Explore the vast range of titles available.

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.

Early virtual fencing trials have effectively contained small groups of sheep within set areas of a paddock when all animals were wearing manual electronic collars. With sheep farming commonly involving large flocks, a potential cost-effective application of virtual fencing would involve applying equipment to only a proportion of the flock. In this study, we tested the ability of virtual fencing to control a small flock of sheep with differing proportions of the group exposed to the virtual fence (VF). Thirty-six Merino sheep were identified as leaders, middle or followers by moving them through a laneway. The sheep were then allocated to groups balanced for order of movement. The groups ( n  = 9 per group) included applying the VF to the following proportions of animals within each group: (1) 100% ( n  = 9 VF) (2) 66% ( n  = 6 VF; n  = 3 no VF) (3) 33% ( n  = 3 VF; n  = 6 no VF) (4) 0% (no VF; free to roam the paddock). The groups were given access to their own paddock (80 × 20 m) for two consecutive days, six hours per day, with the VF groups prevented from entering an exclusion zone that covered 50% of the north side of the paddock. During these hours, VF interactions, behavioural time budgets, and body temperature were recorded as measures of stress, and location was tracked with GPS. Group 100% VF and Control were tested on the first two days and groups 33% VF and 66% VF were tested on the following two days. During VF implementation the 100% VF and 66% VF group were successfully prevented from entering the exclusion zone. Having only 33% of the flock exposed to the virtual fence was not successful, with the sheep pushing forward through the VF to join flock mates in the exclusion zone. For learning to respond to the audio cue, sheep in the 33% group received more electrical stimuli with a 0.51 proportion for the ratio of electrical stimuli to audio cue, compared to 0.22 and 0.28 for the 100% and 66% groups, respectively. There were small differences in behavioural patterns of standing and lying on both days of testing, with the 100% VF and 66% VF groups spending more time lying. Although stress-induced hyperthermia did not occur in any of the VF groups, body temperature differed in the 33% VF group. There were no differences in temperature measures between the control and 100% VF animals. This study demonstrates that for a short period, controlling two-thirds of the flock was equally as effective as virtually fencing all animals, while controlling one-third of a flock with a virtual fence was not effective. For the short term, it appears that implementing the VF to a proportion of the flock can be an effective method of containment. Due to the limitations of this study, these results warrant further testing with larger flocks and for longer periods.

A deep learning approach using long-short term memory (LSTM) networks was implemented in this study to classify the sound of short-term feeding behaviour of sheep, including biting, chewing, bolus regurgitation, and rumination chewing. The original acoustic signal was split into sound episodes using an endpoint detection method, where the thresholds of short-term energy and average zero-crossing rate were utilized. A discrete wavelet transform (DWT), Mel-frequency cepstral, and principal-component analysis (PCA) were integrated to extract the dimensionally reduced DWT based Mel-frequency cepstral coefficients (denoted by PW_MFCC) for each sound episode. Then, LSTM networks were employed to train classifiers for sound episode category classification. The performances of the LSTM classifiers with original Mel-frequency cepstral coefficients (MFCC), DWT based MFCC (denoted by W_MFCC), and PW_MFCC as the input feature coefficients were compared. Comparison results demonstrated that the introduction of DWT improved the classifier performance effectively, and PCA reduced the computational overhead without degrading classifier performance. The overall accuracy and comprehensive F1-score of the PW_MFCC based LSTM classifier were 94.97% and 97.41%, respectively. The classifier established in this study provided a foundation for an automatic identification system for sick sheep with abnormal feeding and rumination behaviour pattern.

Thin-tailed sheep (TTS) and Fat-tailed sheep (FTS) are local Indonesian sheep breeds characterized by coarse wool. This study aimed to investigate the effects of wool shearing on the thermo-physiological, behavior, and productivity traits of these sheep. Sixteen selected rams were utilized in this study. Animals were assigned to a factorial completely randomized design and divided into two groups (TTS and FTS) and two treatments (sheared and unsheared). The study spanned three months under controlled conditions. Variables observed included environmental conditions, thermo-physiological parameters (respiratory rate/RR, pulse rate/PR, rectal temperature/RT, and heat stress index/HSI), sheep behavior (feeding duration, drinking frequency, rumination duration, urination frequency, defecation frequency, standing duration, and lying duration), and sheep productivity (feed intake, average daily gain/ADG, and feed conversion ratio/FCR). Data were analyzed using two-way ANOVA. Throughout the study, average temperature and humidity ranged from 25.13-30.48 oC and 64.50%-91.67%, respectively. Wool shearing significantly influenced (p<0.05) sheep’s thermo-physiological, behavior, and productivity traits. These effects were consistent across sheep breeds, with no significant differences noted. Wool shearing significantly reduced (p<0.05) RR, PR, and RT, while the impact on average HSI was not significant. Additionally, sheared sheep exhibited increased (p<0.05) feeding, rumination, standing duration, and higher defecation frequency. Conversely, drinking frequency, urination frequency, and lying duration decreased in the sheared sheep group. Moreover, the sheared sheep demonstrated higher (p<0.05) feed intake and ADG, leading to a reduced (p<0.05) FCR compared to the unsheared group. In conclusion, shearing is a recommended practice for coarse wool-type sheep in tropical environments. This technique does not induce stress and enhances their thermo-physiological, behavior, and productivity traits.

Factors influencing grazing behavior in species‐rich grasslands have been little studied. Methodologies have mostly had a primary focus on grasslands with lower floristic diversity. We test the hypothesis that grazing behavior is influenced by both animal and plant factors and investigate the relative importance of these factors, using a novel combination of video technology and vegetation classification to analyze bite and step rates. In a semi‐natural, partially wooded grassland in northern Estonia, images of the vegetation being grazed and records of steps and bites were obtained from four video cameras, each mounted on the sternum of a sheep, during 41 animal‐hours of observation over five days. Plant species lists for the immediate field of view were compiled. Images were partnered by direct observation of the nearest‐neighbor relationships of the sheep. TWINSPAN, a standard vegetation classification technique allocating species lists to objectively defined classes by a principal components procedure, was applied to the species lists and 25 vegetation classes (15 open pasture and 10 woodland) were identified from the images. Taking bite and step rates as dependent variables, relative importance of animal factors (sheep identity), relative importance of day, and relative importance of plant factors (vegetation class) were investigated. The strongest effect on bite rates was of vegetation class. Sheep identity was less influential. When the data from woodland were excluded, sheep identity was more important than vegetation class as a source of variability in bite rate on open pasture. The original hypothesis is therefore supported, and we further propose that, at least with sheep in species‐rich open pastures, animal factors will be more important in determining grazing behavior than plant factors. We predict quantifiable within‐breed and between‐breed differences, which could be exploited to optimize conservation grazing practices and contribute to the sustainability of extensive grazing systems. Sheep carried video cameras enabling their interactions with the vegetation of their species‐rich pasture to be evaluated. Their behavior, as measured by bite rates, depended far more on their individuality than on the vegetation. This novel combination of vegetation analysis and video technology could provide underpinning for the practice of grazing in areas of conservation importance.

Sheep are exposed to numerous stressors and environments during the pre-export phase of the live export industry. Establishing how animal behavior, health and demeanor reflect their experiences prior to sea transport is the first step toward testing the suitability and practicality of animal welfare measures. A total of 240 merino wethers originating from four farms were assessed at four locations in the live export chain: on farm, upon arrival to the registered export feedlot (Fe1), prior to departing the feedlot (Fe2) and 30 min post loading onto a live export vessel. Each of these locations and time points represent relevant assessment points as part of the commercial live export process. Pen-side behavioral and health measures were collected. Video footage was collected and edited to provide 48 30–45 s duration clips that were then scored by 12 assessors against 10 demeanor terms using a Qualitative Behavioral Assessment (QBA) methodology; data were analyzed using Principal Components (PC) analysis. Repeated Measures ANOVAs tested for variation in each dependent measure across each location and time point. There were low levels of health issues recorded overall; however, seven health and behavior measures significantly varied across the locations and time points. Most vocalizing was recorded on farm; most drinking, eating and resting behaviors were recorded at Fe1 and ruminating at Fe2; while the highest percentage of wethers with ocular discharge and lameness was on the vessel. For QBA, PC1 explained 30.5% of the variability, with agitated and nervous loaded to one end of the axis and calm and relaxed loaded to the opposing end. PC2 explained 24.5% of the variability, with interested, alert and sociable loaded to one end of the axis and lethargic loaded to the opposing end. Spearman's rank correlations between behavior, health and PC scores indicated that wethers eating, ruminating and resting were scored as more calm/relaxed , while those scored as more agitated/nervous or / lethargic were also likely to vocalize. Determining how wethers respond to the different environments in the immediate pre-export phase of the journey informs on their welfare and the practicality of using a behavior tool to assess animal welfare.

In precision feeding, non-contact and pressure-free monitoring of sheep feeding behavior is crucial for health monitoring and optimizing production management. The experimental conditions and real-world environments differ when using acoustic sensors to identify sheep feeding behaviors, leading to discrepancies and consequently posing challenges for achieving high-accuracy classification in complex production environments. This study enhances the classification performance by integrating the deep spectrogram features and acoustic characteristics associated with feeding behavior. We conducted the task of collecting sound data in actual production environments, considering noise and complex surroundings. The method included evaluating and filtering the optimal acoustic features, utilizing a customized convolutional neural network (SheepVGG-Lite) to extract Short-Time Fourier Transform (STFT) spectrograms and Constant Q Transform (CQT) spectrograms’ deep features, employing cross-spectrogram feature fusion and assessing classification performance through a support vector machine (SVM). Results indicate that the fusion of cross-spectral features significantly improved classification performance, achieving a classification accuracy of 96.47%. These findings highlight the value of integrating acoustic features with spectrogram deep features for accurately recognizing sheep feeding behavior.

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.