Search

Stocking density (SD) may affect broiler productivity and welfare. This study investigated the performance and welfare of Ross 708 and Cobb 700 broilers as affected by four SDs (27, 29, 32, and 44 kg/m2) until day 56. A total of 432 birds per strain were used, with 10, 12, 14, and 18 birds per pen (1.1 m × 1.5 m), corresponding to the respective SDs. Each SD treatment comprised eight replicates. The target SD was determined based on the projected market weight of 4 kg at 56 days of age. The average body weight (BW), feed intake, and feed conversion ratio (FCR) were measured biweekly. Welfare indicators (four broilers per pen), including gait score, feather cleanliness, feather coverage, body temperature, and footpad condition, were evaluated on days 28 and 56. Tibia strength (two broilers per pen) was measured on day 56. The results show that the BW and FCR of both broiler strains were not affected by SD. For both strains, the male broilers exhibited greater bone strength compared to that of the female broilers (129.06 lbf M vs. 91.70 lbf F for Ross, and 130.86 lbf M vs. 117.40 lbf F for Cobb), but the influence of SD on bone strength was found to be significant only for the Ross male broilers. Most welfare indicators were not affected by the SD on days 28 and 56 for either broiler strain, except for feather cleanliness in Ross broilers and footpad in Cobb broilers on day 56, which improved at lower SDs. Strong age and sex effects on the welfare indicators were also identified for both broiler strains. It was concluded that the SD is not a significant factor for broiler productivity, and it has a minor influence on broiler welfare compared to those of age and sex.

This research proposes a low-cost system consisting of a hardware setup and a deep learning-based model to estimate broiler chickens’ feed intake, utilizing audio signals captured by piezoelectric sensors. The signals were recorded 24/7 for 19 consecutive days. A subset of the raw data was chosen, and events were labeled in two classes, feed-pecking and non-pecking (including singing, anomaly, and silence samples). Next, the labeled data were preprocessed through a noise removal algorithm and a band-pass filter. Then, the spectrogram and the signal envelope were extracted from each signal and fed as inputs to a VGG-16-based convolutional neural network (CNN) with two branches for 1D and 2D feature extraction followed by a binary classification head to classify feed-pecking and non-pecking events. The model achieved 92% accuracy in feed-pecking vs. non-pecking events classification with an f1-score of 91%. Finally, the entire raw dataset was processed utilizing the developed model, and the resulting feed intake estimation was compared with the ground truth data from scale measures. The estimated feed consumption showed an 8 ± 7% mean percent error on daily feed intake estimation with a 71% R2 score and 85% Pearson product moment correlation coefficient (PPMCC) on hourly intake estimation. The results demonstrate that the proposed system estimates broiler feed intake at each feeder and has the potential to be implemented in commercial farms.

In this paper, the authors’ previous work regarding a conceptual drone-assisted autonomous pollination system (APS) is extended with regards to path planning and flight control. The APS Path Planning module is extended to optimize the path for missions requiring three-dimensional (3D) path planning, such as the pollination of almond trees. A new method of simplifying the 3D path planning problem by selecting cells or groups of flowers to visit is shown in this paper. This method is numerically demonstrated based on a simulated almond tree. The Flight Control module is extended to incorporate drag into a novel convex-optimization-based flight controller and a new method of collision avoidance called control sequence stitching (CSS). A linear drag model is integrated into the flight control formulation, which is validated through a simulated test flight. The concept of CSS is developed and explained as a method to generate seamless flight trajectories, while still reaping the benefits of convex optimization. This method can be used to generate collision-free trajectories and control commands rapidly for potential real-world APS missions.

ABSTRACT: This study evaluated the welfare and behaviors of Cobb 700 broilers as affected by growth rate (GR) and stocking density (SD). Slower-growth (weight gain < 50 g/d) and medium-growth (weight gain = 50–60 g/d) broilers were produced by providing 57.1% and 78.6% of the feed intake listed in the Cobb 700 production manual for standard (fed ad libitum) broilers (weight gain > 60 g/d). Broilers at all 3 GRs were reared at 2 SDs of 30 and 40 kg/m2. Broiler welfare indicators, including gait score, tibia strength, feather coverage, and footpad condition were evaluated when birds reached 1, 2, and 3 kg of body weight. The activity index was determined by overhead cameras and image processing, and the time spent at feeders was recorded using the radio-frequency identification (RFID) systems. The results show that it took 45 d for standard, 52 d for medium-growth, and 62 d for slower-growth broilers to reach a 3 kg market body weight. Feed conversion ratios (FCR, kg/kg) were 1.57 for standard, 1.67 for medium-growth, and 1.80 for slower-growth broilers. Growth rate and SD had an interaction effect on feather cleanliness (P = 0.03), and belly feather coverage (P = 0.02). Slower-growth broilers were more active and had better feather coverage and gait scores than medium-growth and standard broilers (all P < 0.01) but may feel hungry and depressed, medium-growth broilers spent the most time at the feeder among the 3 growth groups (P = 0.02), and standard broilers showed the best production performance. Broilers at 30 kg/m2 showed better bone strength (P = 0.04), and footpad condition (P < 0.01) compared to those at 40 kg/m2. In conclusion, reducing GR and SD may slightly improve broiler leg health at the high expense of compromised production performance and prolonged production cycles.

Investigating broilers drinking behavior can provide vital information for farmers regarding broilers’ well-being, insights into farm management, and poultry resources to prepare optimal conditions in poultry farms. Therefore, the current study's objective was to assess individual broilers' drinking time using a three-step algorithm based on behavior recognition. First, the proposed algorithm detects the broilers using the U-Net architecture with ResNet50 as the encoder block. Second, the tracking algorithm based on Euclidean distance tracks the detected broilers. Third, if the algorithm recognizes that the tracked broiler satisfies the three-step pattern of drinking behavior, then a 3D convolutional network would estimate the drinking time of the tracked broiler. The proposed algorithm attained an accuracy level of 83.21 % and 88.32 % for the comprehensive estimation of drinking time and the assessment of individual broiler drinking time during each visit to the drinker, respectively. These values prove the efficiency of the proposed algorithm as a real-time and reliable tool in poultry farms.

US nurseries are experiencing a workforce shortage that is expected to intensify. A mixed-mode survey of decision-makers representing the US nursery industry was conducted in 2021. The survey assessed practices used in 2020 to elicit a better understanding of nursery approaches to the challenges presented by persistent labor scarcity. We compare our results with survey data collected ∼15 years earlier at container nurseries. Survey responses revealed that nurseries were undertaking strategies that aimed to improve production efficiency, better recruit and retain employees, and secure other sources of labor to overcome this shortage. Specifically, more than 65% of surveyed US nurseries increased worker wages, and more than 55% of respondents adopted automation to address the labor shortage. Strategies in use by ≥23% of respondents may limit future growth or jeopardize long-term nursery survival. These include diversifying tasks of current employees, reducing production of labor-intensive plants, or delaying expansion plans. Survey results suggested that production tasks excluding irrigation were on average 31% automated or mechanized at container nurseries, an increase from 16% during the prior survey. Field nurseries were 35% automated or mechanized in 2020. Newly developed or yet-to-be developed automated and mechanized technology (AMT) that decision-makers perceive as being helpful were reported. This article explores linkages between nursery characteristics and AMT adoption and highlights research and extension programming initiatives that are needed to help growers make informed decisions regarding adopting automation.

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 [...]

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.

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.

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.

The decline of natural pollinators necessitates the development of novel pollination technologies. In this work, we propose a drone-enabled autonomous pollination system (APS) that consists of five primary modules: environment sensing, flower perception, path planning, flight control, and pollination mechanisms. These modules are highly dependent upon each other, with each module relying on inputs from the other modules. In this paper, we focus on approaches to the flower perception, path planning, and flight control modules. First, we briefly introduce a flower perception method from our previous work to create a map of flower locations. With a map of flowers, APS path planning is defined as a variant of the Travelling Salesman Problem (TSP). Two path planning approaches are compared based on mixed-integer programming (MIP) and genetic algorithms (GA), respectively. The GA approach is chosen as the superior approach due to the vast computational savings with negligible loss of optimality. To accurately follow the generated path for pollination, we develop a convex optimization approach to the quadrotor flight control problem (QFCP). This approach solves two convex problems. The first problem is a convexified three degree-of-freedom QFCP. The solution to this problem is used as an initial guess to the second convex problem, which is a linearized six degree-of-freedom QFCP. It is found that changing the objective of the second convex problem to minimize the deviation from the initial guess provides improved physical feasibility and solutions similar to a general-purpose optimizer. The path planning and flight control approaches are then tested within a model predictive control (MPC) framework where significant computational savings and embedded adjustments to uncertainty are observed. Coupling the two modules together provides a simple demonstration of how the entire APS will operate in practice.

AIM: To explore efficacy of the different kinds of artificial tears treatment in patients with xerophthalmia after phacoemulsification combined with intraocular lens implantation.METHODS: Totally 280 patients(280 eyes)with xerophthalmia after operation in our hospital from January 2015 to June 2016 were selected. According to the different treatment methods, they were divided into control group(n=70; treated with tobramycin and dexamethasone eye ointment 3 times per day for 1wk, levofloxacin eye drops 3 times per day for 1wk, pranoprofen eye drops 4 times per day for 1mo), polyacrylic acid group(n=70; besides the treatment of control group, polyacrylic acid was used 4 times per for 1mo), polyethylene glycol group(n=70; besides the treatment of control group, polyethylene glycol was used 4 times per for 1mo)and sodium hyaluronate group(n=70; besides the treatment of control group, sodium hyaluronate was used 4 times per for 1mo). The tear film break up time(BUT), Schirmer Ⅰ test(SⅠt), symptoms of dry eye and corneal staining in four groups were observed. RESULTS:(1)BUT: The BUT of the four groups significantly increased after treatment(PPPPPPPPPPP>0.05); sodium hyaluronate group was significant lower than other groups in corneal staining score at 3wk and 1mo after treatment(PCONCLUSION: Artificial tears in the treatment of xerophthalmia after cataract phacoemulsification combined with intraocular lens implantation has better clinical efficacy, which contains sodium hyaluronate may be the better than others.

Current approaches to topdressing and weeding operations for rice cultivation present several disadvantages, such as poor precision, low efficiency, serious environmental pollution, and so on. This paper presents a row-controlled fertilizing–weeding machine to improve the precision of fertilizing and weeding operations and to reduce the heavy pollution associated with rice cultivation. A proportional–integral–derivative algorithm was adopted to realize accurate fertilization control, and an automatic driving system for agricultural machinery based on BeiDou navigation was used for accurate row-controlled operation. Accuracy testing and field experiments were carried out. The results show that the fertilization control system can stabilize the speed to within 0.55 s of the desired speed with a standard deviation of around 0.32 r·min−1. The row-controlled operation ensures the lateral deviation is within ± 5 cm at operating speeds below 5 km·h−1. The high uniformity and accuracy of fertilization meet agronomic requirements and rice cultivation standards, and the weeding performance is acceptable at working speeds below 5 km·h−1.

Strawberry growers in Florida suffer from a lack of efficient and accurate yield forecasts for strawberries, which would allow them to allocate optimal labor and equipment, as well as other resources for harvesting, transportation, and marketing. Accurate estimation of the number of strawberry flowers and their distribution in a strawberry field is, therefore, imperative for predicting the coming strawberry yield. Usually, the number of flowers and their distribution are estimated manually, which is time-consuming, labor-intensive, and subjective. In this paper, we develop an automatic strawberry flower detection system for yield prediction with minimal labor and time costs. The system used a small unmanned aerial vehicle (UAV) (DJI Technology Co., Ltd., Shenzhen, China) equipped with an RGB (red, green, blue) camera to capture near-ground images of two varieties (Sensation and Radiance) at two different heights (2 m and 3 m) and built orthoimages of a 402 m2 strawberry field. The orthoimages were automatically processed using the Pix4D software and split into sequential pieces for deep learning detection. A faster region-based convolutional neural network (R-CNN), a state-of-the-art deep neural network model, was chosen for the detection and counting of the number of flowers, mature strawberries, and immature strawberries. The mean average precision (mAP) was 0.83 for all detected objects at 2 m heights and 0.72 for all detected objects at 3 m heights. We adopted this model to count strawberry flowers in November and December from 2 m aerial images and compared the results with a manual count. The average deep learning counting accuracy was 84.1% with average occlusion of 13.5%. Using this system could provide accurate counts of strawberry flowers, which can be used to forecast future yields and build distribution maps to help farmers observe the growth cycle of strawberry fields.

The Cu-12Al-4Ni-1Mn-xB（x=0%，0.1%，0.2%，0.3%，mass fraction，the same below） shape memory alloys were prepared by vacuum arc melting furnace after introducing trace boron element into the alloy. The influence of boron addition on the microstructure， phase transformation， and mechanical properties of the alloy was investigated. The results show that the addition of boron significantly refines the grain size， with the grain size decreasing from hundreds of microns to （11±3.45） μm. The phase transformation temperature shifts to the high-temperature side after boron is added， indicating that the phase transformation process requires higher thermal activation energy. When the boron content is 0.2%， the microhardness of the alloy is enhanced， from （301.7±2.6）HV without adding boron element to （334.3±3.4）HV， which is attributed to grain refinement and the precipitation of hard and brittle borides. The tensile fracture strength and elongation are greatly improved， with the fracture strength increasing from （320±2.6） MPa to （788±17） MPa， and the elongation increasing from （1.44±0.05）% to （3.74±0.12）%. After solid solution annealing， the fracture strength and the elongation are both further increased to （856±10.7）MPa and （5.78±0.16）%， respectively. Analysis indicates that grain refinement strengthening， precipitation strengthening of borides， and solid solution strengthening are the main mechanisms for the improvement of mechanical properties. The fracture mode of the alloy shifts from brittle fracture to ductile fracture.

CuAlMn shape memory alloys have specific target demands in various fields due to excellent thermal stability and high damping properties.However， the mechanical property of the alloy is severely weakened due to the intergranular fracture arising from the coarse grain size. To improve the mechanical properties， the Cu-11.36Al-5Mn-xY （x=0-3， mass fraction/%，the same below） alloys were prepared by using a vacuum arc melting furnace by introducing rare earth Y element. The microstructure of the as-cast CuAlMn alloy was subsequently tailored and homogenized through solid solution and aging treatment. The phase transformation， phase composition， and microstructure of the alloy were respectively characterized by DSC， XRD， metallography and SEM observations. The hardness and mechanical properties of the alloy were tested by using a microhardness tester and a universal materials testing machine. Results show that the addition of Y element effectively refines the CuAlMn alloy grain， and the grain size even reduces from several hundred μm to around 10 μm. The grain refinement is mainly associated with the increased grain nucleation areas and the inhibition of grain growth during the cooling process. Moreover， quite numbers of Y-containing precipitates with the network structure are formed and distributed along the grain boundaries. The hardness of the alloy increases with the enhancement of Y element addition， which is associated with the precipitation of a large amount of hard and brittle containing Y phases.The hardness of the solution-aged sample is higher than that of the cast sample， due to the precipitate distribution throughout the entire matrix and higher volume fraction of precipitates for the former sample.In addition， the compressive and tensile fracture strength of the alloy are significantly improved when the Y content is in the range of 0.1%-0.4%. The strengthening mechanism can be understood by grain refinement strengthening， precipitation strengthening and solution strengthening. The compressive fracture strain of the alloy reaches its maximum when the Y content is 0.4%， while the elongation after fracture exhibits the maximum value with Y content of 0.1%. The changing trend is closely related to the coupling effect between grain refinement and precipitation phases.

The Ti50-0.5xNi50-0.5xZrx series alloys were prepared by vacuum arc melting and subsequent suction casting. Metallographic observation and tensile mechanical tests show that adding trace amount of Zr can reduce grain size and increase higher tensile strength and elongation， however， excessive Zr content can easily lead to the formation of brittle intermetallic compound Zr2Ni and reduce its mechanical properties. The multi-pass cold-rolling deformation and annealing treatment on Ti49.9Ni49.9Zr0.2 alloy were carried out. The results show that the tensile strength σb and the elongation δ of the Ti50－0.5xNi50－0.5xZrx alloys increase with the increase of cold-rolling deformation. Compared with the unrolled alloys， after four-passes cold-rolling deformation， the tensile strength and the elongation after fracture of the alloys increase from 561 MPa，1.14% to 768 MPa ，35.1%，respectively.Microscopic observation of SEM and TEM show that the hard Ti2Ni particles distributed along the grain boundaries during the cold rolling process are sheared and broken， resulting in a discontinuous distribution of refinement. After 700 ℃ annealing process， the deformed microstructure has recovery recrystallization， resulting in the appearance of nanocrystalline and amorphous regions. Moreover， a large number of plate-like nano-twin structures and high-density dislocations appear in the TiNi matrix with the increase of cold-rolling deformation.