This study was conducted to secure basic data for developing technologies to reduce the generation of odor substances by investigating the effects of environmental temperature on growth performance and the generation of odor substances from feces in growing pigs. A total of 16 pigs (Landrace × Yorkshire × Duroc, average body weight 56.49±0.47kg) were randomly assigned to two treatments: thermal-neutral (TN) and heat stress (HS) conditions. The experiments were conducted for two weeks, with average temperature-humidity indices of 68.91±0.09 for TN and 85.98±0.08 for HS. The results showed that HS significantly decreased average daily feed intake (ADFI, 33.3%) and average daily gain (ADG, 25.8%) compared with TN (p<0.05). Non-esterified fatty acid in serum was lower (36.2%) in HS compared with TN (p<0.05). However, protein, blood urea nitrogen, cholesterol, triglyceride, glucose, and IgG in serum showed no difference between HS and TN. Phenol (350.0%) and skatole (416.3%) were significantly higher in HS than in TN (p<0.05). The decrease in growth performance is attributed to reduction in ADFI. The increase in phenol and skatole in HS is presumed to be due to the effect of HS on the metabolism of intestinal microbial composition. Digestion rate, intestinal microbial composition, and urine emissions are known to affect odor substances. Further research on the content of odor substances in urine, nutrient digestion rate, and intestinal microbial composition is considered necessary to determine the exact associations.

On pig farms, the highest mortality rate is observed among nursing piglets. To reduce this mortality rate, farmers need to carefully observe the piglets to prevent accidents such as being crushed and to maintain a proper body temperature. However, observing a large number of pigs individually can be challenging for farmers. Therefore, our aim was to detect the behavior of piglets and sows in real-time using deep learning models, such as YOLOv4-CSP and YOLOv7-E6E, that allow for real-time object detection. YOLOv4-CSP reduces computational cost by partitioning feature maps and utilizing Cross-stage Hierarchy to remove redundant gradient calculation. YOLOv7-E6E analyzes and controls gradient paths such that the weights of each layer learn diverse features. We detected standing, sitting, and lying behaviors in sows and lactating and starving behaviors in piglets, which indicate nursing behavior and movement to colder areas away from the group. We optimized the model parameters for the best object detection and improved reliability by acquiring data through experts. We conducted object detection for the five different behaviors. The YOLOv4-CSP model achieved an accuracy of 0.63 and mAP of 0.662, whereas the YOLOv7-E6E model showed an accuracy of 0.65 and mAP of 0.637. Therefore, based on mAP, which includes both class and localization performance, YOLOv4-CSP showed the superior performance. Such research is anticipated to be effectively utilized for the behavioral analysis of fattening pigs and in preventing piglet crushing in the future.