Biometric Physiological Responses from Dairy Cows Measured by Visible Remote Sensing Are Good Predictors of Milk Productivity and Quality through Artificial Intelligence

Abstract

New and emerging technologies, especially those based on non-invasive video and thermal infrared cameras, can be readily tested on robotic milking facilities. In this research, implemented non-invasive computer vision methods to estimate cow’s heart rate, respiration rate, and abrupt movements captured using RGB cameras and machine learning modelling to predict eye temperature, milk production and quality are presented. RGB and infrared thermal videos (IRTV) were acquired from cows using a robotic milking facility. Results from 102 different cows with replicates (n = 150) showed that an artificial neural network (ANN) model using only inputs from RGB cameras presented high accuracy (R = 0.96) in predicting eye temperature (°C), using IRTV as ground truth, daily milk productivity (kg-milk-day−1), cow milk productivity (kg-milk-cow−1), milk fat (%) and milk protein (%) with no signs of overfitting. The ANN model developed was deployed using an independent 132 cow samples obtained on different days, which also rendered high accuracy and was similar to the model development (R = 0.93). This model can be easily applied using affordable RGB camera systems to obtain all the proposed targets, including eye temperature, which can also be used to model animal welfare and biotic/abiotic stress. Furthermore, these models can be readily deployed in conventional dairy farms.

Livestock Identification Using Deep Learning for Traceability

“…Further field test is required to validate an optimal setup (e.g., camera positioning, power supply, and connectivity) as well as to evaluate external environment factors (e.g., lightning, dust, ambient temperature). The deployed device can incorporate other algorithms to predict physiological responses [ 32 ].…”

“…An advantage of the model developed is that it can be integrated with previous works from the Digital Agriculture, Food and Wine research group from The University of Melbourne related to the welfare assessment of farm animals. Specifically, different models have been developed to extract animal physiological information from RGB and infrared thermal videos, such as heart rate, eye temperature, respiration rate, and sudden movements for pigs [ 34 ], sheep [ 35 ], cattle [ 36 ], and dairy cows [ 32 ]. Hence, integrating the analysis pipeline ( Figure 2 ) up to face cropping with the ML models developed for animal physiology will allow extracting the ID per animal and parameters to assess welfare.…”

“…Hence, integrating the analysis pipeline ( Figure 2 ) up to face cropping with the ML models developed for animal physiology will allow extracting the ID per animal and parameters to assess welfare. These integrated models may not require a FLIR DUO PRO, just normal RGB cameras, since eye temperature has been extracted using ML models from heart rate and respiration rate plus environmental temperature and relative humidity for dairy cows [ 32 ]. The latter explains using the FLIR visible and infrared thermal integrated camera for this study.…”

Effect of Packaging and Portioning on the Dynamics of Water–Fat Serum Release from Fresh Pasta Filata Soft Cheese

“…Experimental data describing the leachate amount collected within 24 h of unpacking the pasta filata cheeses from C cheese and CS cheese with various degrees of sample fragmentation, vacuum-packed and packed in brine were used to develop the ANN model. In previous research, ANNs in the form of MLP with a single hidden layer were sufficient in describing a non-linear phenomenon occurring in food processing [43][44][45][46]. Therefore, in our study, such topologies were used to model the amount of leachate from pasta filata cheese.…”

Identification of Factors Affecting Environmental Contamination Represented by Post-Hatching Eggshells of a Common Colonial Waterbird with Usage of Artificial Neural Networks

“…ANNs are more and more frequently applied to the analysis of the results of experimental research conducted in many research programs [ 23 , 24 , 25 , 26 , 27 ]. Neural modeling can be effectively used to solve classification and regression problems in biological sciences, including prediction [ 28 , 29 ].…”