Animals

Editorial

3 pages, 142 KiB

Open AccessEditorial

Field Implementation of Precision Livestock Farming: Selected Proceedings from the 2nd U.S. Precision Livestock Farming Conference

by Yang Zhao, Brett C. Ramirez, Janice M. Siegford, Hao Gan, Lingjuan Wang-Li, Daniel Berckmans and Robert T. Burns

Animals 2024, 14(7), 1128; https://doi.org/10.3390/ani14071128 - 07 Apr 2024

Viewed by 631

Abstract

Precision Livestock Farming (PLF) involves the real-time monitoring of images, sounds, and other biological, physiological, and environmental parameters to assess and improve animal health and welfare within intensive and extensive production systems [...] Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

Research

Jump to: Editorial

19 pages, 2333 KiB

Open AccessArticle

Model Adaptation and Validation for Estimating Methane and Ammonia Emissions from Fattening Pig Houses: Effect of Manure Management System

by Paria Sefeedpari, Seyyed Hassan Pishgar-Komleh and Andre J. A. Aarnink

Animals 2024, 14(6), 964; https://doi.org/10.3390/ani14060964 - 20 Mar 2024

Cited by 1 | Viewed by 806

Abstract

This paper describes a model for the prediction of methane and ammonia emissions from fattening pig houses. This model was validated with continuous and discrete measurements using a reference method from two manure management systems (MMS): long storage (LS) in deep pits and [...] Read more.

This paper describes a model for the prediction of methane and ammonia emissions from fattening pig houses. This model was validated with continuous and discrete measurements using a reference method from two manure management systems (MMS): long storage (LS) in deep pits and short storage (SS) by daily flushing of a shallow pit with sloped walls and partial manure dilution. The average calculated methane and ammonia emissions corresponded well with the measured values. Based on the calculated and measured results, the average calculated CH₄ emission (18.5 and 4.3 kg yr⁻¹ per pig place) was in between the means from the continuous data from sensors (15.9 and 5.6 kg yr⁻¹ per pig place) and the means from the discrete measurements using the reference method (22.0 and 3.1 kg yr⁻¹ per pig place) for the LS and SS systems, respectively. The average calculated NH₃ emission (2.6 and 1.4 kg yr⁻¹ per pig place) corresponded well with the continuous data (2.6 and 1.2 kg yr⁻¹ per pig place) and the discrete measurements using the reference method (2.7 and 1.0 kg yr⁻¹ per pig place) from LS and SS, respectively. This model was able to predict the reduction potential for methane and ammonia emissions by the application of mitigation options. Furthermore, this model can be utilized as a predictive tool, enabling timely actions to be taken based on the emission prediction. The upgraded model with robust calculation rules, extensive validations, and a simplified interface can be a useful tool to assess the current situation and the impact of mitigation measures at the farm level. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

14 pages, 4823 KiB

Open AccessArticle

Determining the Presence and Size of Shoulder Lesions in Sows Using Computer Vision

by Shubham Bery, Tami M. Brown-Brandl, Bradley T. Jones, Gary A. Rohrer and Sudhendu Raj Sharma

Animals 2024, 14(1), 131; https://doi.org/10.3390/ani14010131 - 29 Dec 2023

Cited by 1 | Viewed by 971

Abstract

Shoulder sores predominantly arise in breeding sows and often result in untimely culling. Reported prevalence rates vary significantly, spanning between 5% and 50% depending upon the type of crate flooring inside a farm, the animal’s body condition, or an existing injury that causes [...] Read more.

Shoulder sores predominantly arise in breeding sows and often result in untimely culling. Reported prevalence rates vary significantly, spanning between 5% and 50% depending upon the type of crate flooring inside a farm, the animal’s body condition, or an existing injury that causes lameness. These lesions represent not only a welfare concern but also have an economic impact due to the labor needed for treatment and medication. The objective of this study was to evaluate the use of computer vision techniques in detecting and determining the size of shoulder lesions. A Microsoft Kinect V2 camera captured the top-down depth and RGB images of sows in farrowing crates. The RGB images were collected at a resolution of 1920 × 1080. To ensure the best view of the lesions, images were selected with sows lying on their right and left sides with all legs extended. A total of 824 RGB images from 70 sows with lesions at various stages of development were identified and annotated. Three deep learning-based object detection models, YOLOv5, YOLOv8, and Faster-RCNN, pre-trained with the COCO and ImageNet datasets, were implemented to localize the lesion area. YOLOv5 was the best predictor as it was able to detect lesions with an mAP@0.5 of 0.92. To estimate the lesion area, lesion pixel segmentation was carried out on the localized region using traditional image processing techniques like Otsu’s binarization and adaptive thresholding alongside DL-based segmentation models based on U-Net architecture. In conclusion, this study demonstrates the potential of computer vision techniques in effectively detecting and assessing the size of shoulder lesions in breeding sows, providing a promising avenue for improving sow welfare and reducing economic losses. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

13 pages, 3861 KiB

Open AccessArticle

Deep Learning Models to Predict Finishing Pig Weight Using Point Clouds

by Shiva Paudel, Rafael Vieira de Sousa, Sudhendu Raj Sharma and Tami Brown-Brandl

Animals 2024, 14(1), 31; https://doi.org/10.3390/ani14010031 (registering DOI) - 21 Dec 2023

Cited by 2 | Viewed by 1041

Abstract

The selection of animals to be marketed is largely completed by their visual assessment, solely relying on the skill level of the animal caretaker. Real-time monitoring of the weight of farm animals would provide important information for not only marketing, but also for [...] Read more.

The selection of animals to be marketed is largely completed by their visual assessment, solely relying on the skill level of the animal caretaker. Real-time monitoring of the weight of farm animals would provide important information for not only marketing, but also for the assessment of health and well-being issues. The objective of this study was to develop and evaluate a method based on 3D Convolutional Neural Network to predict weight from point clouds. Intel Real Sense D435 stereo depth camera placed at 2.7 m height was used to capture the 3D videos of a single finishing pig freely walking in a holding pen ranging in weight between 20–120 kg. The animal weight and 3D videos were collected from 249 Landrace × Large White pigs in farm facilities of the FZEA-USP (Faculty of Animal Science and Food Engineering, University of Sao Paulo) between 5 August and 9 November 2021. Point clouds were manually extracted from the recorded 3D video and applied for modeling. A total of 1186 point clouds were used for model training and validating using PointNet framework in Python with a 9:1 split and 112 randomly selected point clouds were reserved for testing. The volume between the body surface points and a constant plane resembling the ground was calculated and correlated with weight to make a comparison with results from the PointNet method. The coefficient of determination (R² = 0.94) was achieved with PointNet regression model on test point clouds compared to the coefficient of determination (R² = 0.76) achieved from the volume of the same animal. The validation RMSE of the model was 6.79 kg with a test RMSE of 6.88 kg. Further, to analyze model performance based on weight range the pigs were divided into three different weight ranges: below 55 kg, between 55 and 90 kg, and above 90 kg. For different weight groups, pigs weighing below 55 kg were best predicted with the model. The results clearly showed that 3D deep learning on point sets has a good potential for accurate weight prediction even with a limited training dataset. Therefore, this study confirms the usability of 3D deep learning on point sets for farm animals’ weight prediction, while a larger data set needs to be used to ensure the most accurate predictions. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

12 pages, 1918 KiB

Open AccessArticle

Improving Dry Matter Intake Estimates Using Precision Body Weight on Cattle Grazed on Extensive Rangelands

by Hector Manuel Menendez III, Jameson Robert Brennan, Krista Ann Ehlert and Ira Lloyd Parsons

Animals 2023, 13(24), 3844; https://doi.org/10.3390/ani13243844 - 14 Dec 2023

Cited by 1 | Viewed by 793

Abstract

An essential component required for calculating stocking rates for livestock grazing extensive rangeland is dry matter intake (DMI). Animal unit months are used to simplify this calculation for rangeland systems to determine the rate of forage consumption and the cattle grazing duration. However, [...] Read more.

An essential component required for calculating stocking rates for livestock grazing extensive rangeland is dry matter intake (DMI). Animal unit months are used to simplify this calculation for rangeland systems to determine the rate of forage consumption and the cattle grazing duration. However, there is an opportunity to leverage precision technology deployed on rangeland systems to account for the individual animal variation of DMI and subsequent impacts on herd-level decisions regarding stocking rate. Therefore, the objectives of this study were, first, to build a precision system model (PSM) to predict total DMI (kg) and required pasture area (ha) using precision body weight (BW), and second, to evaluate differences in PSM-predicted stocking rates compared to the traditional herd-level method using initial or estimated mid-season BW. A deterministic model was constructed in both Vensim (version 10.1.2) and Program R (version 4.2.3) to incorporate individual precision BW data into a commonly used rangeland equation using %BW to estimate individual DMI, daily herd DMI, and area (ha) required to meet animal DMI requirements throughout specific grazing periods. Using the PSM, differences in outputs were evaluated using three scenarios: (1) initial BW (business as usual); (2) average mid-season BW; and (3) individual precision BW using data from two precision rangeland experiments conducted at the South Dakota State University Cottonwood Field Station. The data from the two experiments were used to develop PSM case studies. The trial data were collected using precision weight data (SmartScale™) collected from replacement heifers (Case study 1, n = 60) and steers (Case study 2, n = 254) grazing native rangeland. In Case study 1 (heifers), Scenario 1 versus Scenario 3 resulted in an additional 73.41 ha required. Results from Case study 2 indicated an average additional 4.4 ha required per pasture when comparing Scenario 3 versus Scenario 1. Sensitivity analyses resulted in a difference between maximum and minimum simulated values of 27,995 and 4265 kg forage consumed, and 122 and 8.9 pasture ha required for Case studies 1 and 2, respectively. Thus, results from the scenarios indicate an opportunity to identify both under- and over-stocking situations using precision DMI estimates, which helps to identify high-leverage precision tools that have practical applications for enhancing animal and plant productivity and environmental sustainability on extensive rangelands. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

9 pages, 6939 KiB

Open AccessCommunication

In-Line Detection of Clinical Mastitis by Identifying Clots in Milk Using Images and a Neural Network Approach

by Glenn Van Steenkiste, Igor Van Den Brulle, Sofie Piepers and Sarne De Vliegher

Animals 2023, 13(24), 3783; https://doi.org/10.3390/ani13243783 - 08 Dec 2023

Cited by 1 | Viewed by 3878

Abstract

Automated milking systems (AMSs) already incorporate a variety of milk monitoring and sensing equipment, but the sensitivity, specificity, and positive predictive value of clinical mastitis (CM) detection remain low. A typical symptom of CM is the presence of clots in the milk during [...] Read more.

Automated milking systems (AMSs) already incorporate a variety of milk monitoring and sensing equipment, but the sensitivity, specificity, and positive predictive value of clinical mastitis (CM) detection remain low. A typical symptom of CM is the presence of clots in the milk during fore-stripping. The objective of this study was the development and evaluation of a deep learning model with image recognition capabilities, specifically a convolutional neural network (NN), capable of detecting such clots on pictures of the milk filter socks of the milking system, after the phase in which the first streams of milk have been discarded. In total, 696 pictures were taken with clots and 586 pictures without. These were randomly divided into 60/20/20 training, validation, and testing datasets, respectively, for the training and validation of the NN. A convolutional NN with residual connections was trained, and the hyperparameters were optimized based on the validation dataset using a genetic algorithm. The integrated gradients were calculated to explain the interpretation of the NN. The accuracy of the NN on the testing dataset was 100%. The integrated gradients showed that the NN identified the clots. Further field validation through integration into AMS is necessary, but the proposed deep learning method is very promising for the inline detection of CM on AMS farms. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

13 pages, 1523 KiB

Open AccessArticle

Behavioral Adaptations of Nursing Brangus Cows to Virtual Fencing: Insights from a Training Deployment Phase

by Shelemia Nyamuryekung’e, Andrew Cox, Andres Perea, Richard Estell, Andres F. Cibils, John P. Holland, Tony Waterhouse, Glenn Duff, Micah Funk, Matthew M. McIntosh, Sheri Spiegal, Brandon Bestelmeyer and Santiago Utsumi

Animals 2023, 13(22), 3558; https://doi.org/10.3390/ani13223558 - 17 Nov 2023

Cited by 2 | Viewed by 861

Abstract

Virtual fencing systems have emerged as a promising technology for managing the distribution of livestock in extensive grazing environments. This study provides comprehensive documentation of the learning process involving two conditional behavioral mechanisms and the documentation of efficient, effective, and safe animal training [...] Read more.

Virtual fencing systems have emerged as a promising technology for managing the distribution of livestock in extensive grazing environments. This study provides comprehensive documentation of the learning process involving two conditional behavioral mechanisms and the documentation of efficient, effective, and safe animal training for virtual fence applications on nursing Brangus cows. Two hypotheses were examined: (1) animals would learn to avoid restricted zones by increasing their use of containment zones within a virtual fence polygon, and (2) animals would progressively receive fewer audio-electric cues over time and increasingly rely on auditory cues for behavioral modification. Data from GPS coordinates, behavioral metrics derived from the collar data, and cueing events were analyzed to evaluate these hypotheses. The results supported hypothesis 1, revealing that virtual fence activation significantly increased the time spent in containment zones and reduced time in restricted zones compared to when the virtual fence was deactivated. Concurrently, behavioral metrics mirrored these findings, with cows adjusting their daily travel distances, exploration area, and cumulative activity counts in response to the allocation of areas with different virtual fence configurations. Hypothesis 2 was also supported by the results, with a decrease in cueing events over time and increased reliance with animals on audio cueing to avert receiving the mild electric pulse. These outcomes underscore the rapid learning capabilities of groups of nursing cows in responding to virtual fence boundaries. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

10 pages, 952 KiB

Open AccessArticle

Using Sound Location to Monitor Farrowing in Sows

by Elaine van Erp-van der Kooij, Lois F. de Graaf, Dennis A. de Kruijff, Daphne Pellegrom, Renilda de Rooij, Nian I. T. Welters and Jeroen van Poppel

Animals 2023, 13(22), 3538; https://doi.org/10.3390/ani13223538 - 16 Nov 2023

Cited by 2 | Viewed by 913

Abstract

Precision Livestock Farming systems can help pig farmers prevent health and welfare issues around farrowing. Five sows were monitored in two field studies. A Sorama L642V sound camera, visualising sound sources as coloured spots using a 64-microphone array, and a Bascom XD10-4 security [...] Read more.

Precision Livestock Farming systems can help pig farmers prevent health and welfare issues around farrowing. Five sows were monitored in two field studies. A Sorama L642V sound camera, visualising sound sources as coloured spots using a 64-microphone array, and a Bascom XD10-4 security camera with a built-in microphone were used in a farrowing unit. Firstly, sound spots were compared with audible sounds, using the Observer XT (Noldus Information Technology), analysing video data at normal speed. This gave many false positives, including visible sound spots without audible sounds. In total, 23 of 50 piglet births were visible, but none were audible. The sow’s behaviour changed when farrowing started. One piglet was silently crushed. Secondly, data were analysed at a 10-fold slower speed when comparing sound spots with audible sounds and sow behaviour. This improved results, but accuracy and specificity were still low. When combining audible sound with visible sow behaviour and comparing sound spots with combined sound and behaviour, the accuracy was 91.2%, the error was 8.8%, the sensitivity was 99.6%, and the specificity was 69.7%. We conclude that sound cameras are promising tools, detecting sound more accurately than the human ear. There is potential to use sound cameras to detect the onset of farrowing, but more research is needed to detect piglet births or crushing. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

11 pages, 405 KiB

Open AccessArticle

A Framework for Transparency in Precision Livestock Farming

by Kevin C. Elliott and Ian Werkheiser

Animals 2023, 13(21), 3358; https://doi.org/10.3390/ani13213358 - 29 Oct 2023

Cited by 1 | Viewed by 1291

Abstract

As precision livestock farming (PLF) technologies emerge, it is important to consider their social and ethical dimensions. Reviews of PLF have highlighted the importance of considering ethical issues related to privacy, security, and welfare. However, little attention has been paid to ethical issues [...] Read more.

As precision livestock farming (PLF) technologies emerge, it is important to consider their social and ethical dimensions. Reviews of PLF have highlighted the importance of considering ethical issues related to privacy, security, and welfare. However, little attention has been paid to ethical issues related to transparency regarding these technologies. This paper proposes a framework for developing responsible transparency in the context of PLF. It examines the kinds of information that could be ethically important to disclose about these technologies, the different audiences that might care about this information, the challenges involved in achieving transparency for these audiences, and some promising strategies for addressing these challenges. For example, with respect to the information to be disclosed, efforts to foster transparency could focus on: (1) information about the goals and priorities of those developing PLF systems; (2) details about how the systems operate; (3) information about implicit values that could be embedded in the systems; and/or (4) characteristics of the machine learning algorithms often incorporated into these systems. In many cases, this information is likely to be difficult to obtain or communicate meaningfully to relevant audiences (e.g., farmers, consumers, industry, and/or regulators). Some of the potential steps for addressing these challenges include fostering collaborations between the developers and users of PLF systems, developing techniques for identifying and disclosing important forms of information, and pursuing forms of PLF that can be responsibly employed with less transparency. Given the complexity of transparency and its ethical and practical importance, a framework for developing and evaluating transparency will be an important element of ongoing PLF research. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

10 pages, 3697 KiB

Open AccessArticle

Analysis of the Drinking Behavior of Beef Cattle Using Computer Vision

by Md Nafiul Islam, Jonathan Yoder, Amin Nasiri, Robert T. Burns and Hao Gan

Animals 2023, 13(18), 2984; https://doi.org/10.3390/ani13182984 - 21 Sep 2023

Cited by 2 | Viewed by 1213

Abstract

Monitoring the drinking behavior of animals can provide important information for livestock farming, including the health and well-being of the animals. Measuring drinking time is labor-demanding and, thus, it is still a challenge in most livestock production systems. Computer vision technology using a [...] Read more.

Monitoring the drinking behavior of animals can provide important information for livestock farming, including the health and well-being of the animals. Measuring drinking time is labor-demanding and, thus, it is still a challenge in most livestock production systems. Computer vision technology using a low-cost camera system can be useful in overcoming this issue. The aim of this research was to develop a computer vision system for monitoring beef cattle drinking behavior. A data acquisition system, including an RGB camera and an ultrasonic sensor, was developed to record beef cattle drinking actions. We developed an algorithm for tracking the beef cattle’s key body parts, such as head–ear–neck position, using a state-of-the-art deep learning architecture DeepLabCut. The extracted key points were analyzed using a long short-term memory (LSTM) model to classify drinking and non-drinking periods. A total of 70 videos were used to train and test the model and 8 videos were used for validation purposes. During the testing, the model achieved 97.35% accuracy. The results of this study will guide us to meet immediate needs and expand farmers’ capability in monitoring animal health and well-being by identifying drinking behavior. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

12 pages, 2282 KiB

Open AccessArticle

Effects of a Sprinkler and Cool Cell Combined System on Cooling Water Usage, Litter Moisture, and Indoor Environment of Broiler Houses

by Jonathan Moon, Jan DuBien, Reshma Ramachandran, Yi Liang, Sami Dridi and Tom Tabler

Animals 2023, 13(18), 2939; https://doi.org/10.3390/ani13182939 - 16 Sep 2023

Cited by 1 | Viewed by 1043

Abstract

Climate change is a serious challenge to food production around the world. Sustainability and water efficiency are critical to a poultry industry faced with global production concerns including increased demands for high-quality, affordable animal protein and greater environmental pressures resulting from rising global [...] Read more.

Climate change is a serious challenge to food production around the world. Sustainability and water efficiency are critical to a poultry industry faced with global production concerns including increased demands for high-quality, affordable animal protein and greater environmental pressures resulting from rising global temperatures, flock heat stress, and limits on water availability. To address these concerns, a commercial sprinkler system used in combination with a cool cell system was evaluated against a cool cell system alone for two summer flocks of heavy broilers at Mississippi State University to determine effects of sprinkler technology on cooling water usage, litter moisture, and in-house environments. Environmental data were calculated and recorded throughout the flocks. The combination house exhibited a 2.2 °C (4 °F) increase in daily maximum temperature, lower coincident relative humidity, and a 64% (62,039 L/flock) reduction in average cooling water usage over the cool cell-only house. Litter moisture for the combination house tended to be numerically lower but showed no significant difference at several time points between and across flocks. A combined sprinkler/cool cell system reduced cooling water use by 64% over two flocks compared to a cool cell alone system and decreased in-house relative humidity levels. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

19 pages, 948 KiB

Open AccessArticle

US Swine Industry Stakeholder Perceptions of Precision Livestock Farming Technology: A Q-Methodology Study

by Babatope E. Akinyemi, Faical Akaichi, Janice M. Siegford and Simon P. Turner

Animals 2023, 13(18), 2930; https://doi.org/10.3390/ani13182930 - 15 Sep 2023

Cited by 1 | Viewed by 900

Abstract

This study used the Q-methodology approach to analyze perceptions of precision livestock farming (PLF) technology held by stakeholders directly or indirectly involved in the US swine industry. To see if stakeholders’ perceptions of PLF changed over time as PLF is a rapidly evolving [...] Read more.

This study used the Q-methodology approach to analyze perceptions of precision livestock farming (PLF) technology held by stakeholders directly or indirectly involved in the US swine industry. To see if stakeholders’ perceptions of PLF changed over time as PLF is a rapidly evolving field, we deliberately followed up with stakeholders we had interviewed 6 months earlier. We identified three distinct points of view: PLF improves farm management, animal welfare, and laborer work conditions; PLF does not solve swine industry problems; PLF has limitations and could lead to data ownership conflict. Stakeholders with in-depth knowledge of PLF technology demonstrated elevated levels of optimism about it, whereas those with a basic understanding were skeptical of PLF claims. Despite holding different PLF views, all stakeholders agreed on the significance of training to enhance PLF usefulness and its eventual adoption. In conclusion, we believe this study’s results hold promise for helping US swine industry stakeholders make better-informed decisions about PLF technology implementation. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

8 pages, 1398 KiB

Open AccessCommunication

Training and Adaptation of Beef Calves to Precision Supplementation Technology for Individual Supplementation in Grazing Systems

by Joshua L. Jacobs, Matt J. Hersom, John G. Andrae and Susan K. Duckett

Animals 2023, 13(18), 2872; https://doi.org/10.3390/ani13182872 - 09 Sep 2023

Cited by 1 | Viewed by 789

Abstract

Supplementation of beef cattle can be used to meet both nutrient requirements and production goals; however, supplementation costs influence farm profitability. Common supplementation delivery strategies are generally designed to provide nutrients to the mean of the group instead of an individual. Precision individual [...] Read more.

Supplementation of beef cattle can be used to meet both nutrient requirements and production goals; however, supplementation costs influence farm profitability. Common supplementation delivery strategies are generally designed to provide nutrients to the mean of the group instead of an individual. Precision individual supplementation technologies, such as the Super SmartFeed (SSF, C-Lock Inc., Rapid City, SD, USA), are available but are generally cost prohibitive to producers. These systems require adaptation or training periods for cattle to utilize this technology. The objective of this research was to assess the training and adoption rates of three different groups of cattle (suckling calves, weaned steers, replacement heifers) to the SSF. Successful adaptation was determined if an individual’s supplement intake was above the group average of total allotted feed consumed throughout the training period. Suckling calves (n = 31) underwent a 12 d training period on pasture; 45% of suckling calves adapted to the SSF and average daily intake differed (p < 0.0001) by day of training. Weaned steers (n = 79) were trained in drylot for 13 d. Of the weaned steers, 62% were trained to the SSF, and average daily intake differed (p < 0.0001) by day of training. Replacement heifers (n = 63) grazed tall fescue pastures and had access to SSF for 22 d of training. The success rate of replacement heifers was 73%. For replacement heifers, the daily intake did not differ (p < 0.0001) by day of training. Results indicate production stage may influence cattle adaptation to precision technologies. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

15 pages, 4618 KiB

Open AccessArticle

Broiler Mobility Assessment via a Semi-Supervised Deep Learning Model and Neo-Deep Sort Algorithm

by Mustafa Jaihuni, Hao Gan, Tom Tabler, Maria Prado, Hairong Qi and Yang Zhao

Animals 2023, 13(17), 2719; https://doi.org/10.3390/ani13172719 - 26 Aug 2023

Cited by 4 | Viewed by 1006

Abstract

Mobility is a vital welfare indicator that may influence broilers’ daily activities. Classical broiler mobility assessment methods are laborious and cannot provide timely insights into their conditions. Here, we proposed a semi-supervised Deep Learning (DL) model, YOLOv5 (You Only Look Once version 5), [...] Read more.

Mobility is a vital welfare indicator that may influence broilers’ daily activities. Classical broiler mobility assessment methods are laborious and cannot provide timely insights into their conditions. Here, we proposed a semi-supervised Deep Learning (DL) model, YOLOv5 (You Only Look Once version 5), combined with a deep sort algorithm conjoined with our newly proposed algorithm, neo-deep sort, for individual broiler mobility tracking. Initially, 1650 labeled images from five days were employed to train the YOLOv5 model. Through semi-supervised learning (SSL), this narrowly trained model was then used for pseudo-labeling 2160 images, of which 2153 were successfully labeled. Thereafter, the YOLOv5 model was fine-tuned on the newly labeled images. Lastly, the trained YOLOv5 and the neo-deep sort algorithm were applied to detect and track 28 broilers in two pens and categorize them in terms of hourly and daily travel distances and speeds. SSL helped in increasing the YOLOv5 model’s mean average precision (mAP) in detecting birds from 81% to 98%. Compared with the manually measured covered distances of broilers, the combined model provided individual broilers’ hourly moved distances with a validation accuracy of about 80%. Eventually, individual and flock-level mobilities were quantified while overcoming the occlusion, false, and miss-detection issues. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

12 pages, 3067 KiB

Open AccessArticle

Real-Time Monitoring of Grazing Cattle Using LORA-WAN Sensors to Improve Precision in Detecting Animal Welfare Implications via Daily Distance Walked Metrics

by Shelemia Nyamuryekung’e, Glenn Duff, Santiago Utsumi, Richard Estell, Matthew M. McIntosh, Micah Funk, Andrew Cox, Huiping Cao, Sheri Spiegal, Andres Perea and Andres F. Cibils

Animals 2023, 13(16), 2641; https://doi.org/10.3390/ani13162641 - 16 Aug 2023

Cited by 4 | Viewed by 1565

Abstract

Animal welfare monitoring relies on sensor accuracy for detecting changes in animal well-being. We compared the distance calculations based on global positioning system (GPS) data alone or combined with motion data from triaxial accelerometers. The assessment involved static trackers placed outdoors or indoors [...] Read more.

Animal welfare monitoring relies on sensor accuracy for detecting changes in animal well-being. We compared the distance calculations based on global positioning system (GPS) data alone or combined with motion data from triaxial accelerometers. The assessment involved static trackers placed outdoors or indoors vs. trackers mounted on cows grazing on pasture. Trackers communicated motion data at 1 min intervals and GPS positions at 15 min intervals for seven days. Daily distance walked was determined using the following: (1) raw GPS data (RawDist), (2) data with erroneous GPS locations removed (CorrectedDist), or (3) data with erroneous GPS locations removed, combined with the exclusion of GPS data associated with no motion reading (CorrectedDist_Act). Distances were analyzed via one-way ANOVA to compare the effects of tracker placement (Indoor, Outdoor, or Animal). No difference was detected between the tracker placement for RawDist. The computation of CorrectedDist differed between the tracker placements. However, due to the random error of GPS measurements, CorrectedDist for Indoor static trackers differed from zero. The walking distance calculated by CorrectedDist_Act differed between the tracker placements, with distances for static trackers not differing from zero. The fusion of GPS and accelerometer data better detected animal welfare implications related to immobility in grazing cattle. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

11 pages, 3182 KiB

Open AccessArticle

Estimating the Feeding Time of Individual Broilers via Convolutional Neural Network and Image Processing

by Amin Nasiri, Ahmad Amirivojdan, Yang Zhao and Hao Gan

Animals 2023, 13(15), 2428; https://doi.org/10.3390/ani13152428 - 27 Jul 2023

Cited by 3 | Viewed by 1131

Abstract

Feeding behavior is one of the critical welfare indicators of broilers. Hence, understanding feeding behavior can provide important information regarding the usage of poultry resources and insights into farm management. Monitoring poultry behaviors is typically performed based on visual human observation. Despite the [...] Read more.

Feeding behavior is one of the critical welfare indicators of broilers. Hence, understanding feeding behavior can provide important information regarding the usage of poultry resources and insights into farm management. Monitoring poultry behaviors is typically performed based on visual human observation. Despite the successful applications of this method, its implementation in large poultry farms takes time and effort. Thus, there is a need for automated approaches to overcome these challenges. Consequently, this study aimed to evaluate the feeding time of individual broilers by a convolutional neural network-based model. To achieve the goal of this research, 1500 images collected from a poultry farm were labeled for training the You Only Look Once (YOLO) model to detect the broilers’ heads. A Euclidean distance-based tracking algorithm was developed to track the detected heads, as well. The developed algorithm estimated the broiler’s feeding time by recognizing whether its head is inside the feeder. Three 1-min labeled videos were applied to evaluate the proposed algorithm’s performance. The algorithm achieved an overall feeding time estimation accuracy of each broiler per visit to the feeding pan of 87.3%. In addition, the obtained results prove that the proposed algorithm can be used as a real-time tool in poultry farms. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

11 pages, 1836 KiB

Open AccessArticle

Field Implementation of Forecasting Models for Predicting Nursery Mortality in a Midwestern US Swine Production System

by Edison S. Magalhaes, Danyang Zhang, Chong Wang, Pete Thomas, Cesar A. A. Moura, Derald J. Holtkamp, Giovani Trevisan, Christopher Rademacher, Gustavo S. Silva and Daniel C. L. Linhares

Animals 2023, 13(15), 2412; https://doi.org/10.3390/ani13152412 - 26 Jul 2023

Cited by 1 | Viewed by 955

Abstract

The performance of five forecasting models was investigated for predicting nursery mortality using the master table built for 3242 groups of pigs (~13 million animals) and 42 variables, which concerned the pre-weaning phase of production and conditions at placement in growing sites. After [...] Read more.

The performance of five forecasting models was investigated for predicting nursery mortality using the master table built for 3242 groups of pigs (~13 million animals) and 42 variables, which concerned the pre-weaning phase of production and conditions at placement in growing sites. After training and testing each model’s performance through cross-validation, the model with the best overall prediction results was the Support Vector Machine model in terms of Root Mean Squared Error (RMSE = 0.406), Mean Absolute Error (MAE = 0.284), and Coefficient of Determination (R² = 0.731). Subsequently, the forecasting performance of the SVM model was tested on a new dataset containing 72 new groups, simulating ongoing and near real-time forecasting analysis. Despite a decrease in R² values on the new dataset (R² = 0.554), the model demonstrated high accuracy (77.78%) for predicting groups with high (>5%) or low (<5%) nursery mortality. This study demonstrated the capability of forecasting models to predict the nursery mortality of commercial groups of pigs using pre-weaning information and stocking condition variables collected post-placement in nursery sites. Full article

(This article belongs to the Special Issue 2nd U.S. Precision Livestock Farming Conference)

► Show Figures

Figure 1

Journal Menu

Journal Browser

2nd U.S. Precision Livestock Farming Conference

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (17 papers)

Editorial

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI