An Innovative Concept for a Multivariate Plausibility Assessment of Simultaneously Recorded Data

Abstract

The aim of this work was to develop an innovative multivariate plausibility assessment (MPA) algorithm in order to differentiate between ‘physiologically normal’, ‘physiologically extreme’ and ‘implausible’ observations in simultaneously recorded data. The underlying concept is based on the fact that different measurable parameters are often physiologically linked. If physiologically extreme observations occur due to disease, incident or hormonal cycles, usually more than one measurable trait is affected. In contrast, extreme values of a single trait are most likely implausible if all other traits show values in a normal range. For demonstration purposes, the MPA was applied on a time series data set which was collected on 100 cows in 10 commercial dairy farms. Continuous measurements comprised climate data, intra-reticular pH and temperature, jaw movement and locomotion behavior. Non-continuous measurements included milk yield, milk components, milk mid-infrared spectra and blood parameters. After the application of the MPA, in particular the pH data showed the most implausible observations with approximately 5% of the measured values. The other traits showed implausible values up to 2.5%. The MPA showed the ability to improve the data quality for downstream analyses by detecting implausible observations and to discover physiologically extreme conditions even within complex data structures. At this stage, the MPA is not a fully developed and validated management tool, but rather corresponds to a basic concept for future works, which can be extended and modified as required.

Development of a subacute ruminal acidosis risk score and its prediction using milk mid-infrared spectra in early-lactation cows

“…The temperature in the barn was not recorded during collection of the secondary data. However, because it is needed in the further course of this work for correction purposes of fixed environmental effects, it was estimated using a linear model [coefficient of determi-nation (R 2 ) = 0.99, residual SD = 0.67°C] that was developed by Mensching et al (2020c) and established on the primary data set. In this model, external climate data from a nearby weather station of the German Weather Service (DWD Climate Data Center, 2018), and estimated farm effects were used to predict the temperature in the barn.…”

“…Data acquisitions with automated recording systems and sensitive measuring instruments in difficult environments such as agricultural practice are prone to failure and thus have to be investigated with caution. Therefore, a multivariate plausibility assessment according to Mensching et al (2020c) was applied to the data set, which was aggregated on a daily basis. In this procedure, the observations of all traits were classified as "physiologically normal," "physiologically extreme," or "implausible," considering various simultaneously recorded data.…”

“…Observations of 3 animals were removed even before the plausibility of the data was assessed, as they showed unspecific clinical signs and thus were treated by the herd manager with medications, which might affect rumen fermentation. See Mensching et al (2020c) for more details on this procedure.…”

“…Mensching et al: PREDICTION OF SARA RISK USING MILK MID-INFRARED SPECTRA Data collection scheme, used sequentially in each of the 10 farms (adapted fromMensching et al, 2020c).…”

Precision Detection of Real-Time Conditions of Dairy Cows Using an Advanced Artificial Intelligence Hub

“…The data preprocessing, preparation, and algorithm programming after the acquisition of data were conducted using python 3.7.0 [55]. The commonly used scientific computing toolkits, such as matplotlib and scikit-learn, were also based on python 3.7.0.…”