Area-specific predictions of unwanted events using multivariate modeling of water data

Katarina Nielsen Dominiak; Jeff Hindsborg; Lene Juul Pedersen; Anders Ringgaard Kristensen

Area-specific predictions of unwanted events using multivariate modeling of water data

Katarina Nielsen Dominiak, Jeff Hindsborg, Lene Juul Pedersen, Anders Ringgaard Kristensen

1 Downloads (Pure)

Abstract

In this study simultaneously monitored drinking patterns from multiple pens in one weaner section and one finisher section herd are modeled in a multivariate dynamic linear model (DLM). Correlations between the monitored data are incorporated in the model allowing it to include interactions between pens in each section. A two-sided tabular CUSUM is applied as control chart, whereby alarms for outbreaks of unwanted events amongst the pigs can be generated for specific pens in the herd. Area-specific alarms enable the manager to include specific knowledge of the animals in the targeted area and choose the best suited intervention.

Original language	English
Publication date	12 Jul 2018
Publication status	Published - 12 Jul 2018
Event	2nd International Conference on Agro Big Data and Decision Support Systems in Agriculture - Universitat de Lleida, Lleida, Spain Duration: 12 Jul 2018 → 14 Jul 2018 Conference number: 2 http://www.bigdssagro.udl.cat/congreso2018/?q=presentation

Conference

Conference	2nd International Conference on Agro Big Data and Decision Support Systems in Agriculture
Number	2
Location	Universitat de Lleida
Country/Territory	Spain
City	Lleida
Period	12/07/2018 → 14/07/2018
Internet address	http://www.bigdssagro.udl.cat/congreso2018/?q=presentation

Access to Document

Proceedings_Lleida_bigDSSagro2018Final published version, 58 KBLicence: Unspecified

Cite this

Area-specific predictions of unwanted events using multivariate modeling of water data. / Dominiak, Katarina Nielsen; Hindsborg, Jeff; Pedersen, Lene Juul et al.
2018. 27-30 Paper presented at 2nd International Conference on Agro Big Data and Decision Support Systems in Agriculture, Lleida, Spain.

Research output: Contribution to conference › Paper › Research › peer-review

@conference{dd1b04a53ea846de82ec568d237a3d6f,

title = "Area-specific predictions of unwanted events using multivariate modeling of water data",

abstract = "In this study simultaneously monitored drinking patterns from multiple pens in one weaner section and one finisher section herd are modeled in a multivariate dynamic linear model (DLM). Correlations between the monitored data are incorporated in the model allowing it to include interactions between pens in each section. A two-sided tabular CUSUM is applied as control chart, whereby alarms for outbreaks of unwanted events amongst the pigs can be generated for specific pens in the herd. Area-specific alarms enable the manager to include specific knowledge of the animals in the targeted area and choose the best suited intervention.",

author = "Dominiak, {Katarina Nielsen} and Jeff Hindsborg and Pedersen, {Lene Juul} and Kristensen, {Anders Ringgaard}",

note = "Proceedings of the Second International Conference on Agro Big Data and Decision Support Systems in Agriculture. ISBN: 978-84-09-04920-2.; 2nd International Conference on Agro Big Data and Decision Support Systems in Agriculture ; Conference date: 12-07-2018 Through 14-07-2018",

year = "2018",

month = jul,

day = "12",

language = "English",

pages = "27--30",

url = "http://www.bigdssagro.udl.cat/congreso2018/?q=presentation",

}

TY - CONF

T1 - Area-specific predictions of unwanted events using multivariate modeling of water data

AU - Dominiak, Katarina Nielsen

AU - Hindsborg, Jeff

AU - Pedersen, Lene Juul

AU - Kristensen, Anders Ringgaard

N1 - Conference code: 2

PY - 2018/7/12

Y1 - 2018/7/12

N2 - In this study simultaneously monitored drinking patterns from multiple pens in one weaner section and one finisher section herd are modeled in a multivariate dynamic linear model (DLM). Correlations between the monitored data are incorporated in the model allowing it to include interactions between pens in each section. A two-sided tabular CUSUM is applied as control chart, whereby alarms for outbreaks of unwanted events amongst the pigs can be generated for specific pens in the herd. Area-specific alarms enable the manager to include specific knowledge of the animals in the targeted area and choose the best suited intervention.

AB - In this study simultaneously monitored drinking patterns from multiple pens in one weaner section and one finisher section herd are modeled in a multivariate dynamic linear model (DLM). Correlations between the monitored data are incorporated in the model allowing it to include interactions between pens in each section. A two-sided tabular CUSUM is applied as control chart, whereby alarms for outbreaks of unwanted events amongst the pigs can be generated for specific pens in the herd. Area-specific alarms enable the manager to include specific knowledge of the animals in the targeted area and choose the best suited intervention.

M3 - Paper

SP - 27

EP - 30

T2 - 2nd International Conference on Agro Big Data and Decision Support Systems in Agriculture

Y2 - 12 July 2018 through 14 July 2018

ER -

Area-specific predictions of unwanted events using multivariate modeling of water data

Abstract

Conference

Access to Document

Fingerprint

Cite this