Sensors have been used in various agricultural production scenarios due to significant advances in the Agricultural Internet of Things (Ag-IoT), leading to smart agriculture. Intelligent control or monitoring systems rely heavily on trustworthy sensor systems. Nonetheless, sensor failures are likely due to various factors, including key equipment malfunction or human error. A faulty sensor can produce corrupted measurements, resulting in incorrect decisions. Early detection of potential faults is crucial, and fault diagnosis techniques have been proposed. The purpose of sensor fault diagnosis is to detect faulty data in the sensor and recover or isolate the faulty sensors so that the sensor can finally provide correct data to the user. Current fault diagnosis technologies are based mainly on statistical models, artificial intelligence, deep learning, etc. The further development of fault diagnosis technology is also conducive to reducing the loss caused by sensor failures.

To monitor multiple environmental factors of henhouses in modern chicken farms, a henhouse online monitoring system based on wireless sensor network was developed using wireless sensor technology and computer network technology. Sensor data compensation and correction were designed to be achieved using software and data fitting methods, data reliable transmission achieved using a data loss recovery strategy, and data missing during monitoring addressed using a self-decision and online filling method. Operation test of the system showed that: The system was economic and reliable; it enabled wireless monitoring and Web display of the environmental factors of a henhouse; and the root mean square errors (RMSEs) between the estimated values from the self-decision and on-line filling method and experimental values of the four environmental factors were 0.1698, 3.0859, 77 and 0.094, respectively, indicative of high estimation accuracy. The system can provide support for modern management of henhouses and can be transplanted to related monitoring scenarios in the agricultural field.

Rice seed variety purity, an important index for measuring rice seed quality, has a great impact on the germination rate, yield, and quality of the final agricultural products. To classify rice varieties more efficiently and accurately, this study proposes a multimodal l fusion detection method based on an improved voting method. The experiment collected eight common rice seed types. Raytrix light field cameras were used to collect 2D images and 3D point cloud datasets, with a total of 3194 samples. The training and test sets were divided according to an 8:2 ratio. The experiment improved the traditional voting method. First, multiple models were used to predict the rice seed varieties. Then, the predicted probabilities were used as the late fusion input data. Next, a comprehensive score vector was calculated based on the performance of different models. In late fusion, the predicted probabilities from 2D and 3D were jointly weighted to obtain the final predicted probability. Finally, the predicted value with the highest probability was selected as the final value. In the experimental results, after late fusion of the predicted probabilities, the average accuracy rate reached 97.4%. Compared with the single support vector machine (SVM), k-nearest neighbors (kNN), convolutional neural network (CNN), MobileNet, and PointNet, the accuracy rates increased by 4.9%, 8.3%, 18.1%, 8.3%, and 9%, respectively. Among the eight varieties, the recognition accuracy of two rice varieties, Hannuo35 and Yuanhan35, by applying the voting method improved most significantly, from 73.9% and 77.7% in two dimensions to 92.4% and 96.3%, respectively. Thus, the improved voting method can combine the advantages of different data modalities and significantly improve the final prediction results.

Heavy broilers exposed to hot summer conditions experience fluctuations in surface temperatures due to heat stress, which leads to decreased performance. Maintaining a bird’s homeostasis depends on several environmental factors (temperature, relative humidity, and air velocity). It is important to understand the responses of birds to environmental factors and the amount of heat loss to the surrounding environment to create thermal comfort for the heavy broilers for improved performances and welfare. This study investigates the variation in surface temperatures of heavy broilers under high and low air velocity treatments. Daytime, age and bird location’s effect on the surface temperature variation was also examined. The experiment was carried out in the poultry engineering laboratory of North Carolina State University during summers of 2017, 2018, and 2019 as a part of a comprehensive study on the effectiveness of wind chill application to mitigate heat stress on heavy broilers. This live broiler heat stress experiment was conducted under two dynamic air velocity treatments (high and low) with three chambers per treatment and 44 birds per chamber. Surface temperatures of the birds were recorded periodically through the experimental treatment cycles (flocks, 35–61 d) with infrared thermography in the morning, noon, evening, and nighttime. The overall mean surface temperature of the broilers under two treatments was found to be 35.89 ± 2.37 °C. The variation in surface temperature happened due to air temperature, thermal index, air velocity, bird’s age, daytime, and position of birds inside the experimental chambers. The surface temperatures were found lower under high air velocity treatment and higher under low air velocity treatment. During the afternoon time, the broilers’ surface temperatures were higher than other times of the day. It was also found that the birds’ surface temperature increased with age and temperature humidity indices. Based upon the experimental data of five flocks, a simple linear regression model was developed to predict surface temperature from the birds’ age, thermal indices, and air velocity. It will help assess heavy broilers’ thermal comfort under heat stress, which is essential to provide a comfortable environment for them.

In this paper, a CFD (computational fluid dynamics) numerical calculation was employed to examine whether the ventilation system of the self-designed smart broiler house meets the requirements of cooling and ventilation for the welfare in poultry breeding. The broiler chamber is powered by two negative pressure fans. The fans are designed with different frequencies for the ventilation system according to the specific air temperature in the broiler chamber. The simulation of ventilation in the empty chamber involved five working conditions in this research. The simulation of ventilation in the broiler chamber and the simulation of the age of air were carried out under three working conditions. According to the measured dimensions of the broiler chamber, a three-dimensional model of the broiler chamber was constructed, and then the model was simplified and meshed in ICEM CFD (integrated computer engineering and manufacturing code for computational fluid dynamics). Two models, i.e., the empty chamber mesh model and the chamber mesh model with block model, were imported in the Fluent software for calculation. In the experiment, 15 measurement points were selected to obtain the simulated and measured values of wind velocity. For the acquired data on wind velocity, the root mean square error (RMSE) was 19.1% and the maximum absolute error was 0.27 m/s, which verified the accuracy of the CFD model in simulating the ventilation system of the broiler chamber. The boundary conditions were further applied to the broiler chamber model to simulate the wind velocity and the age of air. The simulation results show that, when the temperature was between 32 and 34 °C, the average wind velocity on the plane of the corresponding broiler chamber (Y = 0.2 m) was higher than 0.8 m/s, which meets the requirement of comfortable breeding. At the lowest frequency of the fan, the oldest age of air was less than 150 s, which meets the basic requirement for broiler chamber design. An optimization idea is proposed for the age of air analysis under three working conditions to improve the structure of this smart broiler chamber.

Novel multiple object tracking method for yellow feather broilers in a flat breeding chamber based on improved YOLOv3 and deep SORT