Automatic classification system for grazing, ruminating and resting behaviour of dairy sheep using a tri-axial accelerometer

Monitoring Cattle Ruminating Behavior Based on an Improved Keypoint Detection Model

Cattle rumination behavior is strongly correlated with its health. Current methods often rely on manual observation or wearable devices to monitor ruminating behavior. However, the manual monitoring of cattle rumination is labor-intensive, and wearable devices often harm animals. Therefore, this study proposes a non-contact method for monitoring cattle rumination behavior, utilizing an improved YOLOv8-pose keypoint detection algorithm combined with multi-condition threshold peak detection to automatically identify chewing counts. First, we tracked and recorded the cattle's rumination behavior to build a dataset. Next, we used the improved model to capture keypoint information on the cattle. By constructing the rumination motion curve from the keypoint information and applying multi-condition threshold peak detection, we counted the chewing instances. Finally, we designed a comprehensive cattle rumination detection framework to track various rumination indicators, including chewing counts, rumination duration, and chewing frequency. In keypoint detection, our modified YOLOv8-pose achieved a 96% mAP, an improvement of 2.8%, with precision and recall increasing by 4.5% and 4.2%, enabling the more accurate capture of keypoint information. For rumination analysis, we tested ten video clips and compared the results with actual data. The experimental results showed an average chewing count error of 5.6% and a standard error of 2.23%, verifying the feasibility and effectiveness of using keypoint detection technology to analyze cattle rumination behavior. These physiological indicators of rumination behavior allow for the quicker detection of abnormalities in cattle's rumination activities, helping managers make informed decisions. Ultimately, the proposed method not only accurately monitors cattle rumination behavior but also provides technical support for precision management in animal husbandry, promoting the development of modern livestock farming.

Application of Precision Technologies to Characterize Animal Behavior: A Review

This study aims to evaluate the state of precision livestock farming (PLF)'s spread, utilization, effectiveness, and evolution over the years. PLF includes a plethora of tools, which can aid in a number of laborious and complex tasks. These tools are often used in the monitoring of different animals, with the objective to increase production and improve animal welfare. The most frequently monitored attributes tend to be behavior, welfare, and social interaction. This study focused on the application of three types of technology: wearable sensors, video observation, and smartphones. For the wearable devices, the focus was on accelerometers and global positioning systems. For the video observation, the study addressed drones and cameras. The animals monitored by these tools were the most common ruminants, which are cattle, sheep, and goats. This review involved 108 articles that were believed to be pertinent. Most of the studied papers were very accurate, for most tools, when utilized appropriate; some showed great benefits and potential.

Genetic parameters of behavior traits of beef cattle classified using wearable devices

With the development of wearable devices, it is now possible to monitor livestock behavior 24 h a day. In this study, we estimated the genetic parameters of the daily duration of six behaviors (feeding, moving, lying, standing, ruminating while lying, and ruminating while standing) in beef cattle, automatically classified using wearable devices. The devices were attached to 332 Japanese beef cattle at two stations for approximately 5 months. We compared repeatability, Poisson regression, and random regression models using the deviance information criterion. Poisson regression models were selected for all traits at each station, probably because of the non-normal distribution of the phenotypes. The heritability estimates by the Poisson regression models were moderate at each station: 0.67 and 0.68 for feeding, 0.68 and 0.53 for moving, 0.47 and 0.55 for lying, 0.45 and 0.40 for standing, 0.51 and 0.59 for ruminating while lying, and 0.37 and 0.45 for ruminating while standing. The genetic correlations between these traits were all negative at both stations, whereas the residual correlations showed different directions depending on the station. Although validation studies with larger populations are needed to confirm these findings, this study provides fundamental knowledge of the genetic basis of daily behavior in beef cattle.

Classifying Chewing and Rumination in Dairy Cows Using Sound Signals and Machine Learning

This research paper introduces a novel methodology for classifying jaw movements in dairy cattle into four distinct categories: bites, exclusive chews, chew-bite combinations, and exclusive sorting, under conditions of tall and short particle sizes in wheat straw and Alfalfa hay feeding. Sound signals were recorded and transformed into images using a short-time Fourier transform. A total of 31 texture features were extracted using the gray level co-occurrence matrix, spatial gray level dependence method, gray level run length method, and gray level difference method. Genetic Algorithm (GA) was applied to the data to select the most important features. Six distinct classifiers were employed to classify the jaw movements. The total precision found was 91.62%, 94.48%, 95.9%, 92.8%, 94.18%, and 89.62% for Naive Bayes, k-nearest neighbor, support vector machine, decision tree, multi-layer perceptron, and k-means clustering, respectively. The results of this study provide valuable insights into the nutritional behavior and dietary patterns of dairy cattle. The understanding of how cows consume different types of feed and the identification of any potential health issues or deficiencies in their diets are enhanced by the accurate classification of jaw movements. This information can be used to improve feeding practices, reduce waste, and ensure the well-being and productivity of the cows. The methodology introduced in this study can serve as a valuable tool for livestock managers to evaluate the nutrition of their dairy cattle and make informed decisions about their feeding practices.

Precision technologies for the management of reproduction in dairy cows

Precision livestock farming (PLF) utilizes information and communication technology (ICT) to continuously monitor, control, and enhance the productivity, reproduction, health, welfare, and environmental impact of livestock. Technological advancements have facilitated the seamless flow of information from animals to humans, enabling practical decision-making processes concerning health, reproduction management, and calving surveillance. With the increasing population of livestock per farm, it has become impractical for farmers to individually track every animal within these large groups. Historically, cattle management decisions heavily relied on human observation, judgment, and experience. However, it is impossible for a single individual to gather reliable audio-visual monitoring data round the clock. Presently, dairy cows exhibit subtler indicators of estrus, resulting in a substantial chance of missing an estrus cycle. Furthermore, calving complications sometimes go unnoticed on farms, resulting in a higher number of culled cattle. In addition, an increasing number of crossbred cows experience delayed return to estrus after calving due to low body condition scores (BCS). The decline in BCS during the dry period is associated with a reduced likelihood of pregnancy following the first and second postpartum inseminations. Precision technologies enable the monitoring and tracking of an individual cow's physiological behavior and reproductive parameters, thereby optimizing management practices and farm performance. Despite the exploration of various technologies, there are still some common challenges that need to be addressed, including battery lifespan, transmission range, specificity and sensitivity, storage capacity, and economic affordability. Nonetheless, the demand for these tools from farmers and researchers is growing, and the implementation of PLF in grazing systems can yield positive outcomes in terms of animal reproductive welfare and labor optimization. This review primarily focuses on the different aspects of reproduction management in dairy using sensors, automated cameras, and various computer software.

Research on Six-Axis Sensor-Based Step-Counting Algorithm for Grazing Sheep

Step counting is an effective method to assess the activity level of grazing sheep. However, existing step-counting algorithms have limited adaptability to sheep walking patterns and fail to eliminate false step counts caused by abnormal behaviors. Therefore, this study proposed a step-counting algorithm based on behavior classification designed explicitly for grazing sheep. The algorithm utilized regional peak detection and peak-to-valley difference detection to identify running and leg-shaking behaviors in sheep. It distinguished leg shaking from brisk walking behaviors through variance feature analysis. Based on the recognition results, different step-counting strategies were employed. When running behavior was detected, the algorithm divided the sampling window by the baseline step frequency and multiplied it by a scaling factor to accurately calculate the number of steps for running. No step counting was performed for leg-shaking behavior. For other behaviors, such as slow and brisk walking, a window peak detection algorithm was used for step counting. Experimental results demonstrate a significant improvement in the accuracy of the proposed algorithm compared to the peak detection-based method. In addition, the experimental results demonstrated that the average calculation error of the proposed algorithm in this study was 6.244%, while the average error of the peak detection-based step-counting algorithm was 17.556%. This indicates a significant improvement in the accuracy of the proposed algorithm compared to the peak detection method.

Exploring 'Wether' Grazing Patterns Differed in Native or Introduced Pastures in the Monaro Region of Australia

Monitoring livestock allows insights to graziers on valuable information such as spatial distribution, foraging patterns, and animal behavior, which can significantly improve the management of livestock for optimal production. This study aimed to understand what potential variables are significant for predicting where sheep spent the most time in native (NP) and improved (IP) paddocks. Wethers (castrated male sheep) were tracked using Global Positioning System (GPS) collars on 15 sheep in the IP and 15 in the NP, respectively, on a property located in the Monaro region of Southern New South Wales, Australia. Trials were performed over four six-day periods in April, July, and November of 2014 and March in 2015. Data were analyzed to understand various trends that may have occurred during different seasons, using random forest models (RFMs). Of the factors investigated, Normalized Difference Vegetation Index (NDVI) was significant (p < 0.01) and highly important for wethers in the IP, but not the NP, suggesting that quality of pasture was key for wethers in the IP. Elevation, temperature, and near distance to trees were important and significant for predicting residency of wethers in the IP, as well as the NP. The result of this study highlights the ability of predictive models to provide insights on behavior-based modelling of GPS data and further enhance current knowledge about location-based choices of sheep on paddocks.

On the Development of a Wearable Animal Monitor

Animal monitoring is a task traditionally performed by pastoralists, as a way of ensuring the safety and well-being of animals; a tremendously arduous and lonely task, it requires long walks and extended periods of contact with the animals. The Internet of Things and the possibility of applying sensors to different kinds of devices, in particular the use of wearable sensors, has proven not only to be less invasive to the animals, but also to have a low cost and to be quite efficient. The present work analyses the most impactful monitored features in the behavior learning process and their learning results. It especially addresses the impact of a gyroscope, which heavily influences the cost of the collar. Based on the chosen set of sensors, a learning model is subsequently established, and the learning outcomes are analyzed. Finally, the animal behavior prediction capability of the learning model (which was based on the sensed data of adult animals) is additionally subjected and evaluated in a scenario featuring younger animals. Results suggest that not only is it possible to accurately classify these behaviors (with a balanced accuracy around 91%), but that removing the gyroscope can be advantageous. Results additionally show a positive contribution of the thermometer in behavior identification but evidences the need for further confirmation in future work, considering different seasons of different years and scenarios including more diverse animals' behavior.

Behavioral Fingerprinting: Acceleration Sensors for Identifying Changes in Livestock Health

During disease or toxin challenges, the behavioral activities of grazing animals alter in response to adverse situations, potentially providing an indicator of their welfare status. Behavioral changes such as feeding behavior, rumination and physical behavior as well as expressive behavior, can serve as indicators of animal health and welfare. Sometimes behavioral changes are subtle and occur gradually, often missed by infrequent visual monitoring until the condition becomes acute. There is growing popularity in the use of sensors for monitoring animal health. Acceleration sensors have been designed to attach to ears, jaws, noses, collars and legs to detect the behavioral changes of cattle and sheep. So far, some automated acceleration sensors with high accuracies have been found to have the capacity to remotely monitor the behavioral patterns of cattle and sheep. These acceleration sensors have the potential to identify behavioral patterns of farm animals for monitoring changes in behavior which can indicate a deterioration in health. Here, we review the current automated accelerometer systems and the evidence they can detect behavioral patterns of animals for the application of potential directions and future solutions for automatically monitoring and the early detection of health concerns in grazing animals.

The livestock farming digital transformation: implementation of new and emerging technologies using artificial intelligence

Livestock welfare assessment helps monitor animal health status to maintain productivity, identify injuries and stress, and avoid deterioration. It has also become an important marketing strategy since it increases consumer pressure for a more humane transformation in animal treatment. Common visual welfare practices by professionals and veterinarians may be subjective and cost-prohibitive, requiring trained personnel. Recent advances in remote sensing, computer vision, and artificial intelligence (AI) have helped developing new and emerging technologies for livestock biometrics to extract key physiological parameters associated with animal welfare. This review discusses the livestock farming digital transformation by describing (i) biometric techniques for health and welfare assessment, (ii) livestock identification for traceability and (iii) machine and deep learning application in livestock to address complex problems. This review also includes a critical assessment of these topics and research done so far, proposing future steps for the deployment of AI models in commercial farms. Most studies focused on model development without applications or deployment for the industry. Furthermore, reported biometric methods, accuracy, and machine learning approaches presented some inconsistencies that hinder validation. Therefore, it is required to develop more efficient, non-contact and reliable methods based on AI to assess livestock health, welfare, and productivity.

Industry 4.0 and Precision Livestock Farming (PLF): An up to Date Overview across Animal Productions

Precision livestock farming (PLF) has spread to various countries worldwide since its inception in 2003, though it has yet to be widely adopted. Additionally, the advent of Industry 4.0 and the Internet of Things (IoT) have enabled a continued advancement and development of PLF. This modern technological approach to animal farming and production encompasses ethical, economic and logistical aspects. The aim of this review is to provide an overview of PLF and Industry 4.0, to identify current applications of this rather novel approach in different farming systems for food producing animals, and to present up to date knowledge on the subject. Current scientific literature regarding the spread and application of PLF and IoT shows how efficient farm animal management systems are destined to become. Everyday farming practices (feeding and production performance) coupled with continuous and real-time monitoring of animal parameters can have significant impacts on welfare and health assessment, which are current themes of public interest. In the context of feeding a rising global population, the agri-food industry and industry 4.0 technologies may represent key features for successful and sustainable development.

Recognition of Cattle's Feeding Behaviors Using Noseband Pressure Sensor With Machine Learning

Automatic monitoring of feeding behavior especially rumination and eating in cattle is important to keep track of animal health and growth condition and disease warnings. The noseband pressure sensor is not only able to accurately sense the pressure change of the cattle's jaw movements, which can directly reflect the cattle's chewing behavior, but also has strong resistance to interference. However, it is difficult to keep the same initial pressure while wearing the pressure sensor, and this will pose a challenge to process the feeding behavior data. This article proposed a machine learning approach aiming at eliminating the influence of initial pressure on the identification of rumination and eating behaviors. The method mainly used the local slope to obtain the local data variation and combined Fast Fourier Transform (FFT) to extract the frequency-domain features. Extreme Gradient Boosting Algorithm (XGB) was performed to classify the features of rumination and eating behaviors. Experimental results showed that the local slope in combination with frequency-domain features achieved an F1 score of 0.96, and recognition accuracy of 0.966 in both rumination and eating behaviors. Combined with the commonly used data processing algorithms and time-domain feature extraction method, the proposed approach improved the behavior recognition accuracy. This work will contribute to the standardized application and promotion of the noseband pressure sensors.

What Are Sheep Doing? Tri-Axial Accelerometer Sensor Data Identify the Diel Activity Pattern of Ewe Lambs on Pasture

Monitoring activity patterns of animals offers the opportunity to assess individual health and welfare in support of precision livestock farming. The purpose of this study was to use a triaxial accelerometer sensor to determine the diel activity of sheep on pasture. Six Perendale ewe lambs, each fitted with a neck collar mounting a triaxial accelerometer, were filmed during targeted periods of sheep activities: grazing, lying, walking, and standing. The corresponding acceleration data were fitted using a Random Forest algorithm to classify activity (=classifier). This classifier was then applied to accelerometer data from an additional 10 ewe lambs to determine their activity budgets. Each of these was fitted with a neck collar mounting an accelerometer as well as two additional accelerometers placed on a head halter and a body harness over the shoulders of the animal. These were monitored continuously for three days. A classification accuracy of 89.6% was achieved for the grazing, walking and resting activities (i.e., a new class combining lying and standing activity). Triaxial accelerometer data showed that sheep spent 64% (95% CI 55% to 74%) of daylight time grazing, with grazing at night reduced to 14% (95% CI 8% to 20%). Similar activity budgets were achieved from the halter mounted sensors, but not those on a body harness. These results are consistent with previous studies directly observing daily activity of pasture-based sheep and can be applied in a variety of contexts to investigate animal health and welfare metrics e.g., to better understand the impact that young sheep can suffer when carrying even modest burdens of parasitic nematodes.

SheepIT, an E-Shepherd System for Weed Control in Vineyards: Experimental Results and Lessons Learned

Simple Summary

Animal-based weeding in vineyards is an ecological approach that cannot be implemented throughout the year, since animals are a threat to the fruits and lower branches of the vines. The SheepIT project addressed the challenge of monitoring and conditioning sheep posture by an autonomous collar. By modifying sheep behaviours, SheepIT collars allows them to be used as a vineyard weeding method. Pilot-test results showed that most animals can be conditioned using a proper combination of stimuli. As such, they interrupt their posture after audio cues. Additionally, some sheep could not be conditioned. The progression of the stimuli counters over the test days showed that the number of audio cues was higher than the number of electrostatic stimuli, proving the principle of the conditioning process, although oscillations associated with animal activity were found. The animal-conditioning analysis, and the results of the blood samples, showed that sheep bearing a collar did not face any additional stress. Additionally, the leaf-count process and the analysis of phenological evolution show that the animal’s presence did not spoil the vine’s development.

Abstract

Weed control in vineyards demands regular interventions that currently consist of the use of machinery, such as plows and brush-cutters, and the application of herbicides. These methods have several drawbacks, including cost, chemical pollution, and the emission of greenhouse gases. The use of animals to weed vineyards, usually ovines, is an ancestral, environmentally friendly, and sustainable practice that was abandoned because of the scarcity and cost of shepherds, which were essential for preventing animals from damaging the vines and grapes. The SheepIT project was developed to automate the role of human shepherds, by monitoring and conditioning the behaviour of grazing animals. Additionally, the data collected in real-time can be used for improving the efficiency of the whole process, e.g., by detecting abnormal situations such as health conditions or attacks and manage the weeding areas. This paper presents a comprehensive set of field-test results, obtained with the SheepIT infrastructure, addressing several dimensions, from the animals’ well-being and their impact on the cultures, to technical aspects, such as system autonomy. The results show that the core objectives of the project have been attained and that it is feasible to use this system, at an industrial scale, in vineyards.

What, how, and how much do herbivores eat? The Continuous Bite Monitoring method for assessing forage intake of grazing animals

Determining herbage intake is pivotal for studies on grazing ecology. Direct observation of animals allows describing the interactions of animals with the pastoral environment along the complex grazing process. The objectives of the study were to evaluate the reliability of the continuous bite monitoring (CBM) method in determining herbage intake in grazing sheep compared to the standard double-weighing technique method during 45-min feeding bouts; evaluate the degree of agreement between the two techniques; and to test the effect of different potential sources of variation on the reliability of the CBM. The CBM method has been used to describe the intake behavior of grazing herbivores. In this study, we evaluated a new approach to this method, that is, whether it is a good proxy for determining the intake of grazing animals. Three experiments with grazing sheep were carried out in which we tested for different sources of variations, such as the number of observers, level of detail of bite coding grid, forage species, forage allowance, sward surface height heterogeneity, experiment site, and animal weight, to determine the short-term intake rate (45 min). Observer (Pexp1  = 0.018, Pexp2  = 0.078, and Pexp3  = 0.006), sward surface height (Pexp2  < 0.001), total number of bites observed per grazing session (Pexp2  < 0.001 and Pexp3  < 0.001), and sward depletion (Pexp3  < 0.001) were found to affect the absolute error of intake estimation. The results showed a high correlation and agreement between the two methods in the three experiments, although intake was overestimation by CBM on experiments 2 and 3 (181.38 and 214.24 units, respectively). This outcome indicates the potential of CBM to determining forage intake with the benefit of a greater level of detail on foraging patterns and components of the diet. Furthermore, direct observation is not invasive nor disrupts natural animal behavior.

Classification of broiler behaviours using triaxial accelerometer and machine learning

Understanding broiler behaviours provides important implications for animal well-being and farm management. The objectives of this study were to classify specific broiler behaviours by analysing data from wearable accelerometers using two machine learning models, K-Nearest Neighbour (KNN) and Support Vector Machine (SVM). Lightweight triaxial accelerometers were used to record accelerations of nine 7-week-old broilers at a sampling frequency of 40 Hz. A total of 261.6-min data were labelled for four behaviours - walking, resting, feeding and drinking. Instantaneous motion features including magnitude area, vector magnitude, movement variation, energy, and entropy were extracted and stored in a dataset which was then segmented by one of the six window lengths (1, 3, 5, 7, 10 and 20 s) with 50% overlap between consecutive windows. The mean, variation, SD, minimum and maximum of each instantaneous motion feature and two-way correlations of acceleration data were calculated within each window, yielding a total of 43 statistic features for training and testing of machine learning models. Performance of the models was evaluated using pure behaviour datasets (single behaviour type per dataset) and continuous behaviour datasets (continuous recording that involved multiple behaviour types per dataset). For pure behaviour datasets, both KNN and SVM models showed high sensitivities in classifying broiler resting (87% and 85%, respectively) and walking (99% and 99%, respectively). The accuracies of SVM were higher than KNN in differentiating feeding (88% and 75%, respectively) and drinking (83% and 62%, respectively) behaviours. Sliding window with 1-s length yielded the best performance for classifying continuous behaviour datasets. The performance of classification model generally improved as more birds were included for training. In conclusion, classification of specific broiler behaviours can be achieved by recording bird triaxial accelerations and analysing acceleration data through machine learning. Performances of different machine learning models differ in classifying specific broiler behaviours.

Quantifying the frequency and volume of urine deposition by grazing sheep using tri-axial accelerometers

Urine patches deposited in pasture by grazing animals are sites of reactive nitrogen (N) loss to the environment due to high concentrations of N exceeding pasture uptake requirements. In order to upscale N losses from the urine patch, several urination parameters are required, including where, when and how often urination events occur as well as the volume and chemical composition. There are limited data available in this respect, especially for sheep. Here, we seek to address this knowledge gap by using non-invasive sensor-based technology (accelerometers) on ewes grazing in situ, using a Boolean algorithm to detect urination events in the accelerometer signal. We conducted an initial study with penned Welsh Mountain ewes (n = 5), with accelerometers attached to the hind, to derive urine flow rate and to determine whether urine volume could be estimated from ewe squat time. Then accelerometers attached to the hind of Welsh Mountain ewes (n = 30 at each site) were used to investigate the frequency of sheep urination events (n = 35 946) whilst grazing two extensively managed upland pastures (semi-improved and unimproved) across two seasons (spring and autumn) at each site (35-40 days each). Sheep urinated at a frequency of 10.2 ± 0.2 and 8.1 ± 0.3 times per day in the spring and autumn, respectively, while grazing the semi-improved pasture. Urination frequency was greater (19.0 ± 0.4 and 15.3 ± 0.3 times per day in the spring and autumn, respectively) in the unimproved pasture. Ewe squat duration could be reliably used to predict the volume of urine deposited per event and was thus used to estimate mean daily urine production volumes. Sheep urinated at a rate of 16.6 mL/s and, across the entire dataset, sheep squatted for an average of 9.62 ± 0.03 s per squatting event, producing an estimated average individual urine event volume of 159 ± 1 mL (n = 35 946 events), ranging between 17 and 745 mL (for squat durations of 1 to 45 s). The estimated mean daily urine volume was 2.15 ± 0.04 L (n = 2 669 days) across the entire dataset. The data will be useful for modelling studies estimating N losses (e.g. ammonia (NH₃) volatilisation, nitrous oxide (N₂O) emission via nitrification and denitrification and nitrate (NO₃^-) leaching) from urine patches.

Understanding intake on pastures: how, why, and a way forward

An assessment of dietary intake is a critical component of animal nutrition. Consumption of feed resources is the basis upon which feeding strategies and grazing management are based. Yet, as far back as 1948, researchers have lauded the trials and tribulations of estimation of the phenomenon, especially when focused on grazing animals and pasture resources. The grazing environment presents a unique situation in which the feed resource is not provided to the animal but, rather, the animal operates as the mechanism of harvest. Therefore, tools for estimation must be developed, validated, and applied to the scenario. There are a plethora of methods currently in use for the estimation of intake, ranging from manual measurement of herbage disappearance to digital technologies and sensors, each of which come with its share of advantages and disadvantages. In order to more firmly grasp these concepts and provide a discussion on the future of this estimation, the Forages and Pastures Symposium at the 2020 ASAS-CSAS-WSASAS Annual Meeting was dedicated to this topic. This review summarizes the presentations in that symposium and offers further insight into where we have come from and where we are going in the estimation of intake for grazing livestock.

Variable selection for monitoring sickness behavior in lactating dairy cattle with the application of control charts

The present observational study investigated the application of multivariate cumulative sum (MCUSUM) control charts by including variables selected by principal component analysis and partial least squares (PLS) regression to identify sickness behavior in dairy cattle. Therefore, sensor information (24 variables) was collected from 480 milking cows on a German dairy farm between September 2018 and December 2019. These variables were gathered in potentially different scenarios on farm. In total, data from 749 animals were available for evaluation. Variables were chosen based on the information of 499 cows (62 healthy; 437 sick) with 93,598 observations. The available diagnoses were collected together to form 1,025 sickness events. Hence, the different numbers of selected variables were included into the MCUSUM control charts. The performance of the MCUSUM control charts was evaluated by a 10-fold cross validation; hence, 90% of the original data set (749 cows) represented the training data, and the remaining 10% was used to test the training results. On average, the 10 training data sets included 124,871 observations with 1,392 sickness events, and the 10 testing data sets included, on average, 13,704 observations with 153 sickness events. The MCUSUM generated from the variables selected by principal component analysis showed comparable results in training and testing in all scenarios; therefore, 70.0 to 97.4% of the sickness events were detected. The false-positive rates ranged from 8.5 to 29.6%, and thus they created at least 2.6 false-positive alerts per day in testing. The variables selected by the PLS regression approach showed comparable sickness detection rates (70.0-99.9%) as well as false-positive rates (8.2-62.8%) in most scenarios. The best performing scenario produced 2.5 false-positive alerts in testing. Summarizing, both approaches showed potential for practical implementation; however, the PLS variable selection approach showed fewer false positives. Therefore, the PLS regression approach could generate a more reliable sickness detection algorithm, if combined with MCUSUM control charts, and considered for practical implementation.

Developing a Simulated Online Model That Integrates GNSS, Accelerometer and Weather Data to Detect Parturition Events in Grazing Sheep: A Machine Learning Approach

Simple Summary

Near-real-time monitoring of livestock using on-animal sensor technology has the potential to improve animal welfare and productivity through increased surveillance and improved decision-making capabilities. One potentially valuable application is for monitoring of lambing events in sheep. This research reports on the development of a machine learning classification algorithm for autonomous detection of lambing events. The algorithm uses data from Global Navigation Satellite System (GNSS) tracking collars, accelerometer ear tags and local weather data. Overall, four features of sheep behaviour were identified as having the greatest importance for lambing detection, including various measures of social distancing and frequency of posture change. Using these four features, the final algorithm was able to detect up to 91% of lambing events. This knowledge is intended to contribute to the development of commercially feasible lambing detection systems for improved surveillance of animals, ultimately improving methods of monitoring during critical welfare periods.

Abstract

In the current study, a simulated online parturition detection model is developed and reported. Using a machine learning (ML)-based approach, the model incorporates data from Global Navigation Satellite System (GNSS) tracking collars, accelerometer ear tags and local weather data, with the aim of detecting parturition events in pasture-based sheep. The specific objectives were two-fold: (i) determine which sensor systems and features provide the most useful information for lambing detection; (ii) evaluate how these data might be integrated using ML classification to alert to a parturition event as it occurs. Two independent field trials were conducted during the 2017 and 2018 lambing seasons in New Zealand, with the data from each used for ML training and independent validation, respectively. Based on objective (i), four features were identified as exerting the greatest importance for lambing detection: mean distance to peers (MDP), MDP compared to the flock mean (MDP.Mean), closest peer (CP) and posture change (PC). Using these four features, the final ML was able to detect 27% and 55% of lambing events within ±3 h of birth with no prior false positives. If the model sensitivity was manipulated such that earlier false positives were permissible, this detection increased to 91% and 82% depending on the requirement for a single alert, or two consecutive alerts occurring. To identify the potential causes of model failure, the data of three animals were investigated further. Lambing detection appeared to rely on increased social isolation behaviour in addition to increased PC behaviour. The results of the study support the use of integrated sensor data for ML-based detection of parturition events in grazing sheep. This is the first known application of ML classification for the detection of lambing in pasture-based sheep. Application of this knowledge could have significant impacts on the ability to remotely monitor animals in commercial situations, with a logical extension of the information for remote monitoring of animal welfare.

An open-source research tool to study triaxial inertial sensors for monitoring selected behaviors in sheep

The use of automated systems for monitoring animal behavior provides information on individual animal behavior and can be used to enhance animal productivity. However, the advancement of this industry is hampered by technology costs, challenges with power supplies, limited data accessibility, and inconsistent testing approaches for confirming the detection of livestock behaviors. Development of open-source research tools similar to commercially available wearable technologies may contribute to the development of more-efficient and affordable technologies. The objective of this study was to demonstrate an open-source, microprocessor-based sensor designed to monitor and enable differentiation among selected behaviors of adult wethers. The sensor was comprised of an inexpensive espressif ESP-32-WROOM-32 microprocessor with Bluetooth communication, a generic MPU92/50 motion sensor that contains a three-axis accelerometer, three-axis magnetometer, a three-axis gyroscope, and a 5-V rechargeable lithium-ion battery. The open-source Arduino IDE software was used to program the microprocessor and to adjust the frequency of sampling, the data packet to send, and the operating conditions. For demonstration purposes, sensors were placed on six housed sheep for three 1-h increments with concurrent visual behavioral observation. Sensor readings (x-, y-, and z-axis) were summarized (mean and SD) within a minute and compared to animal behavior observations (also on a by-minute basis) using a linear mixed-effect model with animal as a random effect and behavioral classifier as a fixed effect. This analysis demonstrated the basic utility of the sensor to differentiate among animal behaviors based on sensed data (P < 0.001). Although substantial additional work is needed for algorithm development, power source testing, and network optimization, this open-source platform appears to be a promising strategy to research wearable sensors in a generalizable manner.

Economic Viability of Adoption of Automated Oestrus Detection Technologies on Dairy Farms: A Review

Simple Summary

The accurate and timely detection of oestrus is a central element of good dairy herd management as it ultimately determines the level of milk production and is core to the economic viability of the farm business. However, the traditional method of oestrus detection, which occurs by observing the dairy cows standing immobile while being mounted, is usually time-consuming, repetitive and requires considerable skill and experience on the part of the farmer to attain a reasonable level of efficiency. Given the limitation of the traditional method of oestrus detection, a number of automated oestrus detection (AOD) technologies have been developed. However, the rate of adoption of these technologies remains low. One reason that has been proposed for farmers’ low adoption of such technologies has been their lack of knowledge around the potential economic returns from investing in AOD technologies. In this paper, we review the empirical literature on the viability of investment in AOD technologies from an economic perspective. The conclusion of this study provides evidence from which farmers can make more informed decisions in relation to investing in AOD technologies. The review and analysis is also of importance for informing policy, as it provides an examination of the incentives and levers that could improve productivity on dairy farms.

Abstract

The decision for dairy farmers to invest in automated oestrus detection (AOD) technologies involves the weighing up of the costs and benefits of implementation. In this paper, through a review of the existing literature, we examine the impacts of investment in AOD technologies in relation to the profitability and technical performance of dairy farms. Peer-reviewed articles published between 1970 and 2019 on the investment viability of AOD technologies were collated and analysed. We capture the different measures used in assessing the economic performance of investment in AOD technologies over time which include net present value (NPV), milk production, Benefit-Cost Ratio (BCR), internal rate of return (IRR) and payback period (PBP). The study concludes that investment in AOD technologies is not only worthwhile but also contributes to farm profitability.

Potential for autonomous detection of lambing using global navigation satellite system technology

Context On-animal sensing systems are being promoted as a solution to the increased demand for monitoring livestock for health and welfare. One key sensor platform, global navigation satellite system (GNSS) positioning, provides information on the location and movement of sheep. This information could be used to detect partition in sheep, a key period of time when both ewes and lambs are at risk. The development of algorithms based on key behavioural features could provide alerts to sheep managers to enable intervention when problems arise. Aims To investigate the use of GNSS monitoring as a method for detecting behavioural changes in sheep in the period around parturition. Methods GNSS collars were attached to 40 late gestation ewes grazing a 3.09 ha paddock in New Zealand. Several metrics were derived: (i) mean daily speed, (ii) maximum daily speed, (iii) minimum daily speed, (iv) mean daily distance to peers, and (v) spatial paddock utilisation by 95% minimum convex polygon. Speed metrics and distance to peers were also evaluated at an hourly scale for the 12 h before and 12 h after lambing. Key results Minimum daily speed peaked on the day of parturition (P &lt; 0.001), suggesting animals may have been expressing more agitation and did not settle. Isolation was also evident during this time, with postpartum ewes located further from their peers than pre-partum ewes (P &lt; 0.001). Day of lambing was also evident by reduced spatial paddock utilisation (P &lt; 0.001). Conclusions This study demonstrates that GNSS technology can be used to detect parturition-related behaviours in sheep at a day scale; however, detection at the hour scale using GNSS is not possible. Implications This research highlights the opportunity to develop predictive models that autonomously detect behavioural changes in ewes at parturition using GNSS. This could then be extended to identify ewes experiencing prolonged parturition, for example dystocic birth enabling intervention which would improve both production and welfare outcomes for the sheep industry.

Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors

The reticuloruminal function is central to the digestive efficiency in ruminants. For cattle, collar- and ear tag-based accelerometer monitors have been developed to assess the time spent ruminating on an individual animal. Cattle that are ill feed less and so ruminate less, thus, the estimation of the time spent ruminating provides insights into the health of individual animals. pH boluses directly provide information on the reticuloruminal function within the rumen and extended (three hours or more) periods during which the ruminal pH value remains below 5.6 is an indicator that dysfunction and poor welfare are likely. Accelerometers, incorporated into the pH boluses, have been used to indicate changes in behaviour patterns (high/low activity), utilised to detect the onset of oestrus. The paper demonstrates for the first time that by processing the reticuloruminal motion, it is possible to recover rumination periods. Reticuloruminal motion energy and the time between reticuloruminal contractions are used as inputs to a Support Vector Machine (SVM) to identify rumination periods with an overall accuracy of 86.1%, corroborated by neck mounted rumination collars.

Validity of Micro-Data Loggers to Determine Walking Activity of Turkeys and Effects on Turkey Gait

Accelerometers have the potential to provide objective, non-invasive methods for detecting changes in animal behavior and health. Our objectives were to: (1) determine the effects of micro-acceleration data loggers (accelerometers) and habituation to accelerometers on turkey gait and health status, (2) determine age-related changes in gait and health status, and (3) assess the validity and reliability of the accelerometers. Thirty-six male commercial turkeys were randomly assigned to one of five groups: accelerometer and habituation period (AH), accelerometer and no habituation period (AN), VetRap bandage (no accelerometer) and habituation period (VH), bandage (no accelerometer) and no habituation period (VN), and nothing on either leg (C). Health status and body condition were assessed prior to video-recording birds as they walked across a Tekscan® pressure pad at 8, 12, and 16 weeks to determine effects of treatment on number of steps, cadence, gait time, gait distance, gait velocity, impulse, gait cycle time, maximum force, peak vertical pressure, single support time, contact time, step length, step time, step velocity, stride length, total double support time, and duty factor. Accelerometer validity and reliability were determined by comparing the number of steps detected by the accelerometer to the number of steps determined from video recordings. Several age-related changes in turkey gait were found regardless of habituation including a slower cadence at 16 weeks, shorter gait distance at 8 weeks, and slower gait velocity at 16 weeks. When comparing bandaged vs. unbandaged limbs, both treatment and age-treatment interactions were found depending on the gait parameter. Accelerometer validity and reliability were affected by both age and treatment. False discovery rate increased, while accuracy and specificity decreased with age. Validity and reliability were lowest for non-habituated birds (AN and VN). Results demonstrated that micro-data loggers do not adversely affect turkey health status, but habituation to wearing accelerometers greatly affects accelerometer reliability and validity. Accelerometer validity and turkey gait are also greatly affected by the age of the turkeys.

Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep

Grazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human operators is prone to human variance, time-consuming and costly, especially on animals kept at pasture or free-ranging. The use of sensors to automatically acquire data, and software to classify and identify behaviours, offers significant potential in addressing such issues. In this work, data collected from sheep by means of an accelerometer/gyroscope sensor attached to the ear and collar, sampled at 16 Hz, were used to develop classifiers for grazing and ruminating behaviour using various machine learning algorithms: random forest (RF), support vector machine (SVM), k nearest neighbour (kNN) and adaptive boosting (Adaboost). Multiple features extracted from the signals were ranked on their importance for classification. Several performance indicators were considered when comparing classifiers as a function of algorithm used, sensor localisation and number of used features. Random forest yielded the highest overall accuracies: 92% for collar and 91% for ear. Gyroscope-based features were shown to have the greatest relative importance for eating behaviours. The optimum number of feature characteristics to be incorporated into the model was 39, from both ear and collar data. The findings suggest that one can successfully classify eating behaviours in sheep with very high accuracy; this could be used to develop a device for automatic monitoring of feed intake in the sheep sector to monitor health and welfare.

Recent advancement in biosensors technology for animal and livestock health management

The term biosensors encompasses devices that have the potential to quantify physiological, immunological and behavioural responses of livestock and multiple animal species. Novel biosensing methodologies offer highly specialised monitoring devices for the specific measurement of individual and multiple parameters covering an animal's physiology as well as monitoring of an animal's environment. These devices are not only highly specific and sensitive for the parameters being analysed, but they are also reliable and easy to use, and can accelerate the monitoring process. Novel biosensors in livestock management provide significant benefits and applications in disease detection and isolation, health monitoring and detection of reproductive cycles, as well as monitoring physiological wellbeing of the animal via analysis of the animal's environment. With the development of integrated systems and the Internet of Things, the continuously monitoring devices are expected to become affordable. The data generated from integrated livestock monitoring is anticipated to assist farmers and the agricultural industry to improve animal productivity in the future. The data is expected to reduce the impact of the livestock industry on the environment, while at the same time driving the new wave towards the improvements of viable farming techniques. This review focusses on the emerging technological advancements in monitoring of livestock health for detailed, precise information on productivity, as well as physiology and well-being. Biosensors will contribute to the 4th revolution in agriculture by incorporating innovative technologies into cost-effective diagnostic methods that can mitigate the potentially catastrophic effects of infectious outbreaks in farmed animals.