Individual feedlot beef cattle identification represents a critical component in cattle traceability in the supply food chain. It also provides insights into tracking disease trajectories, ascertaining ownership, and managing cattle production and distribution. Animal biometric solutions, e.g., identifying cattle muzzle patterns (unique features comparable to human fingerprints), may offer noninvasive and unique methods for cattle identification and tracking, but need validation with advancement in machine learning modeling. The objectives of this research were to (1) collect and publish a high-quality dataset for beef cattle muzzle images, and (2) evaluate and benchmark the performance of recognizing individual beef cattle with a variety of deep learning models. A total of 4923 muzzle images for 268 US feedlot finishing cattle (>12 images per animal on average) were taken with a mirrorless digital camera and processed to form the dataset. A total of 59 deep learning image classification models were comparatively evaluated for identifying individual cattle. The best accuracy for identifying the 268 cattle was 98.7%, and the fastest processing speed was 28.3 ms/image. Weighted cross-entropy loss function and data augmentation can increase the identification accuracy of individual cattle with fewer muzzle images for model development. In conclusion, this study demonstrates the great potential of deep learning applications for individual cattle identification and is favorable for precision livestock management. Scholars are encouraged to utilize the published dataset to develop better models tailored for the beef cattle industry.
Obtaining accurate body weight (BW) is crucial for management decisions yet can be a challenge for cow–calf producers. Fast-evolving technologies such as depth sensing have been identified as low-cost sensors for agricultural applications but have not been widely validated for U.S. beef cattle. This study aimed to (1) estimate the body volume of mature beef cows from depth images, (2) quantify BW and metabolic weight (MBW) from image-projected body volume, and (3) classify body condition scores (BCS) from image-obtained measurements using a machine-learning-based approach. Fifty-eight crossbred cows with a mean BW of 410.0 ± 60.3 kg and were between 4 and 6 yr of age were used for data collection between May and December 2021. A low-cost, commercially available depth sensor was used to collect top-view depth images. Images were processed to obtain cattle biometric measurements, including MBW, body length, average height, maximum body width, dorsal area, and projected body volume. The dataset was partitioned into training and testing datasets using an 80%:20% ratio. Using the training dataset, linear regression models were developed between image-projected body volume and BW measurements. Results were used to test BW predictions for the testing dataset. A machine-learning-based multivariate analysis was performed with 29 algorithms from eight classifiers to classify BCS using multiple inputs conveniently obtained from the cows and the depth images. A feature selection algorithm was performed to rank the relevance of each input to the BCS. Results demonstrated a strong positive correlation between the image-projected cow body volume and the measured BW (r = 0.9166). The regression between the cow body volume and the measured BW had a co-efficient of determination (R2) of 0.83 and a 19.2 ± 13.50 kg mean absolute error (MAE) of prediction. When applying the regression to the testing dataset, an increase in the MAE of the predicted BW (22.7 ± 13.44 kg) but a slightly improved R2 (0.8661) was noted. Among all algorithms, the Bagged Tree model in the Ensemble class had the best performance and was used to classify BCS. Classification results demonstrate the model failed to predict any BCS lower than 4.5, while it accurately classified the BCS with a true prediction rate of 60%, 63.6%, and 50% for BCS between 4.75 and 5, 5.25 and 5.5, and 5.75 and 6, respectively. This study validated using depth imaging to accurately predict BW and classify BCS of U.S. beef cow herds.
Understanding the air temperature distribution, ammonia (NH3) and carbon dioxide (CO2) levels in poultry housing systems are crucial to poultry health, welfare, and productivity. In this study, 4 Intelligent Portable Monitoring Units and 7 temperature sensors were installed inside and between the cages and above 2 minimum ventilation fans of a commercial stacked-deck cage laying hen house in the Midwest United States (425,000 laying hens) to continuously monitor the interior environment over a 6-month period. During cold conditions (March 12th–May 22nd), there was a variation noted, with barn center temperatures consistently being highest in the longitudinal and lateral direction (P < 0.001) and the top floor deck warmer than the bottom floor (P < 0.05). During hotter conditions (May 23rd–July 26th), the interior thermal environment was more uniform than during the winter, resulting in a difference only in the longitudinal direction. The daily CO2 and NH3 concentrations were 400 to 4,981 ppm and 0 to 42.3 ppm among the 4 sampling locations, respectively. Both CO2 and NH3 decreased linearly with increasing outside temperatures. The mean NH3 and CO2 concentrations varied with sampling locations and with the outside temperatures (P < 0.001). For CO2, the minimum ventilation sidewall had lower values than those measured in the barn’s center (P < 0.05) during cold weather, while the barn center and the manure room sidewall consistently measured the highest concentrations during warmer weather (P < 0.05). For NH3, the tunnel ventilation inlet end consistently had the lowest daily concentrations, whereas the in-cage and manure drying tunnel sidewall locations measured the highest concentrations (P < 0.001). Higher NH3 and CO2 concentrations were recorded within the cage than in the cage aisle (P < 0.05). The highest NH3 concentration of 42 ppm was recorded above the minimum exhaust fan adjacent to the manure drying tunnel, which indicated that higher pressure (back pressure) in the manure drying tunnel allowed air leakage back into the production area through nonoperating sidewall fan shutters.
Determining ingestive behaviors of dairy cows is critical to evaluate their productivity and health status. The objectives of this research were to (1) develop the relationship between forage species/heights and sound characteristics of three different ingestive behaviors (bites, chews, and chew-bites); (2) comparatively evaluate three deep learning models and optimization strategies for classifying the three behaviors; and (3) examine the ability of deep learning modeling for classifying the three ingestive behaviors under various forage characteristics. The results show that the amplitude and duration of the bite, chew, and chew-bite sounds were mostly larger for tall forages (tall fescue and alfalfa) compared to their counterparts. The long short-term memory network using a filtered dataset with balanced duration and imbalanced audio files offered better performance than its counterparts. The best classification performance was over 0.93, and the best and poorest performance difference was 0.4–0.5 under different forage species and heights. In conclusion, the deep learning technique could classify the dairy cow ingestive behaviors but was unable to differentiate between them under some forage characteristics using acoustic signals. Thus, while the developed tool is useful to support precision dairy cow management, it requires further improvement.
Transport is a critical factor in modern pork production and can seriously affect swine welfare. While previous research has explored thermal conditions during transport, the impact of extreme weather conditions on the trailer thermal environment under industry practices has not been well documented; and the critical factors impacting microclimate are not well understood. To assess the trailer microclimate during transport events, an instrumentation system was designed and installed at the central ceiling level, pig level and floor-level in each of six zones inside a commercial swine trailer. Transport environmental data from 34 monitoring trips (approximately 1–4 h in duration each) were collected from May, 2012, to February, 2013, with trailer management corresponding to the National Pork Board Transport Quality Assurance (TQA) guidelines in 31 of these trips. According to the TQA guidelines, for outdoor temperature ranging from 5 °C (40 °F) to 27 °C (80 °F), acceptable thermal conditions were observed based on the criteria that no more than 10% of the trip duration was above 35 °C (95 °F) or below 0 °C (32 °F). Recommended bedding, boarding and water application were sufficient in this range. Measurements support relaxing boarding guidelines for moderate outdoor conditions, as this did not result in less desirable conditions. Pigs experienced extended undesirable thermal conditions for outdoor temperatures above 27 °C (80 °F) or below 5 °C (40 °F), meriting a recommendation for further assessment of bedding, boarding and water application guidelines for extreme outdoor temperatures. An Emergency Livestock Weather Safety Index (LWSI) condition was observed inside the trailer when outdoor temperature exceeded 10 °C (50 °F); although the validity of LWSI to indicate heat stress for pigs during transport is not well established. Extreme pig surface temperatures in the rear and middle zones of the trailer were more frequently experienced than in the front zones, and the few observations of pigs dead or down upon arrival were noted in these zones. Observations indicate that arranging boarding placement may alter the ventilation patterns inside the trailer.
Heat stress is one of the most detrimental environmental challenges affecting the biological process and the related production performance of farm animals, especially in poultry. Commercial laying hens have been bred (selected) for high egg production, resulting in increased sensitivity to heat stress due to breeding-linked metabolic heat production. In addition, laying hens are prone to heat stress due to their inadequate species-specific cooling mechanisms resulting in low heat tolerance. In addition, hens have no sweat glands and feathering covers almost their entire body to minimize body heat loss. The poultry industry and scientists are developing cooling methods to prevent or reduce heat stress-caused damage to chicken health, welfare, and economic losses. We have designed and tested a cooling system using perches, in which chilled water (10 °C) circulates through a conventional perch passing through the layer cages to offer the cooling potential to improve hen health, welfare, and performance during acute and chronic periods of heat stress (35 °C). This review summarizes the outcomes of a multi-year study using the designed cooled perch system. The results indicate that conducting heat from perching hens directly onto the cooled perch system efficiently reduces heat stress and related damage in laying hens. It provides a novel strategy: perches, one key furnishment in cage-free and enriched colony facilities, could be modified as cooling devices to improve thermal comfort for hens during hot seasons, especially in the tropical and subtropical regions.