Department of Large Animal Sciences From registration to information II Anders Ringgaard Kristensen
Department of Large Animal Sciences Outline The decision making process revisited Sensors and data source Definition of concepts Value of data • Quality of information • Quality of decisions Advanced Quantitative Methods in Herd Management Slide 2
Department of Large Animal Sciences Making decisions Decision making is based on knowledge: • General knowledge : What you can read in a textbook on animal nutrition, animal breeding, agricultural engineering etc. • Context specific knowledge : What relates directly to the unique decision problem. Examples: • The milk yield of dairy cow No. 678 when considered for culling. • The estrus status of sow No. 345 when considered for insemination. • The current daily gain of the slaughter pigs in House 5 when considering whether or not to adjust protein contents of the diet. When knowledge is represented in a form that may be used directly as basis for a decision, we call it information. Advanced Quantitative Methods in Herd Management Slide 3
Department of Large Animal Sciences Information sources General knowledge: • Look in a textbook • Ask an expert Context specific knowledge: • Obtained through registrations (observations) in the herd: • Traditional registrations • Test day milk yield, cow 567 • Litter size of sow 123 • Sensor based registrations • Conductivity or temperature of milk from AMS • Accelerations of a sow from a censor node in an ear tag • Computer vision (image analysis) Advanced Quantitative Methods in Herd Management Slide 4
Department of Large Animal Sciences From registrations to information We refer to a collection (typically in a database) of registrations of the same kind as data. We don’t use data directly for decision making (huge amounts of data). Before we can use data we need to reduce it through some kind of processing. The resulting information is used for decision making (which again requires processing: optimization). Advanced Quantitative Methods in Herd Management Slide 5
Department of Large Animal Sciences The decision making process: Summary The purpose of monitoring is to improve the decisions Processing of registrations into information is necessary Choosing the best processing is a key issue Information is a tractable representation of context specific knowledge. Monitoring is the sub-path from registration to information During this course we will follow the path from data to decision: Advanced Quantitative Methods in Herd Management Slide 6
Department of Large Animal Sciences Trends in livestock farming Over the last decades we have seen: • Computers available to farmers • Process computers (climate control, feeding systems, milking systems) • Computer networks • On farms • The internet • Automatic registrations by sensors • Improved methods for data filtering • State space models • Bayesian networks • Improved methods for decision support • Decision graphs • Markov decision processes (dynamic programming) • Improved biological understanding How do we include this in herd management? How do we evaluate? Advanced Quantitative Methods in Herd Management Slide 7
Department of Large Animal Sciences PigIT: Sensors as installed in two experimental pens 16 pens in 4 sections are monitored by sensors and cameras Advanced Quantitative Methods in Herd Management Dias 8
Department of Large Animal Sciences PigIT: Data infrastructure in a herd Advanced Quantitative Methods in Herd Management Dias 9
Department of Large Animal Sciences PigIT: Sensor data – what does it look like? Water, Feed Local temp. Section: Temp. Humidity Advanced Quantitative Methods in Herd Management Dias 10
Department of Large Animal Sciences Data sources: Brain storm Live weight assessment: • … Heat detection • … Detection/prediction of farrowing • … Detection of diarrhea • … Detection of mastitis • … … Advanced Quantitative Methods in Herd Management Slide 11
Department of Large Animal Sciences Sensor types Flowmeters Climate sensors (temperature, humidity) Pedometers Accelerometers Vision Acoustic (e.g. coughing) AMS related Sensors provide data! Advanced Quantitative Methods in Herd Management Slide 12
Department of Large Animal Sciences Definition A record: λ Data: Λ = { λ 1 , λ 1 , … , λ k }, Λ ∈ R k Processing: Ψ () Information: I = Ψ ( Λ ), I ∈ R m , where m << k Decision: Θ Decision strategy: I → Θ The processing of data into information typically implies a huge reduction of data. The processing is specific to the decision problem. Advanced Quantitative Methods in Herd Management Slide 13
Department of Large Animal Sciences Value of data (and processing) Improving quality of information • How do we assess the quality of information? • Numerical information: Standard deviation • Categorical information: AUC (area under curve) Improving quality of decisions • How do we assess the quality of decisions: Utility value Advanced Quantitative Methods in Herd Management Slide 14
Department of Large Animal Sciences Numerical information: Number of farrowings Example from exercise later in course: A sow farmer wish to predict the number of farrowings in a given (future) week. Different kinds of data can be collected: • # sows inseminated • Historical farrowing percentage • Heat detection after 3 weeks • Pregnancy test (ultra sound) The information requested is: • Expected number of farrowings The quality of the information is: • The standard deviation (or variance) of the prediction Advanced Quantitative Methods in Herd Management Slide 15
Department of Large Animal Sciences Example from exercises: Number of farrowings More data increase the precision of the prediction! Refer to exercise later in course! In the table, s is the standard deviation of the prediction. Observations (data) s Number of sows inseminated (12) 1.66 + conception rate in herd (historical data) 1.39 + heat detection after 3 weeks (2 in heat) 0.98 + heat detection quality in herd 0.81 + ultra sound scanning of 10 sows 0.47 Advanced Quantitative Methods in Herd Management Slide 16
Department of Large Animal Sciences Categorical information Information provided only as a state: Heat detection: {In heat, Not in heat} Pregnancy test: {Pregnant, Not pregnant} Disease diagnosis: {Diseased, Not diseased} Body Condition Score: {1, 2, 3, 4, 5} State { d 1 , d 2 , … , d n } Advanced Quantitative Methods in Herd Management Slide 17
Department of Large Animal Sciences Categorical information The measurement is (either literally or conceptually) a two step procedure: 1. Measurement of a continuous variable y ~ N( µ i , σ i 2 ) if the animal is in State d i . The observation can be just a number or an entire vectyr. 2. Assigning of a state d i to the measurement depending on a set of threshold values { τ 1 , …, τ n -1 }: 1. τ i -1 < y ≤ τ i ⇒ State d i observed Advanced Quantitative Methods in Herd Management Slide 18
Department of Large Animal Sciences Example – pregnancy diagnosis State, d i {Not pregnant ( i = 0), Pregnant ( i = 1) } Measurement Hormone level, h Distributions: • i = 0 h ~ N(10, 1 2 ) • i = 1 h ~ N(13, 1 2 ) Threshold: 11 Diagnose: • h ≤ 11 Not pregnant • h > 11 Pregnant Advanced Quantitative Methods in Herd Management Slide 19
Department of Large Animal Sciences Overall performance of test – ROC AUC = 0.98 By varying the threshold all combinations of sensitivity and specificity along the curve can be achieved. The circle corresponds to τ = 11.5, where the sensitivity is 0.93 and the specificity is also 0.93. The performance is measured as Area Under Curve (AOC): • AUC = 1: Perfect method • AUC = 0.5: Useless method (lottery) Advanced Quantitative Methods in Herd Management Slide 20
Department of Large Animal Sciences Example – pregnancy diagnosis: Less precise! State, d i {Not pregnant ( i = 0), Pregnant ( i = 1) } Measurement Hormone level, h Distributions: • i = 0 h ~ N(10, 2 2 ) - Standard deviation doubled • i = 1 h ~ N(13, 2 2 ) - Standard deviation doubled Threshold: 11 Diagnose: • h ≤ 11 Not pregnant • h > 11 Pregnant Advanced Quantitative Methods in Herd Management Slide 21
Department of Large Animal Sciences Overall performance of test – ROC – Less precise AUC = 0.83 The quality of this information is less good, because the AUC is smaller than in the other example Advanced Quantitative Methods in Herd Management Slide 22
Department of Large Animal Sciences Back to PigIT: Detection of fouling and diarrhea Data (cf. Slide 18): • Pen level: • Water consumption per hour • Drinking bouts per hour • Temperature at the corridor • Temperature at the resting area • Feed intake per day • Live weight per week • Section level • Temperature • Humidity Information: • Event (fouling or diarrhea) Processing: • Dynamic linear model Jensen, D.B. 2016. Automatic learning and pattern recognition using sensor data in livestock farming. PhD thesis. Department of Large Animal Sciences. 159p. Advanced Quantitative Methods in Herd Management Slide 23
Recommend
More recommend
