In this paper, a water rescue mission system was developed for water safety management areas by utilizing unmanned mobility( drone systems) and AI-based visual recognition technology to enable automatic detection and localization of drowning persons, allowing timely response within the golden time. First, we detected suspected human subjects in daytime and nighttime videos, then estimated human skeleton-based poses to extract human features and patterns using LSTM models. After detecting the drowning person, we proposed an algorithm to obtain accurate GPS location information of the drowning person for rescue activities. In our experimental results, the accuracy of the Drown detection rate is 80.1% as F1-Score, and the average error of position estimation is about 0.29 meters.
Italian ryegrass (Lolium multiflorum Lam., IRG) is a widely cultivated winter forage crop known for its high yield and nutritional value. This study evaluated the processing characteristics and feeding performance of IRG-based pellets in Hanwoo cattle (Bos taurus coreanae) and Korean native black goats (Capra hircus). IRG was harvested at the optimal growth stage and processed into two pellet formulations: IRG ≥80% (with up to 20% soybean meal) and 100% IRG. Feeding trials were conducted under ad libitum feeding conditions. Hanwoo cattle showed higher intake of 100% IRG pellets (7.9 kg/day/head) than IRG ≥80% pellets (7.5 kg/day/head, p<0.05), with similar average daily gain (0.9 ± 0.4 kg/day/head). Conversely, black goats exhibited significantly lower intake of IRG ≥80% pellets (54.6 g/day/head) compared to 100% IRG pellets (266 g/day/head), likely due to reduced palatability associated with soybean meal inclusion. These findings suggest that IRG pellets are suitable for Hanwoo cattle, while further optimization of pellet size and formulation is required to improve acceptance in goats. Future studies should assess long-term impacts on digestion, rumen fermentation, and metabolic responses.
This study was conducted from 2022 to 2024 at the Grassland and Forage Crops Division, National Institute of Animal Science (RDA), in Cheonan, Korea, to develop a medium-maturing variety of Italian ryegrass (Lolium multiflorum Lam.). The newly developed tetraploid cultivar, named ‘Spider’, is characterized by its green leaves, semi-erect growth habit in late autumn, and erect growth habit in mid-spring. With a heading date of May 16, ‘Spider’ is classified as a medium-maturing variety. Compared to the control cultivar ‘Kowinmaster’, ‘Spider’ has a 1.0 mm wider leaf blade, a 1.6 cm longer leaf blade, and is 5 cm taller in plant height. Its dry matter yield (10,169 kg/ha) is significantly higher than that of ‘Kowinmaster’ (p<0.05). The crude protein content of ‘Spider’ is 10.4%, which is 0.2% higher than that of the control. Additionally, ‘Spider’ has a neutral detergent fiber (NDF) content of 49.5% and an acid detergent fiber (ADF) content of 26.6%, showing a 2.2% lower NDF and a 0.2% higher ADF compared to ‘Kowinearly’.
The commercial feed additive, native rumen microbes (RC), derived from a diverse microbial community isolated from the rumen of Hanwoo steers is being explored to enhance rumen fermentation and improve ruminant feed utilization. This study evaluated the impact of native rumen microbes supplementation on methane emissions, microbial diversity, and fermentation efficiency on in vitro assessment. Treatments were as follows: CON (basal diet, without RC); T1 (basal diet + 0.1% RC); T2 (basal diet + 0.2% RC). Rumen fermentation parameters, total gas, and methane production were assessed at 12, 24, and 48 h of incubations. The in vitro gas production was carried out using the Ankom RF Gas Production System. Supplementation of RC significantly reduced the total gas production at 12, 24, and 48 hours of incubation (p < 0.05). Volatile fatty acid concentrations were increased, while acetate and propionate were decreased (p < 0.05) at 48 h by the supplementation of RC. Notably, the 0.1% inclusion level of RC significantly reduced methane production by 28.30% and 21.21% at 12 and 24 hours. Furthermore, microbial diversity analysis revealed significant shifts (p < 0.05) in bacterial composition between the control and treatment groups, while supplementation also promoted the growth of bacterial populations, such as Succiniclasticum. These findings suggest that native rumen microbes supplementation, particularly at 0.1% inclusion level, can enhance rumen microbial composition while significantly reducing methane production in vitro.
The casting manufacturing process of aluminum automotive wheels often involves processing various wheel models during stages such as flow forming, machining, packaging, and delivery. Traditionally, separate equipment or production lines were required for each model, which led to higher facility investment costs and increased labor costs for classification. However, the implementation of machine learning-based model classification technology has made it possible to automatically and accurately distinguish between different wheel models, resulting in significant cost savings and enhanced production efficiency. Additionally, this approach helps prevent product mix-ups during the final inspection process and allows for the quick and precise identification of wheel models during packaging and delivery, reducing shipping errors and improving customer satisfaction. Despite these benefits, the high cost of machine learning equipment presents a challenge for small and medium-sized enterprises(SMEs) to adopt such technologies. Therefore, this paper analyzes the characteristics of existing machine learning architectures applicable to the automotive wheel manufacturing process and proposes a custom CNN(Convolutional Neural Network) that can be used efficiently and cost-effectively.
The utilization of pig slurry (PS) as an organic fertilizer plays a pivotal role in nutrient recycling within agricultural systems. However, this practice concomitantly leads nitrogen (N) losses through ammonia (NH₃) volatilization and nitrous oxide (N₂O) emissions. The objective of this study was to investigate the effect of wood biochar on mitigating NH3 and N2O emissions and enhancing N retention from PS-applied soil, and plant biomass production during the vegetative growth of rapeseed (Brassica napus L.). The experiment consisted of three treatments: 1) water (non-PS), 2) PS, and 3) PS combined with wood biochar (PS+WB). The PS+WB treatment resulted in the maintenance of elevated soil water content during the experimental period. The PS+WB treatment significantly enhanced soil nitrogen retention compared to PS alone, maintaining higher total N and NH₄⁺-N levels while reducing NO₃⁻ -N accumulation. Wood biochar application also leds to substantial reductions in NH₃ and N₂O emissions, mitigating environmental N losses. The PS+WB treatment resulted in an improvement of shoot biomass, crude protein content, and total digestible nutrients, indicating enhanced forage quality. The increased soil moisture content in PS+WB further contributed to plant growth benefits. These findings demonstrate that wood biochar is an effective amendment for improving nitrogen retention, reducing gaseous N emissions, and enhancing crop productivity in PS-amended soils.
육성한 화단국화 품종인 황색 국화(Chrysanthemum morifolium Ramat.)인 ‘한아름볼(Hanarum Ball)’은 충남농업기술원 화훼 연구소에서 모본 ‘Gigi Gold’와 부본 ‘Jinny Ball’을 이용하여 육성되었다. ‘한아름볼’ 품종은 2014년에 인공 교배를 통해 개 발되었으며, 2015년부터 2017년까지 품종 특성을 조사한 후 2017년에 최종 선발되었다. ‘한아름볼’의 초형은 반구형으로, 노랑색 꽃잎(Yellow 5B)을 가진 반겹꽃을 지니고 있으며, 개화 기는 9월 21일이다. 초장은 36.0cm로, 초폭은 66.0cm, 화폭 은 4.1cm, 본당 착화수는 1,147개, 꽃잎수는 81.0개이며, 엽색 은 녹색(Green 137B)이어서, 대조품종인 ‘금방울’과 유사한 형 태와 색을 가지고 있으나, 꽃크기와 착화수, 개화시기에서 차이 를 보였다. ‘한아름볼’은 도로변이나 화단 등 조경용으로 활용 가능하며, 화훼 농가에 새로운 소득원을 제공할 수 있는 품종으 로 기대된다.