Model performance will be investigated by error analysis. This initiative would contribute thus to the sustainable development of pig production by allowing a reduction in nutrient intake and better monitoring of animals thus aiding in making real-time decisions. (AU)

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
HAUSCHILD, L.; KRISTENSEN, A. R.; ANDRETTA, I.; REMUS, A.; SANTOS, L. S.; POMAR, C.. Toward better estimates of the real-time individual amino acid requirements of growing-finishing pigs showing deviations from their typical feeding patterns. ANIMAL, v. 14, n. 2, SI, p. S371-S381, . (16/25157-8, 18/15559-7)

Please report errors in scientific publications list by writing to: cdi@fapesp.br.