Significant intensification in livestock farming has become prevalent to meet the increasing meat production demand, resulting in a higher density of pigs in relatively small areas in a commercial swine building. The subsequent challenges of maintaining the quality of both routine management and environmental comfort of pigs to minimize the loss of both pigs’ health and welfare can be attained by implementing autonomous monitoring and intelligent management decisions based on precision livestock farming (PLF). A three-layer wireless sensor network (WSN) based on ZigBee technology has been devised to monitor four environmental parameters in real-time, namely: temperature, relative humidity, concentrations of carbon dioxide and ammonia in a commercial gestating sow house. The overall packet loss rate of the WSN system which reported 16,371 records from its 41 indoor slave nodes in a 10-min interval for three consecutive days was 4%. The carbon dioxide sensors had an average outlier rate of 6.5% after a series of preprocessing procedures. The spatial and temporal characteristics showed that the carbon dioxide level exceeded the limit of 2700 mg/m³ twice during both 07:00–08:00 and 14:00–15:00. Besides, the overall NH₃ concentration in the swine building was maintained in a relatively low-level range with a maximum of less than 8 mg/m³. In sum, the real-time monitoring and timely intervention of microclimate in this commercial gestating sow house can be achieved by deploying this WSN system, thereby making it possible to provide an intelligent decision on precise management of livestock automatically.

In this paper, a lightweight channel-wise attention model is proposed for the real-time detection of five representative pig postures: standing, lying on the belly, lying on the side, sitting, and mounting. An optimized compressed block with symmetrical structure is proposed based on model structure and parameter statistics, and the efficient channel attention modules are considered as a channel-wise mechanism to improve the model architecture.The results show that the algorithm’s average precision in detecting standing, lying on the belly, lying on the side, sitting, and mounting is 97.7%, 95.2%, 95.7%, 87.5%, and 84.1%, respectively, and the speed of inference is around 63 ms (CPU = i7, RAM = 8G) per postures image. Compared with state-of-the-art models (ResNet50, Darknet53, CSPDarknet53, MobileNetV3-Large, and MobileNetV3-Small), the proposed model has fewer model parameters and lower computation complexity. The statistical results of the postures (with continuous 24 h monitoring) show that some pigs will eat in the early morning, and the peak of the pig’s feeding appears after the input of new feed, which reflects the health of the pig herd for farmers.

The feeding behavior of poultry at a young age is very likely to determine the final growth of the chicken, and can also reflect the feeding status and the health status. It is also of great significance for breeding. This paper describes the development and testing of a real-time automated system and a single passage for monitoring the individual feed intake and body weight of poultry. This system integrates an automatic feeding mechanism, an RFID reading module, a weight scale, a feed scale, and a drop weighting scale. The system uses analog circuits and digital filtering to improve the weighing accuracy, and directly measures the amount of feed falling to the ground using a high-precision weighing scale. Through the sequential opening and closing of a sliding door, group-housed chickens are separated so that the young ones are fed individually. As a result of the experiment, we learned that a young chicken grows at a rate of about 8.88 g/day, and the food conversion rate (FCR) is about 4.4, which proves that this system matches the single passage and can accurately monitor the body weight change and feeding behavior of young chickens.

A novel method is proposed based on the improved YOLOV5 and feeding functional area proposals to identify the feeding behaviors of nursery piglets in a complex light and different posture environment. The method consists of three steps: first, the corner coordinates of the feeding functional area were set up by using the shape characteristics of the trough proposals and the ratio of the corner point to the image width and height to separate the irregular feeding area; second, a transformer module model was introduced based on YOLOV5 for highly accurate head detection; and third, the feeding behavior was recognized and counted by calculating the proportion of the head in the located feeding area. The pig head dataset was constructed, including 5040 training sets with 54,670 piglet head boxes, and 1200 test sets, and 25,330 piglet head boxes. The improved model achieves a 5.8% increase in the mAP and a 4.7% increase in the F1 score compared with the YOLOV5s model. The model is also applied to analyze the feeding pattern of group-housed nursery pigs in 24 h continuous monitoring and finds that nursing pigs have different feeding rhythms for the day and night, with peak feeding periods at 7:00–9:00 and 15:00–17:00 and decreased feeding periods at 12:00–14:00 and 0:00–6:00. The model provides a solution for identifying and quantifying pig feeding behaviors and offers a data basis for adjusting the farm feeding scheme.

Accurate recognition of agricultural pests is crucial for effective pest management and reducing pesticide usage. In recent research, deep learning models based on residual networks have achieved outstanding performance in pest recognition. However, challenges arise from complex backgrounds and appearance changes throughout the pests’ life stages. To address these issues, we develop a multi-task learning framework utilizing the discriminative attention multi-network (DAM-Net) for the main task of recognizing intricate fine-grained features. Additionally, our framework employs the residual network-50 (ResNet-50) for the subsidiary task that enriches texture details and global contextual information. This approach enhances the main task with comprehensive features, improving robustness and precision in diverse agricultural scenarios. An adaptive weighted loss mechanism dynamically adjusts task loss weights, further boosting overall accuracy. Our framework achieves accuracies of 99.7% on the D0 dataset and 74.1% on the IP102 dataset, demonstrating its efficacy in training high-performance pest-recognition models.

The moisture content of Yinghong No. 9 tea leaves is an important indicator for their processing. The traditional method used to detect the moisture content of tea leaves is not suitable for large-scale production. To improve the efficiency of tea processing, a moisture content detection system for Yinghong No. 9 tea leaves based on machine vision was developed, and the relationship between the moisture content and the fresh tea leaves was researched. Firstly, nine color features and five texture features of the tea leaves images were extracted, and two different tea leaves databases were constructed based on linear discriminant analysis (LDA) and principal component analysis (PCA). Secondly, two models of moisture prediction for fresh tea leaves were built using a backpropagation (BP) neural network, which were then optimized by particle swarm optimization (PSO) and a genetic algorithm (GA), respectively. After, the two preprocessing methods and the two optimization algorithms were cross-combined to optimize the models for moisture content prediction. Finally, the models above were filtered using segmental analysis for the segmental moisture content prediction. It was verified by experiments that the coefficient of determination (R²) of the combined model of PCA-GA-BP and PCA-PSO-BP was 94.1073%, the RMSE was 1.1490%, and the MAE was 0.9982%. The results of this paper can help in the instantaneous detection of the moisture content of fresh tea leaves during processing, improving the production efficiency of Yinghong No. 9 tea.