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

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6844
Author(s):  
Sigfredo Fuentes ◽  
Claudia Gonzalez Viejo ◽  
Eden Tongson ◽  
Nir Lipovetzky ◽  
Frank R. Dunshea

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.

2021 ◽  
Vol 37 ◽  
pp. 00091
Author(s):  
Vladimir Trukhachev ◽  
Serhii Oliinyk ◽  
Nikolay Zlydnev ◽  
Alexey Pokotilo ◽  
Alexander Ershov

The introduction of modern technological advances and principles of dairy herd management, which were developed in the member countries of the International Committee for Animal Registration (ICAR), contributed to the increase in milk productivity of pedigree cattle at the national level. The harmonization of national regulatory documents with the methodological principles developed in ICAR is a promising area. The study of new methodological approaches to the assessment of milk productivity shows that one of the differences in the assessment of daily milk yield, milk fat and protein yield is the different frequency of performing the corresponding work on the control milking of cows, the formation of a daily milk sample and the necessary mathematical calculations. In the in article various approaches to assessing the daily yield of the main dairy components during 2- and 3-fold milking of cows of a herd of pedigree black-and-white cattle are considered and coefficients are proposed for recalculating the daily content of fat and protein in milk. At the same time, the presented research results, in general, coincide with the main trends in the dynamics of milk fat and protein indicators shown in the ICAR recommendations.


Author(s):  
V. A. Tereshchenko ◽  
E. A. Ivanov ◽  
O. V. Ivanova ◽  
G. V. Permyakova ◽  
A. V. Semenovich

An important factor in increasing the productivity of dairy cattle is to ensure the full value of diets by improving the quality of feeds and enriching its with a complex of additives from alternative sources, in particular from the richest forest resources. Scientific-economically experience by studying the effect of feeding coniferous flour on milk productivity and metabolic parameters of cows and determining its optimal dosage was carried out in the conditions of LLC Plemzavod Tayozhny Sukhobuzimsky district of the Krasnoyarsk territory. Three groups of milking cows (control and two experimental) of the Black-Motley breed of the second calving, 5 heads in each group were formed for the experiment on the principle of analogues. The duration of the experiment was 100 days. According to the scheme of studies, the control group received the main diet, the 1st experimental group in addition to the main diet received coniferous flour at a dosage of 50 g/head/day, the 2nd experimental group coniferous flour at a dosage of 100 g/head/day. Research and data processing were carried out according to generally accepted methods. As a result of researches positive influence of coniferous flour on milk productivity and technological properties of cow milk was established. The analysis of the obtained data allowed to determine the most effective dosage of coniferous flour for the diet of cows 50 g/head/day, which contributed to an increase in milk yield for 100 days of lactation by 15.6%, the milk fat amount by 29.8%, the milk protein amount by 17.1%, milk of basic fat content by 29.4%, improvement technological properties of milk.


Author(s):  
A. Zheltikov ◽  
N. Kostomakhin ◽  
D. Adushinov ◽  
O. Zaiko ◽  
V. Dementev ◽  
...  

The characteristic of milk productivity of cows of Holstein and Simmental breeds in LLC “Sibirskaya Niva” in the Maslyaninsky district in the Novosibirsk region has been given. It has been revealed that under the natural and climatic environments of the Western Siberia, when creating favorable conditions for feeding and housing for cows of Holstein and Simmental breeds have sufficiently high milk productivity. It has been found that Holstein first-calf heifers surpassed their Simmental herdmates by 959 kg in milk yield for the first 305 days of lactation under the same conditions of housing and feeding, by 3,1 kg in daily milk yield, by 38,2 kg in milk fat yield, and by 28,3 kg in milk protein yield (P < 0,001). There were no statistically significant differences between animals of Holstein and Simmental breeds in terms of fat and protein content in milk, which amounted to 3,94 and 2,96 % in Holstein breed and 3,97 and 2,98 % in Simmental breed, respectively. Both breeds have shown high milk productivity during the first 3 lactations. Thus, the milk yield of Holstein cows for the first 3 lactation was 6475–9290 kg, Simmental cows it was 5516–7680 kg, fat content was 3,93–3,99 and 3,96–3,97 %, respectively. The protein content in the milk of cows of both breeds did not exceed 3,0 %. High variability has been found in milk yield, yield of milk fat and protein, the coefficient of milk content and duration of lactation, the lowest in the content of protein and fat in milk and live weight. The correlation coefficients between the fat and protein content in milk were generally positive, but did not exceed 0,28. Therefore, breeding in the herd of cows in LLC “Sibirskaya Niva” have to be conducted not only by fat content, but also by protein content in milk.


Author(s):  
S. Sukhanova ◽  
N. Pozdnyakova ◽  
F. Yaroslavtsev

The results of researches on the development of new mineral feed additives based on raw materials produced by Uralchem and the study of the eff ectiveness of their use in the rations of lactating cows have been presented in the article. The experiment has been carried out in the conditions of LLC “PF Barabinskoe” in the Dalmatovsky area in the Kurgan region where 3 groups of lactating cows of Black-and-White breed have been formed. Animals in the control group have been received the ration adopted in the farm, the 1st experimental group with the additive RusMA No. 1 at a dose of 150 g, the 2nd experimental group– with the additive RusMA No. 2 at the dose of 350 g. The use of experimental mineral additives in feeding lactating cows allowed us to increase their milk productivity and profi tability of production. At the same time, the best eff ectiveness was shown by the additive RusMA No. 2 at the dose of 350 g/head/day. The use of RusMA additives during the experiment period (105 days) allowed to increase the milk productivity of cows in the 1st experimental group by 6,03 % and in the 2nd experimental group by 8,24 %. Taking into account the fat content in milk, this diff erence was 6,31 and 8,53 %, respectively. The energy value of milk from cows of the experimental groups was higher compared to the control group by 2,45 and 1,76 %, respectively. According to the content of dry matter in milk, cows of the 2nd experimental group exceeded the control and 1st experimental group by 0,39 and 0,12 abs.%, respectively. The maximum milk fat content has been observed in the milk of cows of the 1st experimental group by 0,03 and 0,01 abs.% more than in the control and 2nd experimental groups, respectively. In terms of protein content, the cows of the 2nd experimental group signifi cantly exceeded the control group by 0,10 abs.% and the 1st experimental by 0,04 abs.%. The content of milk sugar in the 2nd experimental group was higher than in the control by 0,30 abs.% and compared to the 1st experimental by 0,11 %. Signifi cantly more calcium and phosphorus were contained in the milk of cows of the 2nd experimental group by 4,58 % (Р ≤ 0,001) and 2,86 % (Р ≤ 0,05), compared with the control group. The expenditures of feed in the EFU for the production of 1 kg of milk in animals of the 2nd experimental group was less by 5,13 % than in control cows and by 2,63 % compared to the 1st experimental group. The prime cost of 1 centner of milk was lower in the 2nd experimental group by 3,94 %, in the 1st experimental group by 2,65 % compared to the control group. The level of profi tability of milk production in the 2nd experimental group was higher by 9,0 and 1,0 abs.% in comparison with the control and 1st experimental groups, respectively.


Animals ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1840
Author(s):  
Ramūnas Antanaitis ◽  
Vida Juozaitienė ◽  
Vesta Jonike ◽  
Vytenis Čukauskas ◽  
Danguolė Urbšienė ◽  
...  

The aim of this study was to assess the relationship between temperament and milk performance in cows at different stages of lactation, describing their productivity, metabolic status and resistance to mastitis. This study showed that with increasing lactation, cows’ temperament indicators decreased (p < 0.001) and they became calmer. The highest temperament score on a five-point scale was found in cows between 45 and 100 days of lactation. In the group of pregnant cows, we found more cows (p = 0.005) with a temperament score of 1–2 compared with non-pregnant cows A normal temperament was usually detected in cows with lactose levels in milk of 4.60% or more and when the somatic cell count (SCC) values in cow milk were <100,000/mL and 100,000–200,000/mL, with a milk fat-to-protein ratio of 1.2. A larger number of more sensitive and highly aggressive cows was detected at a low milk urea level. In contrast to a positive phenotypic correlation (p < 0.05), this study showed a negative genetic correlation between the temperament of cows and milk yield (p < 0.001). Positive genetic correlations between temperament scores and milk somatic cells (p < 0.001) and milk fat-to-protein ratio (p < 0.05) were found to indicate a lower genetic predisposition in cows with a calmer temperament to subclinical mastitis and ketosis. On the other hand, the heritability of temperament (h2 = 0.044–0.100) showed that only a small part of the phenotypic changes in this indicator is associated with genetic factors.


Transport ◽  
2009 ◽  
Vol 24 (2) ◽  
pp. 135-142 ◽  
Author(s):  
Ali Payıdar Akgüngör ◽  
Erdem Doğan

This study proposes an Artificial Neural Network (ANN) model and a Genetic Algorithm (GA) model to estimate the number of accidents (A), fatalities (F) and injuries (I) in Ankara, Turkey, utilizing the data obtained between 1986 and 2005. For model development, the number of vehicles (N), fatalities, injuries, accidents and population (P) were selected as model parameters. In the ANN model, the sigmoid and linear functions were used as activation functions with the feed forward‐back propagation algorithm. In the GA approach, two forms of genetic algorithm models including a linear and an exponential form of mathematical expressions were developed. The results of the GA model showed that the exponential model form was suitable to estimate the number of accidents and fatalities while the linear form was the most appropriate for predicting the number of injuries. The best fit model with the lowest mean absolute errors (MAE) between the observed and estimated values is selected for future estimations. The comparison of the model results indicated that the performance of the ANN model was better than that of the GA model. To investigate the performance of the ANN model for future estimations, a fifteen year period from 2006 to 2020 with two possible scenarios was employed. In the first scenario, the annual average growth rates of population and the number of vehicles are assumed to be 2.0 % and 7.5%, respectively. In the second scenario, the average number of vehicles per capita is assumed to reach 0.60, which represents approximately two and a half‐fold increase in fifteen years. The results obtained from both scenarios reveal the suitability of the current methods for road safety applications.


Author(s):  
Х.А. АМЕРХАНОВ ◽  
Г.В. РОДИОНОВ ◽  
Л.П. ТАБАКОВА ◽  
А.П. ОЛЕСЮК ◽  
В.В. БОШЛЯКОВА ◽  
...  

Проведено комплексное исследование морфофункциональных особенностей молочной железы коров черно-пестрой и ярославской пород с разным уровнем молочной продуктивности в условиях крестьянско-фермерского хозяйства Московской области. Рассмотрены молочная продуктивность, морфологические и функциональные свойства вымени подопытных животных, гистологическая структура молочной железы. Отмечено, что у коров черно-пестрой породы количество молочного жира за лактацию составило 256 кг, а у ярославской породы — 233 кг. Показатель коэффициента молочности составил у черно-пестрых животных 1180 кг, а у коров ярославской породы — 1132кг. При анализе лактационных кривых было выявлено, что у подопытных коров обеих групп наивысший суточный удой получен на 2-м и 3-м мес лактации. Так, коэффициент постоянства лактации у коров черно-пестрой породы составил 88,7%, ярославской — 73,5%. При взятии промеров установлено, что по длине задние соски вымени черно-пестрых коров не соответствуют требованиям технологического отбора, а по диаметру сосков обе группы имеют оптимальные показатели. Время доения черно-пестрых животных составило 12,76±0,92 мин, ярославских — 11,45±0,94 мин. По индексу вымени у коров черно-пестрой породы показатели выше, чем у животных ярославской породы на 6,22%. Площадь паренхимы вымени составляет 81,4%, стромы 18,6%, у черно-пестрых особей, тогда как у ярославских на долю железистой ткани приходится 66%, соединительной — 34%. На основании проведенных исследований для повышения продуктивности стада желательно увеличить поголовье черно-пестрых животных и использовать инновационные методы, направленные на повышение качественных показателей молочной продуктивности коров ярославской породы. Complex study of morphological and functional characteristics of the mammary gland of black-and-white and yaroslavskaya breeds of cows with different levels of milk productivity under conditions of a peasant farm from Moscow region has been conducted. Milk productivity, morphological and functional properties of the udder of the animals, histological structure of the mammary gland have been observed. It has been noted that cows of black-and-white breed produced 256 kg of milk fat during lactation, cows of yaroslavskaya breed – 233 kg of milk fat. Milk productivity coefficient indicator for black-and-white breed was 1180 kg, 1132 kg for yaroslavskaya breed. Analysisof lactation curves of the cows studied has revealed that animals from both groups had the highest daily milk yield at the 2nd and 3rd months of lactation. The coefficient of lactation consistency of black-and-white cows has reached 88.7%,yaroslavskaya breed — 73.5%. Measurements taken has revealed that the length of the rear teatsof black-and-white cows did not meet the requirements of technological selection, at the  same time both groups had optimaldiameter of the teat indicators. Milking time for black-and-white cows has reached 12.76±0.92 minutes, for yaroslavskaya breed — 11.45 ± 0.94 minutes. According to the udder index, animals of black-and-white breed had higher indicator than that of the other group, by 6.22%. Cows of black-and-white breed had udder tissue consisting of 81.4% parenchyma and 18.6% stroma, while that of yaroslavskaya breed consisted of 66% glandular tissue, 34% connective tissue. Based on conducted studies it could be concluded, that it is preferable to increase the amount of black-and-white cows in the herd and to use innovative methods for increasing milk productivity of yaroslavskaya breed cows, in order to achieve higher milk productivity of entire herd.


2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
B Aparicio Ruiz ◽  
L Bori ◽  
E Paya ◽  
M A Valera ◽  
A Quiñonero ◽  
...  

Abstract Study question Would it be possible to predict embryo ploidy by taking into account conventional morphological and morphokinetic parameters together with IL-6 concentration in spent culture medium? Summary answer Our artificial neural network (ANN) trained with blastocyst morphology, embryo morphokinetics and IL-6 concentration distinguished between euploid/aneuploid embryos in 65% of the testing dataset. What is known already The analysis of spent embryo culture media represents the protein and metabolic state of the embryo and could be a non-invasive method of obtaining information about embryo quality. The impact of the presence/absence of several proteins in embryo culture samples over clinical results has been widely studied. The IL-6 is one of the most mentioned protein for its effect on embryo development, implantation and likelihood of achieving a live birth. In this initial attempt, we examined the predictive value for euploidy of a model that took into account the concentration of IL-6 in the spent culture medium. Study design, size, duration This prospective study included 319 embryos with PGT-A results. Out of the total, 127 were euploid and 192 aneuploid embryos. Concentration of IL-6 in spent embryo culture media (collected on the day of trophectoderm biopsy-fifth/sixth day of development), morphokinetic parameters (division time to 2 cells-t2; to 3 cells-t3, to 4 cells-t4; to 5 cells-t5 and time of blastocyst formation-tB) and blastocyst morphological grade (according to ASEBIR criteria) were considered to predict the embryo ploidy. Participants/materials, setting, methods Embryos were cultured in EmbryoScope. The chromosome analysis was performed using next-generation sequence technology. The concentration of IL-6 was measured in 20µL of spent embryo culture media with ELISA kits. Morphokinetic parameters were automatically annotated and the blastocyst morphology was evaluated by senior embryologists based on blastocele expansion, inner cell mass and trophectoderm quality. All the embryos were divided into 70% for training, 15% for validating and 15% for testing our ANN model with MatLab®. Main results and the role of chance The general description for the euploid embryo population was the following: 2% of the embryos were graded as A, 71% were graded as B and 28% were graded as C; the means and standard deviations were 25.32±2.97 hours (h) for t2, 35.33±5.15h for t3, 37.30±5.43h for t4, 48.24±6.62h for t5 and 103.93±12.8h for tB; and the average of IL-6 concentration was 1.51±0.70 pg/ml. The general description for the aneuploid embryo population was the following: 1% of the embryos were graded as A, 48% were graded as B and 51% were graded as C; the means and standard deviations were 26.13±3.51h for t2, 36.70±4.29h for t3, 38.20±4.24h for t4, 49.86±6.89h for t5 and 107.10±8.29h for tB; and the average of IL-6 concentration was 1.47±0.71 pg/ml. Our ANN model showed a higher general success rate as we increased the variables considered in the final prediction of euploid embryos. The accuracy, sensitivity and specificity for the testing dataset were: 0.60, 0.12 and 0.87 with morphokinetic parameters; 0.63, 0.24 and 0.93 with morphokinetics and IL-6 concentration; and 0.65, 0.16 and 0.96 with morphokinetics, IL-6 concentration and blastocyst morphological grade. Limitations, reasons for caution The low sensitivity and high specificity achieved in our models indicated that they were more capable of detecting aneuploid than euploid embryos. As this was a preliminary study, the small number of embryos included in the test (n = 48) was also a limitation. Wider implications of the findings The results showed that our model tended to classify the embryos as aneuploid. More euploid embryos would be necessary to train our model and achieve better results in the prediction of chromosomally normal embryos. Further studies with large number of embryos and additional variables could improve the non-invasive ploidy prediction. Trial registration number not applicable


Sign in / Sign up

Export Citation Format

Share Document