Livestock Monitoring System Research Articles

269 Evaluation of changes in the activity of group-housed nursery pigs exposed to an endotoxin challenge using the NUtrack Livestock Monitoring System

Abstract The objective of this study was to evaluate the changes in activity of group-housed, newly weaned, Duroc-sired crossbred commercial pigs exposed to a lipopolysaccharide (LPS) challenge. At weaning, pigs [n = 192, body weight (BW) = 5.73 ± 1.8 kg] were stratified by sex, litter, and weaning weight and randomly assigned to one of three treatment groups (16 pigs/pen, 4 pens/treatment). Treatments were: 1) control – saline-injected (SAL), 2) 50% challenged (LPS50) – one-half of the pigs in a pen (n = 8) were challenged with LPS, the remaining 8 pigs received saline, and 3) 100% LPS challenged (LPS100) – all pigs in a pen were challenged with LPS. Pigs in the SAL group and 32 in the LPS50 group received a 3.0 mL subcutaneous saline injection. The remaining pigs in the LPS50 group and all pigs in the LPS100 group received a 3.0 mL subcutaneous LPS (E. coli O111:B4) injection dissolved in sterile saline calculated to challenge each pig with 300 µg/kg of BW. Pigs were continuously monitored (24 h/d) during the 42-d nursery period via the NUtrack Livestock Monitoring System. Activity traits included distance traveled (m/d), time spent at the feeder (% of day), and time spent standing (% of day) and were analyzed using the PROC GLIMMIX procedure of SAS. When main effects or interactions were significant (P ≤ 0.05), specific comparisons were made using the PDIFF option in SAS. Changes in activities were observed (P ≤ 0.03) in both LPS groups for the first 3 to 4 d after the challenge. During this period, pigs in the LPS50 and LPS100 groups walked less (P ≤ 0.001) and spent less (P ≤ 0.002) time standing and less (P ≤ 0.03) time at the feeder when compared with pigs in the SAL group. By d 5, activities were similar (P ≥ 0.07) between the three treatment groups and remained similar (P ≥ 0.38) until 9 d after the LPS challenge. Starting on d 11 and continuing until d 15, there was an increase (P ≤ 0.03) in both meters walked/d and time spent standing for pigs in the LPS100 group compared with the SAL group. Furthermore, on d 10 to 15, pigs in the LPS50 and LPS100 groups spent more (P ≤ 0.05) time at the feeder when compared with the pigs in the SAL group. However, increased time at the feeder from d 9 to 15 for LPS100 did not offset the impact of the LPS challenge on nursery exit weight. At exit (d 42), pigs in the LPS100 group had reduced (P ≤ 0.04) BW and average daily gain, when compared with the pigs in the SAL group. Overall, these results suggest that changes in activities following an LPS challenge are not limited to the days immediately following the challenge. Although an LPS challenge elicits a short-lived (3 - 4 d) immune response, its effects can be long-lasting.

Nano Sensor Empowered Livestock Monitoring System Using Golden Section Optimized Recurrent Neural Network IoT Platform

Nano Sensor Empowered Livestock Monitoring System Using Golden Section Optimized Recurrent Neural Network IoT Platform

OPTIMIZATION OF LIVESTOCK MONITORING SYSTEM IN OUTDOOR BASED ON INTERNET OF THINGS (IOT)

Livestock businesses are often underestimated by the public because they are associated with less hygienic working environments. However, the demand for livestock products such as meat and milk is increasing, providing significant business opportunities. Several obstacles, such as livestock loss and the capital required for cage construction, are barriers to starting a livestock business. Livestock losses, especially in outdoor farms, often occur because of the lack of proper monitoring and data collection. Therefore, technology is required to overcome this problem. The application of IoT technology is an effective solution for overcoming this problem. By utilizing sensors, such as GPS, temperature, and heart rate, farmers can monitor farm animals remotely using Android applications. In this study, a U-blox Neo6m GPS sensor was used to track the location of farm animals, a temperature sensor was used to monitor the temperature conditions of farm animals, and a heart rate sensor was used to determine the health of farm animals that had been tested. The use of a 1500 mAh LI-ION LITHIUM battery as a power source proved to be sufficient for 7 h. The results showed that this IoT-based Outdoor Livestock Monitoring System can provide information on the last location of livestock as well as real-time heart rate and temperature data in the database. This innovation opens opportunities for farmers to improve livestock management and monitoring efficiently, minimize losses, and increase the productivity of their livestock business

Evaluation of a novel computer vision-based livestock monitoring system to identify and track specific behaviors of individual nursery pigs within a group-housed environment.

Animal behavior is indicative of health status and changes in behavior can indicate health issues (i.e., illness, stress, or injury). Currently, human observation (HO) is the only method for detecting behavior changes that may indicate problems in group-housed pigs. While HO is effective, limitations exist. Limitations include HO being time consuming, HO obfuscates natural behaviors, and it is not possible to maintain continuous HO. To address these limitations, a computer vision platform (NUtrack) was developed to identify (ID) and continuously monitor specific behaviors of group-housed pigs on an individual basis. The objectives of this study were to evaluate the capabilities of the NUtrack system and evaluate changes in behavior patterns over time of group-housed nursery pigs. The NUtrack system was installed above four nursery pens to monitor the behavior of 28 newly weaned pigs during a 42-d nursery period. Pigs were stratified by sex, litter, and randomly assigned to one of two pens (14 pigs/pen) for the first 22 d. On day 23, pigs were split into four pens (7 pigs/pen). To evaluate the NUtrack system’s capabilities, 800 video frames containing 11,200 individual observations were randomly selected across the nursery period. Each frame was visually evaluated to verify the NUtrack system’s accuracy for ID and classification of behavior. The NUtrack system achieved an overall accuracy for ID of 95.6%. This accuracy for ID was 93.5% during the first 22 d and increased (P < 0.001) to 98.2% for the final 20 d. Of the ID errors, 72.2% were due to mislabeled ID and 27.8% were due to loss of ID. The NUtrack system classified lying, standing, walking, at the feeder (ATF), and at the waterer (ATW) behaviors accurately at a rate of 98.7%, 89.7%, 88.5%, 95.6%, and 79.9%, respectively. Behavior data indicated that the time budget for lying, standing, and walking in nursery pigs was 77.7% ± 1.6%, 8.5% ± 1.1%, and 2.9% ± 0.4%, respectively. In addition, behavior data indicated that nursery pigs spent 9.9% ± 1.7% and 1.0% ± 0.3% time ATF and ATW, respectively. Results suggest that the NUtrack system can detect, identify, maintain ID, and classify specific behavior of group-housed nursery pigs for the duration of the 42-d nursery period. Overall, results suggest that, with continued research, the NUtrack system may provide a viable real-time precision livestock tool with the ability to assist producers in monitoring behaviors and potential changes in the behavior of group-housed pigs.

Automated Muzzle Detection and Biometric Identification via Few-Shot Deep Transfer Learning of Mixed Breed Cattle

Livestock welfare and management could be greatly enhanced by the replacement of branding or ear tagging with less invasive visual biometric identification methods. Biometric identification of cattle from muzzle patterns has previously indicated promising results. Significant barriers exist in the translation of these initial findings into a practical precision livestock monitoring system, which can be deployed at scale for large herds. The objective of this study was to investigate and address key limitations to the autonomous biometric identification of cattle. The contributions of this work are fourfold: (1) provision of a large publicly-available dataset of cattle face images (300 individual cattle) to facilitate further research in this field, (2) development of a two-stage YOLOv3-ResNet50 algorithm that first detects and extracts the cattle muzzle region in images and then applies deep transfer learning for biometric identification, (3) evaluation of model performance across a range of cattle breeds, and (4) utilizing few-shot learning (five images per individual) to greatly reduce both the data collection requirements and duration of model training. Results indicated excellent model performance. Muzzle detection accuracy was 99.13% (1024 × 1024 image resolution) and biometric identification achieved 99.11% testing accuracy. Overall, the two-stage YOLOv3-ResNet50 algorithm proposed has substantial potential to form the foundation of a highly accurate automated cattle biometric identification system, which is applicable in livestock farming systems. The obtained results indicate that utilizing livestock biometric monitoring in an advanced manner for resource management at multiple scales of production is possible for future agriculture decision support systems, including providing useful information to forecast acceptable stocking rates of pastures.

Design of Scalable IoT Architecture Based on AWS for Smart Livestock.

Simple SummaryDue to the growing number of connected IoT devices, the scalability capacity and available computing power of the existing architectural frameworks would be reached. This necessitates finding a solution that meets the growing demands. Cloud-based IoT is becoming an increasingly popular and desirable solution. This work presents a specially designed architecture based on Amazon Web Services (AWS) for monitoring livestock using cyber–physical systems (CPS) and Internet of things (IoT) equipment and a wide range of cloud native services. Used services in AWS cloud are described in detail and their tasks according to the application area are clarified. A stress test to prove the ability of the developed architecture for data processing was completed. Experimental results showed that the proposed architecture with the services provided by Amazon is fully capable of processing the required amount of data and allows the CPS/IoT infrastructure to use automated scaling mechanisms.In the ecological future of the planet, intelligent agriculture relies on CPS and IoT to free up human resources and increase production efficiency. Due to the growing number of connected IoT devices, the maximum scalability capacity, and available computing power of the existing architectural frameworks will be reached. This necessitates finding a solution that meets the continuously growing demands in smart farming. Cloud-based IoT solutions are achieving increasingly high popularity. The aim of this study was to design a scalable cloud-based architecture for a smart livestock monitoring system following Agile methodology and featuring environmental monitoring, health, growth, behaviour, reproduction, emotional state, and stress levels of animals. The AWS services used, and their specific tasks related to the proposed architecture are explained in detail. A stress test was performed to prove the data ingesting and processing capability of the proposed architecture. Experimental results proved that the proposed architecture using AWS automated scaling mechanisms and IoT devices are fully capable of processing the growing amount of data, which in turn allow for meeting the required needs of the constantly expanding number of CPS systems.

181 Utilization of the Nutrack Livestock Monitoring System to Identify Changes in General and Spatial Behaviors of Newly Weaned Nursery Exposed to an Endotoxin Challenge

Abstract Incorporation of precision livestock technology has the potential to provide swine producers with the means to rapidly and accurately identify immune-compromised pigs, allowing for accurate and timely interventions. The objective of this study was to utilize the NUtrack System (NUtrack) to identify changes in general (lying, standing and sitting) and spatial behaviors (at the feeder and meters/day) of newly weaned pigs exposed to a lipopolysaccharide (LPS) challenge. To achieve this objective, 12 nursery pens with 192 weaned pigs (16 pigs/pen) were randomly assigned to three treatments (4 pens/treatment): Control (saline injection), Mixed (8 pigs/pen received an LPS challenge and 8 pigs received saline injection) and 100% (all pigs received LPS). The LPS challenge consisted of a bolus subcutaneous injection at 300 µg/kg BW (E. coli O111:B4). Prior to placement, NUtrack was installed above the 12 nursery pens and initiated continuous data capture for the duration of the nursery phase (43 days). Ten days after placement in the nursery pens pigs received the assigned challenge (LPS or sham). Data were analyzed using the MIXED procedure of SAS specific for repeated measures (SAS Inst. Inc., Cary, NC). Regardless of treatment group, general special behaviors were similar (P = &amp;gt;0.28) prior to the LPS challenge (days 1–9). Following LPS challenge (day 10), spatial behaviors decreased (P = &amp;lt;0.01) and time associated with general behaviors increased (P = &amp;lt;0.01) for LPS challenged pigs when compared to pigs not challenged (Control and 50% non-challenged). This change in both general and spatial behaviors remained until day 12. In addition, general and spatial behaviors of the 50% treatment (challenged and non-challenged) were different (P = &amp;lt; 0.03), when compared to Controls. Results suggest precision livestock technology, like the NUtrack System, has the potential to monitor changes in behaviors following an endotoxin challenge.

Deep Learning-Based Cattle Vocal Classification Model and Real-Time Livestock Monitoring System with Noise Filtering.

Simple SummaryIn the application of artificial intelligence and advanced sound technologies in animal sound classification, certain challenges are still faced, such as the disruptions of background noise. To address this problem, we propose a web-based and real-time cattle monitoring system for evaluating cattle conditions. The system contained a convolutional neural network (CNN) for classifying cattle vocals and removing background noise as well as another CNN for behavior classification from existing datasets. The developed model was applied to cattle sound data obtained from an on-site monitoring system through sensors and achieved a final accuracy of 81.96% after the sound filtering. Finally, the model was deployed on a web platform to assist farm owners in monitoring the conditions of their livestock. We believe that our study makes a significant contribution to the literature because it is the first attempt to combine CNN and Mel-frequency cepstral coefficients (MFCCs) for real-time cattle sound detection and a corresponding behavior matching.The priority placed on animal welfare in the meat industry is increasing the importance of understanding livestock behavior. In this study, we developed a web-based monitoring and recording system based on artificial intelligence analysis for the classification of cattle sounds. The deep learning classification model of the system is a convolutional neural network (CNN) model that takes voice information converted to Mel-frequency cepstral coefficients (MFCCs) as input. The CNN model first achieved an accuracy of 91.38% in recognizing cattle sounds. Further, short-time Fourier transform-based noise filtering was applied to remove background noise, improving the classification model accuracy to 94.18%. Categorized cattle voices were then classified into four classes, and a total of 897 classification records were acquired for the classification model development. A final accuracy of 81.96% was obtained for the model. Our proposed web-based platform that provides information obtained from a total of 12 sound sensors provides cattle vocalization monitoring in real time, enabling farm owners to determine the status of their cattle.

Animal Monitoring Scheme in Smart Farm using Cloud-Based System

&#x0D; &#x0D; &#x0D; Currently, many operations are carried out manually on farms for raising livestock. In particular, it does not use equipment to understand the condition of animals, but relies only on the farmer’s perspective. If information can be obtained by monitoring farm animals, manager can determine the behavior of the animals and use this information to predict the health of the animals. In this paper, we propose a livestock monitoring system based on WSN. The proposed system can monitor farm animals using IoT equipment and cloud platforms. A collar was mounted on the neck of an animal using IoT equipment, and the activity of the livestock was monitored. Farming man- ager can supervises live information by transmitting livestock observation information to cloud platforms. Through actual implementation, we verified that the proposed system can monitor animals on farms in real time.&#x0D; &#x0D; &#x0D;

Perancangan Sistem Pemantauan Peternakan Ayam Berbasis Internet of Things (IoT) dengan Cisco packet tracer 7.0

To maintain temperature stability in chickens, it is generally done by visiting the cage regularly. However, as technology develops, many have implemented the Internet of Things (IoT) system. IoT is a concept that certain objects have the ability to transmit data over a network without any human interaction. ne of the IoT applications is in the chicken livestock monitoring system. Chicken breeds at the Faculty of Animal Husbandry, Udayana University have not implemented an IoT system. To implement the IoT system, temperature sensors, humidity sensors, motion sensors, room heaters, air conditioners are needed. Where the temperature sensor and humidity sensor function to monitor and forwarded through a micro controller that has been applied to the program so that the heating and air conditioning work at the set temperature. This IoT system can be simulated in advance to ensure the system runs well before it is applied to the actual media. Cisco Packet Tracer v7.0 is an application that supports IoT simulation using Visual Block Programing. The simulation results on motion sensors, temperature sensors, humidity sensors, room heaters, and air conditioners work well in the simulation, but the temperature sensor and humidity sensor readings are not precise due to bugs from the application.

Efficient Herd – Outlier Detection in Livestock Monitoring System Based on Density – Based Spatial Clustering

In today's society, increasing the quality and the productivity of dairy products are very important and need detailed data collection and analysis. Manual collection of data and its analysis for livestock monitoring is costly in terms of high man power and time consumption. In order to overcome this deficit, object detection and clustering methods are investigated in this research as it is in line with Smart Farming 4.0. Faster RCNN is used to help ranchers to detect livestock while clustering methods help to detect the herds and outliers effectively and efficiently. In clustering methods, K-means clustering technique and Density-Based Spatial Clustering of Application with Noise or DBScan clustering technique are adopted. In K-means clustering, k is an important parameter which represents the number of clusters. By changing the number of clusters, the pattern of clusters is observed. Then, the best k value is selected. In DBScan clustering, epsilon is an important parameter which represents the circle radius from a particular data point. The higher the value of epsilon, the formation of clusters becomes easier as it is easy to accept data point in a larger circle radius to form cluster. By changing the epsilon, the pattern of cluster is observed and chosen. Euclidean distance and Manhattan distance are used to compare the effects of different distance metrics on the results of clusters. Cluster pattern is compared between K-means and DBScan techniques. Obtained results show that DBScan overwhelmed K-means in term of efficient clustering in detecting the herds and outliers of livestock.

Predicting Lameness in Sheep Activity Using Tri-Axial Acceleration Signals.

Simple SummaryMonitoring livestock farmed under extensive conditions is challenging and this is particularly difficult when observing animal behaviour at an individual level. Lameness is a disease symptom that has traditionally relied on visual inspection to detect those animals with an abnormal walking pattern. More recently, accelerometer sensors have been used in other livestock industries to detect lame animals. These devices are able to record changes in activity intensity, allowing us to differentiate between a grazing, walking, and resting animal. Using these on-animal sensors, grazing, standing, walking, and lame walking were accurately detected from an ear attached sensor. With further development, this classification algorithm could be linked with an automatic livestock monitoring system to provide real time information on individual health status, something that is practically not possible under current extensive livestock production systems.Lameness is a clinical symptom associated with a number of sheep diseases around the world, having adverse effects on weight gain, fertility, and lamb birth weight, and increasing the risk of secondary diseases. Current methods to identify lame animals rely on labour intensive visual inspection. The aim of this current study was to determine the ability of a collar, leg, and ear attached tri-axial accelerometer to discriminate between sound and lame gait movement in sheep. Data were separated into 10 s mutually exclusive behaviour epochs and subjected to Quadratic Discriminant Analysis (QDA). Initial analysis showed the high misclassification of lame grazing events with sound grazing and standing from all deployment modes. The final classification model, which included lame walking and all sound activity classes, yielded a prediction accuracy for lame locomotion of 82%, 35%, and 87% for the ear, collar, and leg deployments, respectively. Misclassification of sound walking with lame walking within the leg accelerometer dataset highlights the superiority of an ear mode of attachment for the classification of lame gait characteristics based on time series accelerometer data.

가축 생산성 향상을 위한 유비쿼터스 통합 모니터링 시스템

This research aims to propose a ubiquitous integration monitoring system for the feeding and environment management of livestock production. The integration monitoring system proposed in this research is based on an integrated platform, and consists of livestock shed environment monitoring system, livestock monitoring system, livestock remote medical treatment, and feeding and management system. This research conducts the followings. First, we review the previous researches on livestock related ubiquitous monitoring system to examine the factors to be considered in the proposed system. Then, we design the system and implement the prototype to demonstrate the possibility of the application of this system to real stockbreeding environment.