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.

(1) Background: With the development of cold chain logistics in recent years, the demand for refrigerated display cases has greatly increased in the home and commercial markets. However, the difference of temperature and humidity between each layer of refrigerated display cabinet is great, which affects the health of consumers. In order to reduce the temperature difference for each layer in a cabinet and to improve the temperature uniformity inside the cabinet, an open-hole shelf is designed according to the principle of aerodynamics. (2) Methods: The influence of different shelf aperture ratios on the periodic temperature fluctuation, average temperature, temperature non-uniformity coefficient, and temperature maintenance coefficient inside the cabinet is studied by means of experiments with pork. (3) Results: The results show that when the aperture ratio increases from 0% to 90%, the average maximum temperature in a single cycle in the cabinet shows a trend of first decreasing and then increasing. The minimum temperature difference in the cabinet is 4.3 °C, and the corresponding aperture ratio is 25%. (4) Conclusions: The results show that 25% is the optimal aperture ratio for a shelf in the refrigerated display cabinet. The results provide a better reference for optimization of the structure and temperature in an open refrigerated display cabinet.

A novel intelligent wet feed system was designed to accurately match the dynamic nutritional requirements of lactating sows. An experimental study was conducted to compare the performance of this novel feeding system with the traditional manual feeding method. Twenty-two first-parity sows selected through screening were randomly divided into intelligent feeding and manual feeding groups. Feed intake and backfat thickness changes during lactation were monitored, and the growth performance of 30 piglets was assessed. The effects of feeding methods on feed intake, backfat thickness, and piglet growth were evaluated. Results showed that the intelligent group increased the feed intake under high feeding conditions, with feed conversion efficiency improved by 21.8%. A backfat conservation effect was observed, with backfat loss reduced by 82.5% and the daily loss rate being only 16.6% of that in the manual group. Piglet growth performance was improved, with the peak growth rate increased by 14.2% and the growth inflection point brought forward by 10.6%, both reaching medium to large effect sizes. The results indicate that the intelligent wet feeding system improved feed conversion efficiency in sows under high feeding conditions, reduced backfat loss, and enhanced piglet growth rates. These findings provide references for the application of intelligent feeding technology and offer technical pathways for intelligent and efficient pig farming.