Behavior Of Dairy Cows Research Articles

Social network analysis to predict social behavior in dairy cattle

Dairy cattle are frequently housed in free stalls with limited space, impacting social interactions between individuals. Social behavior in dairy cattle is gaining recognition as a valuable tool for identifying sick animals, but its application is hampered by the complexities of analyzing social interactions in intensive housing systems. In this context, precision livestock technologies present the opportunity to continuously monitor dyadic spatial associations on dairy farms. The aim of this study is to evaluate the accuracy of predicting social behavior of dairy cows using social network analysis. Daily social networks were built using the position data from 149 cows over 14 consecutive days of the study period. We applied the separable temporal exponential random graph models to estimate the likelihood of formation and persistence of social contacts between dairy cows individually and to predict the social network on the subsequent day. The correlation between the individual degree centrality values, the number of established social contacts per individual, between the predicted and observed networks ranged from 0.22 to 0.49 when the structural information from network triangles was included in the model. This study presents a novel approach for predicting animal social behavior in intensive housing systems using spatial association information obtained from a real-time location system. The results indicate the potential of this approach as a crucial step toward the larger goal of identifying disruptions in dairy cows expected social behavior.

A methodological approach to compare continuous and instantaneous sampling and two methods to deal with animals out of sight on dairy cattle behavior and interaction with their calf in the first hours post-partum.

Animal behavior can provide useful information about animal welfare, but methods and tools used to gather behavioral data and data treatment can influence the results. Therefore, this study was carried out on dairy cow (Bos taurus) behavior and interaction with calves early post-partum aiming at comparing two sampling rules, namely continuous and instantaneous sampling at scan intervals of 30 s, 1, 2, 3, 4, 5, and 10 min, and of two methods to deal with out of sight animals. The study was based on three assumptions: (1) continuous sampling provides the most complete and accurate data, allowing the observation of seldom behaviors and short events; (2) instantaneous sampling can provide accurate measurements of frequency and duration, especially at short scan intervals; (3) differences in behavioral results may occur depending on whether a correction for time out of sight is applied or not. Thus, 10 dams were observed from videos in the 2 h post-parturition. Ruminating, stereotypies, calf-biting and calf-butting were not recorded during the observation period. Other behaviors were observed only with continuous sampling or with continuous and instantaneous at 30-s scan intervals. The recoding of several behaviors was less accurate when applying longer scan intervals. Data from continuous and instantaneous sampling at 30-s scan intervals were compared with Wilcoxon test. Results showed no significant differences for posture, position in the pen and all behaviors (p > 0.05) except vocalizing (p = 0.003). The same test did not highlight significant differences due to method of dealing with out of sight for both sampling rules (p > 0.05). Correlation between continuous and instantaneous sampling were prevalently high at 30-s intervals and they decreased as the length of scan intervals increased for most behaviors. Results confirmed the first two assumptions suggesting that continuous sampling is more accurate, in particular for short and rare behaviors, and caution against the suitability of dam behavioral data collected using instantaneous sampling at scan intervals of minutes. The third assumption was not proven by this study. Results should be considered in light of the development of new technologies that relies on data acquired by sensors and imaging to monitor cow-calf welfare and behavior post-parturition.

The Relation between Milk Lactose Concentration and the Rumination, Feeding, and Locomotion Behavior of Early-Lactation Dairy Cows.

This study hypothesizes that higher in-line milk lactose concentrations are indicative of enhanced dairy cow behaviors-including increased rumination, feeding, and locomotion activities-reflecting superior overall health and well-being. It posits that fluctuations in milk lactose levels have a substantial impact on the physiological and behavioral responses of dairy cows, thereby affecting their milk yields and compositions. Each cow's milk lactose, fat, protein, and fat-to-protein ratio were continuously monitored using the BROLIS HerdLine in-line milk analyzer (Brolis Sensor Technology, Vilnius, Lithuania). The RumiWatch noseband sensor (RWS; ITIN + HOCH GmbH, Fütterungstechnik, Liestal, Switzerland) was employed to measure the biomarkers of the rumination, feeding, and locomotion behavior. The measurements were recorded over 5 days at the same time (during morning milking). A total of 502 cows were examined. During these 5 days, 2510 measurements were taken. Based on the lactose content in their milk, the cows were divided into two categories: the first group consisted of cows with milk lactose levels below 4.70%, while the second group included cows with milk lactose levels of 4.70% or higher. Our study showed that cows with higher milk lactose concentrations (≥4.70%) produced significantly more milk (16.14% increase) but had a lower milk protein concentration (5.05% decrease) compared to cows with lower lactose levels. These cows also exhibited changes in rumination and feeding behaviors, as recorded by the RWS: there was an increase in the mastication and rumination behaviors, evidenced by a 14.09% rise in other chews and a 13.84% increase in rumination chews, along with a 16.70% boost in bolus activity. However, there was a notable 16.18% reduction in their physical activity, as measured by the change in time spent walking.

Grazing behavior of dairy cows under contrasting pasture allocation frequencies and areas

This study aimed to compare grazing behavior of dairy cows with highly contrasting pasture allocation frequencies. The study ran from September 9, 2022, to December 2, 2022 (12 wk), during a time when daily pasture growth was expected to exceed daily herd intake. Three pasture allocation frequencies were compared, each with 11 spring-calving cows grazing a 4-ha farmlet. The allocations were high frequency rotational grazing (HFRG; 32.5 m2/cow per allocation and 4 allocations/d), rotational grazing with weekly allocations (7RG; 909 m2/cow per allocation and each allocated area continuously grazed over 7 d), and continuous grazing (CG; 1,818 m2/cow per allocation). Animal behavior was monitored using IceQube accelerometers (Peacock Technology) and CowManager ear tags (Agis Automatisering BV). Milk yield and composition were measured and pasture cover was estimated. Daily eating time was highest for CG animals, whereas lying time, lying bouts, and ruminating time were lowest, with no differences between HFRG and 7RG. There were no differences in fat- and protein-corrected milk yield between farmlets; however, estimated accumulated pasture yield was greater with more frequent allocations. Although milk production did not differ between treatment groups, this appeared to be achieved through greater eating times when allocated pasture less frequently, at the expense of time spent lying.

Machine learning methods for genomic prediction of cow behavioral traits measured by automatic milking systems in North American Holstein cattle

Identifying genome-enabled methods that provide more accurate genomic prediction is crucial when evaluating complex traits such as dairy cow behavior. In this study, we aimed to compare the predictive performance of traditional genomic prediction methods and deep learning algorithms for genomic prediction of milking refusals (MREF) and milking failures (MFAIL) in North American Holstein cows measured by automatic milking systems (milking robots). A total of 1,993,509 daily records from 4,511 genotyped Holstein cows were collected by 36 milking robot stations. After quality control, 57,600 single nucleotide polymorphisms (SNP) were available for the analyses. Four genomic prediction methods were considered: Bayesian Lasso (LASSO), Multiple Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Genomic Best Linear Unbiased Prediction (GBLUP). We implemented the first 3 methods using the Keras and TensorFlow libraries in Python (v.3.9) while the GBLUP method was implemented using the BLUPF90+ family programs. The accuracy of genomic prediction (Mean Square Error) for MREF and MFAIL was 0.34 (0.08) and 0.27 (0.08) based on LASSO, 0.36 (0.09) and 0.32 (0.09) for MLP, 0.37 (0.08) and 0.30 (0.09) for CNN, and 0.35 (0.09) and 0.31(0.09) based on GBLUP, respectively. Additionally, we observed a lower re-ranking of top selected individuals based on the MLP versus CNN methods compared with the other approaches for both MREF and MFAIL. Although the deep learning methods showed slightly higher accuracies than GBLUP, the results may not be sufficient to justify their use over traditional methods due to their higher computational demand and the difficulty of performing genomic prediction for non-genotyped individuals using deep learning procedures. Overall, this study provides insights into the potential feasibility of using deep learning methods to enhance genomic prediction accuracy for behavioral traits in livestock. Further research is needed to determine their practical applicability to large dairy cattle breeding programs.

Effect of monensin and live-cell yeast supplementation on lactation performance, feeding behavior, and total-tract nutrient digestibility in dairy cows

Effect of monensin and live-cell yeast supplementation on lactation performance, feeding behavior, and total-tract nutrient digestibility in dairy cows

Shelter preference and behavior of dairy cows managed outdoors during calving in temperate winter conditions

This study aimed to assess the preference and use of an artificial shelter in dairy cows managed outdoors at calving during winter. We also evaluated whether this preference would be influenced by weather conditions (rain, air temperature, or wind) or the time of the day at calving. Two weeks before their expected calving date, 18 cows were paired based on body weight, body condition score, parity, and expected calving date. Each pair was assigned to an open paddock (42 m2/cow) with a bare soil surface, high mud content, and access to an artificial shelter until calving. The shelter consisted of a 6 × 3 m metal structure, with 3 sides covered with zinc sheets, a polycarbonate roof, and a thick layer of dry sawdust covering the ground surface. Shelter use and cow behavior inside it (lying and sleeping) were continuously recorded via video and analyzed using continuous observation. Observations were divided into 2 periods: the day before calving (24 to 48 h before calving) and the day of calving (24 h before calving until calving). Ninety-four percent (15/16) of the cows preferred to calve inside the artificial shelter, and this preference was not affected by the time of day or weather conditions. Regardless of the day of study (the day before calving or the day of calving), cows spent approximately 64% of their daily time inside the shelter, and once inside, they spent most of the time lying down. Our findings indicate dairy cows prefer using an artificial shelter as a calving and lying place, suggesting that opportunities for protection should be provided when they are managed outdoors in muddy paddock conditions.

Effect of extended heat stress in dairy cows on productive and behavioral traits

This study evaluates the response of dairy cows to short and extended heat stressing conditions (from 1 to 28 days), as expressed in changes in their behavior. Due to climate change, heat stress and strong heat waves are frequently affecting the productivity and behavior of dairy cows. In the five years under study from 2018 to 2022, two were characterized by extremely strong heat waves occurring in the region analyzed in this study (Northern Italy). The dairy cattle farm involved in this study is located in Northern Italy and includes about 1 600 Holstein Friesian lactating dairy cows. Phenotypic data were provided by the Afimilk system and compromised behavioral and productive traits. Behavioral traits analyzed were activity, rest time, rest bouts, rest ratio, rest per bout and restlessness. Production traits were daily milk yield, average milking time, somatic cell count, fat percentage, protein percentage and lactose percentage. Climate data came from the National Aeronautics and Space Administration/Prediction of Worldwide Energy Resources database. Heat stress was analyzed considering Temperature-Humidity Index (THI) averaged over 28 different time windows of continuous heat stress. Results showed that rest time and milk yield were the two traits most affected by the increased THI. Rest time was immediately affected by high THI, showing a marked decrease already from 1d window and maintaining this all over the other windows. Furthermore, results show that rest time and rest ratio were only slightly negatively correlated with milk yield (−0.14 and −0.15). In addition, heat stress has a different effect depending on parity and lactation stages on the studied traits. In conclusion, the results indicate that heat stress increases activity and compromises milk production, rest time and milk quality traits. Results further suggest that rest time can be a better parameter than activity to describe the effects of heat stress on dairy cattle. The novel approach used in this study is based on the use of different time windows (up to 28 days) before the emergence of undesired THI and allows to identify the traits that are immediately influenced by the undesirable THI values and those that are influenced only after a prolonged heat stress period.

Recognition of the behaviors of dairy cows by an improved YOLO

The physiological well-being of dairy cows is intimately tied to their behavior. Detecting aberrant dairy cows early and reducing financial losses on farms are both possible with real-time and reliable monitoring of their behavior. The behavior data of dairy cows in real environments have dense occlusion and multi-scale issues, which affect the detection results of the model. Therefore, we focus on both data processing and model construction to improve the results of dairy cow behavior detection. We use a mixed data augmentation method to provide the model with rich cow behavior features. Simultaneously refining the model to optimize the detection outcomes of dairy cow behavior amidst challenging conditions, such as dense occlusion and varying scales. First, a Res2 backbone was constructed to incorporate multi-scale receptive fields and improve the YOLOv3’s backbone for the multi-scale feature of dairy cow behaviors. In addition, YOLOv3 detectors were optimized to accurately locate individual dairy cows in different dense environments by combining the global location information of images, and the Global Context Predict Head was designed to enhance the performance of recognizing dairy cow behaviors in crowded surroundings. The dairy cow behavior detection model we built has an accuracy of 90.6%, 91.7%, 80.7%, and 98.5% for the four behaviors of dairy cows standing, lying, walking, and mounting, respectively. The average accuracy of dairy cow detection is 90.4%, which is 1.2% and 12.9% higher than the detection results of YOLOV3, YOLO-tiny and other models respectively. In comparison to YOLOv3, the Average Precision evaluation of the model improves by 2.6% and 1.4% for two similar features of walking and standing behaviors, respectively. The recognition results prove that the model generalizes better for recognizing dairy cow behaviors using behavior videos in various scenes with multi-scale and dense environment features.

Alterations in Rumination, Eating, Drinking and Locomotion Behavior in Dairy Cows Affected by Subclinical Ketosis and Subclinical Acidosis

This study delves into the effects of subclinical ketosis (SCK) and subclinical acidosis (SCA) on various parameters related to dairy cow rumination, eating, drinking and locomotion behavior. The research hypothesized that these subclinical metabolic disorders could affect behaviors such as rumination, feeding, and locomotion. A total of 320 dairy cows, with a focus on those in their second or subsequent lactation, producing an average of 12,000 kg/year milk in their previous lactation, were examined. These cows were classified into three groups: those with SCK, those with SCA, and healthy cows. The health status of the cows was determined based on the milk fat–protein ratio, blood beta-hydroxybutyrate, and the results of clinical examinations performed by a veterinarian. The data collected during the study included parameters from the RumiWatch sensors. The results revealed significant differences between the cows affected by SCK and the healthy cows, with reductions observed in the rumination time (17.47%) and various eating and chewing behaviors. These changes indicated that SCK had a substantial impact on the cows’ behavior. In the context of SCA, the study found significant reductions in Eating Time 2 (ET2) of 36.84% when compared to the healthy cows. Additionally, Eating Chews 2 (EC2) exhibited a significant reduction in the SCA group, with an average of 312.06 units (±17.93), compared to the healthy group’s average of 504.20 units (±18.87). These findings emphasize that SCA influences feeding behaviors and chewing activity, which can have implications for nutrient intake and overall cow health. The study also highlights the considerable impact of SCK on locomotion parameters, as the cows with SCK exhibited a 27.36% reduction in the walking time levels. These cows also displayed reductions in the Walking Time (WT), Other Activity Time (OAT), and Activity Change (AC). In conclusion, this research underscores the critical need for advanced strategies to prevent and manage subclinical metabolic disorders within the dairy farming industry. The study findings have far-reaching implications for enhancing the well-being and performance of dairy cattle. Effective management practices and detection methods are essential to mitigate the impact of SCK and SCA on dairy cow health and productivity, ultimately benefiting the dairy farming sector.

Effect of Climatic Condition, Type of Trough and Water Cleanliness on Drinking Behavior in Dairy Cows.

Increasing ambient temperatures lead to higher water intake and higher risks of microbial growth in cattle troughs. This study aims to analyze drinking water quality and dairy cows' drinking behavior (n = 8081 drinking episodes) on a commercial farm with 135 and 144 lactating cows in two climatic conditions, considering trough type and cleanliness, respectively. Daily video recording was conducted at two trough types (two open troughs, 70 L; two-valve troughs, variable volume of 5-15 L) in the first two hours after feeding (n = 60 days in total) under cold (December 2019-February 2020) and warm ambient temperatures (September 2021). The trough cleaning scheme allowed cows to access either cleaned or uncleaned troughs in each system. Water quality was tested daily and analyzed at the beginning and end of the trials. In warmer ambient temperatures, fewer and-at uncleaned troughs and open troughs-shorter drinking episodes were recorded, with longer but fewer water intake periods, longer drinking breaks, and fewer sips (p < 0.0001). Considering the drinking episodes, respectively, water intake and drinking breaks in number and duration, the number of sips and the number of agonistic behaviors might optimize dairy cow water supply and hygiene management.

Comparative Analysis of Milking and Behavior Characteristics of Multiparous and Primiparous Cows in Robotic Systems.

Robotic milking systems are successful innovations in the development of dairy cattle. The objective of this study was to analyse the milking characteristics and behavior of dairy cows of different calving orders in "milk first" robotic milking systems. The data were collected from a commercial herd located in the Midwest region of Minas Gerais (Brazil), which uses an automatic milking system (AMS TM, DeLaval). Were analysed 26,574 observations of 235 Holstein cows were available. Data were evaluated by multivariate analysis of variance and the Tukey test. - Tthe characteristics milk flow and milking efficiency were more favourable for multiparous cows (p <0.01), while the time in the stall was more favourable for primiparous females (p <0.01). The values of handling time were better in the primiparous cows (p <0.01). Primiparous cows had higher amounts of kick-off (p <0.001), and multiparous cows had higher incomplete milkings (p <0.001). The number of incomplete milkings showed a higher ratio in terms of reduction in milk production in 26.6% in primiparous cows and 26.7% in multiparous cows (p <0.01). Regarding the behavioral characteristics, primiparous cows had higher amounts of kickbacks, while multiparous cows had greater quantities of incomplete milkings.

Effect of Temperature Humidity Index (THI) on resting pattern of dairy cows in different regions of Sri Lanka.

The ability to spend time resting is extremely important for dairy cattle welfare. Through this study, lying behaviour of dairy cows in to Up-Country (UP), Mid-Country (MC), Coconut-Triangle (CT) and Western-Province (WP) of Sri Lanka was studied to get an insight into their resting pattern. Resting pattern was assessed in 170 Holstein-Friesian/ Jersey crossed, tie-stalled lactating cows (UP = 49, MC = 49, CT = 48 and WP = 24) using electronic data loggers. Appropriate resting behaviours were attained in UP and MC regions, with longer lying time (11.7, 11.3 h/day) and lying bout durations (78.0, 84.9 min) respectively, where lower THI ranges were observed compared to other regions. WP and CT resulted with lower lying times (9.00, 9.26 h/day) and lying bout durations (48.3, 64.3 min) respectively with higher THI. There is a slight variation of the environmental temperature of each region with the time period of experiment. Cows in all regions prefer to lie on their left side (UP-6.1, MC-6.1, CT-4.4, WP-4.7 h/d) and with significant differences (P<0.05) between MC-WP, MC-CT, UP-CT and UP-WP. A negative significant (P<0.05) correlation was observed between THI and lying behaviours. There were significant effects of time (hour) and time × region interaction (P<0.05) on the lying down pattern. More lying down was observed in late night and early morning with a peak rest around the hours of 21:00-05:00. Overall, according to the results of the current study, the existing environmental conditions of four regions affected the resting pattern of dairy cows and, identification of possible mechanisms to modify the environment to enhance cow comfort is vital.

Estimation of genetic parameters and single-step genome-wide association studies for eating time and rumination time in Holstein dairy cows

The aims of this study were to estimate genetic parameters and to identify genomic regions associated with eating time (ET) and rumination time (RUT) in Holstein dairy cows. Genetic correlations among ET, RUT, and milk yield traits were also estimated. The data were collected from 2019 to 2022 in 6 dairy herds located in the Walloon Region of Belgium. The dataset consisted of daily ET and RUT records on 284 Holstein cows, from which 41 cows had records only for the first parity (P1), 101 cows had records from both the first and second parities, and 142 cows had records only for the second parity (P2). The number of daily ET and RUT records in the P1 and P2 cows were 18,569 (on 142 cows) and 34,464 (on 243 cows), respectively. Data on 28,994 SNPs located on 29 Bos taurus autosomes (BTA) of 747 animals (435 males) were used. Random regression test-day models were used to estimate genetic parameters through the Bayesian Gibbs sampling method. The SNP solutions were estimated using a single-step genomic best linear unbiased prediction approach. The proportion of genetic variance explained by each 20-SNP sliding window (with an average size of 1.52 Mb) was calculated, and regions accounting for at least 1.0% of the total additive genetic variance were used to search for candidate genes. Mean (standard deviation; SD) averaged daily ET and RUT were 327.0 (85.66) and 559.4 (77.69) min/d for cows in P1 and 316.0 (82.24) and 574.2 (75.42) min/d for cows in P2, respectively. Mean (standard deviation; SD) heritability estimates for daily ET and RUT were 0.42 (0.09) and 0.45 (0.06) for cows in P1 and 0.45 (0.04) and 0.43 (0.02) for cows in P2, respectively. Mean (SD) daily genetic correlations between daily ET and RUT were 0.27 (0.07) for P1 and 0.34 (0.08) for P2. Genome-wide association analyses identified 6 genomic regions distributed over 5 chromosomes (BTA1, BTA4, BTA11, 2 regions of BTA14, and BTA17) associated with ET or RUT. The findings of this study increase our preliminary understanding of the genetic background of feeding behavior in dairy cows; however, larger datasets are needed to determine whether ET and RUT might have the potential to be used in selection programs.

X3DFast model for classifying dairy cow behaviors based on a two-pathway architecture

Behavior is one of the important factors reflecting the health status of dairy cows, and when dairy cows encounter health problems, they exhibit different behavioral characteristics. Therefore, identifying dairy cow behavior not only helps in assessing their physiological health and disease treatment but also improves cow welfare, which is very important for the development of animal husbandry. The method of relying on human eyes to observe the behavior of dairy cows has problems such as high labor costs, high labor intensity, and high fatigue rates. Therefore, it is necessary to explore more effective technical means to identify cow behaviors more quickly and accurately and improve the intelligence level of dairy cow farming. Automatic recognition of dairy cow behavior has become a key technology for diagnosing dairy cow diseases, improving farm economic benefits and reducing animal elimination rates. Recently, deep learning for automated dairy cow behavior identification has become a research focus. However, in complex farming environments, dairy cow behaviors are characterized by multiscale features due to large scenes and long data collection distances. Traditional behavior recognition models cannot accurately recognize similar behavior features of dairy cows, such as those with similar visual characteristics, i.e., standing and walking. The behavior recognition method based on 3D convolution solves the problem of small visual feature differences in behavior recognition. However, due to the large number of model parameters, long inference time, and simple data background, it cannot meet the demand for real-time recognition of dairy cow behaviors in complex breeding environments. To address this, we developed an effective yet lightweight model for fast and accurate dairy cow behavior feature learning from video data. We focused on four common behaviors: standing, walking, lying, and mounting. We recorded videos of dairy cow behaviors at a dairy farm containing over one hundred cows using surveillance cameras. A robust model was built using a complex background dataset. We proposed a two-pathway X3DFast model based on spatiotemporal behavior features. The X3D and fast pathways were laterally connected to integrate spatial and temporal features. The X3D pathway extracted spatial features. The fast pathway with R(2 + 1)D convolution decomposed spatiotemporal features and transferred effective spatial features to the X3D pathway. An action model further enhanced X3D spatial modeling. Experiments showed that X3DFast achieved 98.49% top-1 accuracy, outperforming similar methods in identifying the four behaviors. The method we proposed can effectively identify similar dairy cow behaviors while improving inference speed, providing technical support for subsequent dairy cow behavior recognition and daily behavior statistics.

The effect of prepartum synthetic zeolite supplementation on the eating, lying and activity behaviours of grazing dairy cows

ABSTRACT This study determined the effect of feeding synthetic zeolite A prepartum to reduce periparturient hypocalcaemia risk on the eating, lying, and activity behaviours of multiparous grazing dairy cows. Animals were randomly allocated to either a Zeolite treatment group (n = 21; individually fed 500 g/d zeolite for two weeks prepartum) or a Control group (n = 22). Behaviour data obtained from accelerometers were analysed to determine the effects of treatment, parity (Parity 2−3 vs. 4+), and their interactions during 3 periods: PRE (−21 to −3 d), PERI (−2–2 d) and POST (3–28 d) relative to the day of calving (day 0). Parity 2–3 Zeolite cows ate for 18 min/day less than Parity 2–3 Control cows PRE. Zeolite-fed cows also ate for 24 min/day less than Control cows during the PERI period. There were no treatment differences in lying time or activity PRE or PERI, but Zeolite-fed cows spent more time lying POST. Regardless of treatment, Parity 2–3 cows were generally more active and ate for longer than Parity 4 + cows. Our results suggest zeolite may subtly decrease appetite or alter eating behaviour during the supplementation period, particularly in younger cows, and may improve cow comfort postcalving.

A note on dairy cow behavior when measuring enteric methane emissions with the GreenFeed emission monitoring system in tiestalls

Changes in the environment or novel procedures can result in altered cow behavior during data collection; training is often recommended to ensure accurate data is being recorded. Currently, little is known regarding the habituation of dairy cows during methane emission testing with the GreenFeed emission monitoring system (C-Lock Inc., Rapid City, SD), or how behavior relates to enteric methane emission measurements. Methane emissions were estimated from a total of 202 Holstein dairy cows (120–150 d in milk) housed in tiestalls as part of a larger project. Cows were tested on d 0 (training day) and d 1–5 (test day) for approximately 10 min, during which behavior was recorded by a trained observer. While cows spent more time with their head outside of the machine on the training day (d 0) than during the test days (d 1–5), the opposite pattern was observed for the number of leg movements. No differences in estimated methane production were found over the different days, though it was negatively correlated with both behaviors. These results highlight the importance of habituation of dairy cows to the GreenFeed system for methane measurements to minimize changes to cow behavior under tiestall conditions, whereas the methane emissions themselves are less affected. However, further research is needed to determine the impact of cow behavior on the reliability and repeatability of methane emission measurements as it may introduce bias in genetic evaluations for methane efficiency.

Daylong acoustic recordings of grazing and rumination activities in dairy cows

Monitoring livestock feeding behavior may help assess animal welfare and nutritional status, and to optimize pasture management. The need for continuous and sustained monitoring requires the use of automatic techniques based on the acquisition and analysis of sensor data. This work describes an open dataset of acoustic recordings of the foraging behavior of dairy cows. The dataset includes 708 h of daily records obtained using unobtrusive and non-invasive instrumentation mounted on five lactating multiparous Holstein cows continuously monitored for six non-consecutive days in pasture and barn. Labeled recordings precisely delimiting grazing and rumination bouts are provided for a total of 392 h and for over 6,200 ingestive and rumination jaw movements. Companion information on the audio recording quality and expert-generated labels is also provided to facilitate data interpretation and analysis. This comprehensive dataset is a useful resource for studies aimed at exploring new tools and solutions for precision livestock farming.

On-farm assessment of grazing behaviour of dairy cows in two pasture management systems by low-cost and reliable cowtrackers

In dairy farming, sensors are commonly applied to monitor animal health and performance. One key task of such sensors is the behaviour classification of cows. The behaviour classification needs to take into account the differences between stable and pasture: the process of feed intake by grazing is different from feed intake in the stable. Pasture management systems differ and this introduces further variability within pasture-based systems, e.g. by different sward heights. Moreover, on pasture, spatial variables like walking distance allow the inference of further information about cow behaviour. Therefore, data accessibility and customizability of sensors is important for the development of pasture specific behaviour classification algorithms. Our objective was to construct an open-source and neck located cowtracker that combines an accelerometer, gyroscope and global navigation satellite system sensors with an Arduino microcontroller. The blueprints of the cowtracker are provided in the manuscript. Cows were tracked on two commercial dairy farms with different breeds and in different grazing systems to ensure high variability of the data. Animal behaviour was classified by training a random forest algorithm that was used to predict animal behaviour from the sensor data. The training data was obtained from visual observations in the field and differentiating between the behaviours grazing, rumination, walking, resting and drinking. The overall accuracy was 0.94 when predicting test data consisting of data retained randomly from all individuals. The predictive performance slightly decreased to 0.89 overall accuracy when whole animal data sets were retained as test data. The decrease in predictive performance was stronger for the rarely observed behaviour drinking. As a showcase, cow behaviour was analysed and differed between the two grazing systems. In continuous grazing at low sward heights (6 cm) the cows allocated more time to grazing and walking whereas in rotational grazing with pre- and post-grazing sward heights of 11.3 cm and 6.3 cm respectively, the cows allocated more time to rumination and less to grazing. The observed grazing time was comparably short in this experiment. The spatial observations revealed longer walking distances and higher herd scatter in continuous grazing which reflects the greater effort in satisfying the feed demand in low swards.

Recognition and statistical method of cows rumination and eating behaviors based on Tensorflow.js

Information about dairy cow ruminating is closely associated with the health status of dairy cows. Therefore, it is of great significance to recognize and make statistics of dairy cows’ ruminating and feeding behavior. Concerning conventional recognition methods which are dependent on contact type devices, they have some defects of poor instantaneity and strong stress responses. As for recognition based on machine vision, it needs to transmit masses of data and raises high requirements for the cloud server and network performance. According to principles of edge computing, the model is deployed via Tensorflow.js in an edge device in the present study, constructing a recognition and statistical system for ruminating and feeding behavior of dairy cows. Through the application programming interface (API) of the browser, an edge device is able to invoke a camera and acquire dairy cow images. Then, the images can be inputted in the SSD MobileNet V2 model, which is followed by inference based on browser hashrate. Moreover, the edge device merely uploads recognition results to the cloud server for statistics, which features high instantaneity and compatibility. In terms of recognizing ruminating and feeding behavior of dairy cows, the proposed system has a precision ratio of 96.50%, a recall rate of 91.77%, an F1-score of 94.08%, specificity of 91.36%, and accuracy of 91.66%. This suggests that the proposed method is effective in recognizing dairy cow behavior.