Assessing Environmental Control Strategies in Cage-Free Egg Production Systems: Effect on Spatial Occupancy and Natural Behaviors

Interindividual distances and orientations of laying hens under 8 stocking densities measured by integrative deep learning techniques

Interindividual distances and orientations of laying hens provide quantitative measures to calculate and optimize space allocations for bird flocks. However, these metrics were often measured manually and have not been examined for different stocking densities of laying hens. The objectives of this study were to 1) integrate and develop several deep learning techniques to detect interindividual distances and orientations of laying hens; and 2) examine the 2 metrics under 8 stocking densities via the developed techniques. Laying hens (Jingfen breed, a popular hen breed in China) at 35 wk of age were raised in experimental compartments at 8 different stocking densities of 3,840, 2,880, 2,304, 1,920, 1,646, 1,440, 1,280, and 1,152 cm2•bird-1 (3-10 hens per compartment, respectively), and cameras on the top of the compartments recorded videos for further analysis. The designed deep learning image classifier achieved over 99% accuracy to classify bird's perching status and excluded frames with bird perching to ensure that all birds analyzed were on the same horizontal plane, reducing calculation errors. The YOLOv5m oriented object detection model achieved over 90% precision, recall, and F1 score in detecting birds in compartments and can output bird centroid coordinates and angles, from which interindividual distances and orientations were calculated based on pairs of birds. Laying hens maintained smaller minimum interindividual distances in higher stocking densities. They were in an intersecting relationship with conspecifics for over 90% of the time. The developed integrative deep learning techniques and behavior metrics provide animal-based measurement of space requirement for laying hens.

Numerical Simulation of Airborne Disease Spread in Cage-Free Hen Housing with Multiple Ventilation Options

The current ventilation designs of poultry barns have been present deficiencies with respect to the capacity to protect against disease exposure, especially during epidemic events. An evolution of ventilation options is needed in the egg industry to keep pace with the advancing transition to cage-free production. In this study, we analyzed the performances of four ventilation schemes for constraining airborne disease spread in a commercial cage-free hen house using computational fluid dynamics (CFD) modeling. In total, four three-dimensional models were developed to compare a standard ventilation configuration (top-wall inlet sidewall exhaust, TISE) with three alternative designs, all with mid-wall inlet and a central vertical exhaust. A one-eighth scale commercial floor-raised hen house with 2365 hens served as the model. Each ventilation configuration simulated airflow and surrogate airborne virus particle spread, assuming the initial virus was introduced from upwind inlets. Simulation outputs predicted the MICE and MIAE models maintained a reduced average bird level at 47% and 24%, respectively, of the standard TISE model, although the MIRE model predicted comparable virus mass fraction levels with TISE. These numerical differences unveiled the critical role of centrally located vertical exhaust in removing contaminated, virus-laden air from the birds housing environment. Moreover, the auxiliary attic space in the MIAE model was beneficial for keeping virus particles above the bird-occupied floor area.

Design and Implementation of Poultry Farming Information Management System Based on Cloud Database

Aiming at breaking down the bottleneck problems of different scale of poultry farms, the low profitability of poultry farming, and backward information management in China, a safe and efficient information management system for poultry farming was designed. This system consists of (1) a management system application layer, (2) a data service layer, and (3) an information sensing layer. The information sensing layer obtains and uploads production and farming information through the wireless sensor network built in the poultry house. The use of a cloud database as an information storage carrier in the data service layer eliminates the complex status of deploying local server clusters, and it improves the flexibility and scalability of the system. The management system application layer contains many sub-function modules including poultry disease detection functions to realize the visual management of farming information and health farming; each module operates independently and cooperates with each other to form a set of information management system for poultry farming with wide functional coverage, high service efficiency, safety, and convenience. The system prototype has been tested for the performance of wireless sensor network and cloud database, and the results show that the prototype is capable of acquiring and managing poultry farming information.