Conventional fixed-time traffic signal operations at urban intersections are typically based on prescheduled plans that presume stable and recurring traffic patterns, particularly during peak commuting hours. However, recent societal changes—including flexible work schedules, telecommuting, and evolving workweek structures—have introduced greater variability in traffic demand, thereby diminishing the effectiveness of traditional peak-hour-focused control strategies. This study investigated the performance of an AI-based adaptive traffic signal control system that operated independently of predefined time plans. A field demonstration was conducted in Jeju City, South Korea, where the system was deployed in both the cyclic and acyclic operation modes. By leveraging real-time traffic data obtained from AI-enabled video detectors, the system adjusted the signal timings on a per-second basis in response to dynamic traffic conditions. The performance was evaluated against the conventional time-of-day (TOD) control method under diverse traffic scenarios, including typical weekdays, weekends, and local event days. The AI-based system achieved substantial reductions in intersection delays—24.3% on weekdays, 22.2% on weekends, and 17.1% on event days—compared with the TOD baseline. Moreover, it preserved a comparable level of traffic progression (measured by the proportion of non-stop vehicle flows) even during acyclic operations. The greatest efficiency gains were observed during the nighttime and low-traffic periods, underscoring the capacity of the system to minimize unnecessary delays under variable conditions. These results highlighted the potential of AI-based adaptive signal control as a viable alternative to conventional fixed-time operations, offering enhanced responsiveness and operational flexibility in increasingly complex urban traffic environments. Future research will focus on scaling the system to larger networks and developing integrated optimization strategies across multiple intersections.

본 논문은 아프리카 마다가스카르의 의료 인력 부족과 기본 외과 수술 접근성의 제약 문제를 해결하기 위해 시행된 지구병원 기본 외과 의사 양성 프로그램을 소개한다. 2017년부터 기획되어 2023~2024년 실행된 본 사업은 한국의 정부 및 비정부 기관 (KOICA, AFF, WELL International, 한국누가회 등)과 마다가스카르 보건부 및 국립보건원 (INSPC)의 협력으로 추진되었다. 마다가스카르 정부 소속 현지 공무원 의사 20명을 선발해 2년간 7가지 핵심 외과술기 중심의 훈련을 시행하고, 이후 5년간 비수도권 지구병원에 배치함으로써 약 500만 명의 주민에게 외과 진료 접근성을 제공하였다. 마다가스카르 정부의 급여 지원과 제도화 의지는 이 프로그램의 효과 및 지속 가능성을 보여주는 성과이다. 본 프로그램은 선교적 가치에 기반한 현지인 역량 강화형 의료선교 모델로, 향후 사업의 확대와 유사한 환경의 저개발국에서 적용 가능한 보건의료 인력개발 전략의 하나로서 그 가능성과 의의를 가진다.

본 연구는 병원성 박테리아 Agrobacterium rhizogenes에 대해 저압 수은 UV-C 소독 시스템의 살균 성능을 정량적으로 평가하고, 램프 소비전력과 유량의 조합에 따른 소독 효율에 미치는 영향을 분석하였다. 농업용수는 경상남도 사천시 소 재 세 농가(A, B, C)와 함안군 군북면의 한 농가(D)에서 채취 하였으며, 목표 병원균을 인위적으로 접종한 뒤 실험을 수행 하였다. 실험은 1차와 2차로 구분되며, 1차 실험은 소비전력 40, 75, 105W와 유량 10, 15, 30L/min의 3×3 조합으로 구성 되었고, 2차 실험은 소비전력 75W 조건 하에서 고유량(60, 120L/min) 조건을 적용하였다. 대부분의 실험 조건에서 박테 리아가 완전히 사멸되었으며, 유일하게 생균이 검출된 조건 (#33, 75W－60L/min)에서만 생균이 검출되었다. 그러나 해 당 조건에서도 생균수는 UV 비처리 대조군(#37)에 비해 약 4.9log 수준 감소하여 유의미한 소독 효과가 확인되었다. 이 러한 결과는 고유량 조건에서도 충분한 UV 조사량이 확보된 다면 안정적인 소독이 가능함을 시사한다. 본 연구는 저압 UV-C 시스템의 운전 변수에 따라 살균 효율이 어떻게 달라지 는지를 실험적으로 입증하였으며, 농업용수 처리에 있어 해 당 기술의 실용적 적용 가능성을 제시하였다.

Springtails (class Collembola) play a crucial role in soil ecosystems. They are commonly used as standard species in soil toxicity assessments. According to the ISO 11267 guidelines established by the International Organization for Standardization (ISO), Allonychiurus kimi uses adult survival and juvenile production as toxicity assessment endpoint. Conventional toxicity assessment methods require manually counting adults and larvae under a microscope after experiments, which is time-consuming and laborintensive. To overcome these limitations, this study developed a model using YOLOv8 to detect and count both adults and juveniles of A. kimi. An AI model was trained using a training dataset and evaluated using a validation dataset. Both training and validation datasets used for AI model were created by picturing plate images that included adults and larvae. Statistical comparison of validation dataset showed no significant difference between manual and automatic counts. Additionally, the model achieved high accuracies (Precision=1.0, Recall=0.95 for adults; Precision=0.95, Recall=0.83 for juveniles). This indicates that the model can successfully detect objects. Additionally, the system can automatically measure body areas of individuals, enabling more detailed assessments related to growth and development. Therefore, this study establishes that AI-based counting methods in toxicity assessments with offer high levels of accuracy and efficiency can effectively replace traditional manual counting methods. This method significantly enhances the efficiency of large-scale toxicity evaluations while reducing researcher workload.

감마-오리자놀(γ-oryzanol)은 phytochemical의 한 종류로 항산화, 항염증, 항암, 항당뇨, 콜레스테롤 감소 등의 효능이 알려져 있다. 본 연구에서는 현미를 백미로 도정할 때 부산물로 발생하는 미강으로부터 생리활성물질 중의 하나인 γ-oryzanol 함량이 높은 추출조건에서의 분말을 제조하고, 이를 쌀국수에 첨가하여 항산화성이 개선된 국수를 제조하고자 하였다. 미강을 에탄올 농도 0, 20, 40, 80%의 에탄올로 추출한 결과 80% 에탄올로 추출한 추출분말에서 γ-oryzanol 함량이 가장 높았으며, DPPH 소거능과 ABTS 소거능이 가장 높았다. 미강추출분말의 γ-oryzanol의 함량을 높이기 위하여 Saccharomyces cerevisiae로 미강을 고상발효시킨 후 80% 에탄올로 추출하여 동결건조시킨 분말의 γ-oryzanol의 함량은 발효시키지 않은 미강을 추출분말보다 약 2.18배 증가하였으며, DPPH 소거능 및 ABTS 소거능, 단백질분해효능이 증가하였다. 오리자놀 함량이 높은 미강추출 물을 쌀가루에 첨가하여 쌀국수를 제조한 결과 쌀국수의 경도, 탄력성, 씸힘성, 점착성 등이 증가하였으며, 쌀국수의 γ-oryzanol 함량, DPPH 소거능, ABTS 소거능 등이 증가하여 항산화 활성이 개선되었음을 확인하였다.

Purpose This study aimed to develop and evaluate a simulation-based autotransfusion device training program to enhance the clinical performance, performance confidence, and educational satisfaction of post-anesthesia care unit (PACU) nurses. Methods: A single-group pretestposttest study was conducted with 30 PACU nurses. The program, based on the ADDIE model, included orientation, simulation training, and debriefing. Data were collected using validated tools before and after the program and analyzed using the Wilcoxon signed-rank test. Results: Clinical performance improved from a median of 30.00 to 43.00 (Z =−4.78, p < .001). Performance confidence increased from 31.00 to 47.50 (Z =−4.71, p < .001), while educational satisfaction rose from 26.00 to 40.00 (Z =−4.73, p < .001). Conclusions: The simulation-based program effectively enhanced the clinical performance, performance confidence, and education satisfaction of PACU nurses. These findings underscore the value of simulation-based training for enhancing nurses’ competence in using complex, high-risk medical devices.

The aim of this study was to produce a fermented rice bran extract with enhanced ferulic acid γ-oryzanol contents and high antioxidant activities. The ferulic acid content in the freeze-dried extract of rice bran treated with plantase PT enzyme, increased by 4.1-fold compared to that of untreated sample, the DPPH radical scavenging activity also increased by 1.5-fold and 1.2-fold, respectively. The γ-oryzanol content of the dried powder prepared by inoculating Apergillus oryzae BOT1869 onto steamed rice bran for solid-state fermentation followed by extraction with 80% ethanol, increased 2.3-fold compared to that in an 80% ethanol extract powder of raw materials. The ABTS scavenging activity also increased 1.5-fold. When the ferulic acid content-enhanced extract and the γ-oryzanol content-enhanced extract of rice bran were mixed and subjected to liquid fermentation with Lactiplantibacillus pentosus BOT406 and then freeze-dried, the ferulic acid content of the extract powder increased about 3.0 times compared to that of original extract powder. In addition, its γ-oryzanol content increased about 1.5 times, the DPPH radical scavenging activity increased 1.4 times, and the ABTS radical scavenging activity increased 1.6 times.

Reinforcement learning (RL) is successfully applied to various engineering fields. RL is generally used for structural control cases to develop the control algorithms. On the other hand, a machine learning (ML) is adopted in various research to make automated structural design model for reinforced concrete (RC) beam members. In this case, ML models are developed to produce results that are as similar to those of training data as possible. The ML model developed in this way is difficult to produce better results than the training data. However, in reinforcement learning, an agent learns to make decisions by interacting with an environment. Therefore, the RL agent can find better design solution than the training data. In the structural design process (environment), the action of RL agent represent design variables of RC beam. Because the number of design variables of RC beam section is many, multi-agent DQN (Deep Q-Network) was used in this study to effectively find the optimal design solution. Among various versions of DQN, Double Q-Learning (DDQN) that not only improves accuracy in estimating the action-values but also improves the policy learned was used in this study. American Concrete Institute (318) was selected as the design codes for optimal structural design of RC beam and it was used to train the RL model without any hand-labeled dataset. Six agents of DDQN provides actions for beam with, beam depth, bottom rebar size, number of bottom rebar, top rebar size, and shear stirrup size, respectively. Six agents of DDQN were trained for 5,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases that is not used for training. Based on this study, it can be seen that the multi-agent RL algorithm can provide successfully structural design results of doubly reinforced beam.

The rapid expansion of bridge and tunnel infrastructure has resulted in a growing incidence of wind-induced traffic accidents occurring at bridge approaches and tunnel portals. These accidents not only inflict direct damage on vehicles but also lead to substantial social and economic losses, stemming from roadway infrastructure repair and maintenance costs, as well as elevated logistics expenses due to traffic delays and congestion. In this study, a theoretical expression for the lateral displacement of vehicles as a function of wind speed was derived. Subsequently, lateral displacement and lateral wind force were analyzed and compared across vehicle types, considering both straight and curved roadway sections. An analysis of prevailing wind directions at each site revealed that, for passenger cars, the maximum lateral force and displacement on straight sections occurred at a wind incidence angle of 45°, whereas on curved sections with a pier curvature of 90°, the critical wind direction ranged from 0° to 120°. These results demonstrate that vehicle stability can be significantly compromised during high-speed travel under crosswind conditions. Based on departure trajectories of vehicles under varying wind speeds, a risk-assessment scale for wind-induced accidents was developed. In addition, design guidelines were proposed for the strategic placement of windbreak barriers to enhance driving safety under strong wind conditions.

최근 한반도 주변 해역에서 해상사고로 인한 인명피해가 증가함에 따라 실종자 수색 및 구조 활동을 지원하기 위한 수중환경 정보 산출 기술 개발의 필요성이 대두되고 있다. 끊임없이 변화하는 해양환경 속에서 수중시야를 예측하는 것은 매우 중요한 과제이다. 본 연구에서는 인공위성 영상과 현장실험 자료를 활용하여 탁도와 수중시야 간의 상관 성을 분석하고, 한반도 서해 연안에 적합한 수중시야 산출 알고리즘을 제시하고자 한다. 이를 위해 대천항 인근 해역의 두 정점을 선정하여 탁도 센서와 세키디스크를 이용해 깊이에 따른 탁도 및 수중시야를 측정하였으며, 동시에 고해상도 인공위성 영상을 수집하여 표층 원격반사도 자료를 획득하였다. 또한 서해 연안에서의 탁도 변화에 따른 수중시야의 공 간 분포를 비교하기 위해 Sentinel-2 위성의 560 nm 반사도를 활용하여 연구 해역의 탁도를 산출하고, 실측 탁도와 수 중시야 간의 상관성을 분석하였다. 연구 결과, 서해 연안에서는 2 .0- 3.0NTU 범위의 탁도가 분포하였으며, 수중거리는 1.5-3.5 m 사이의 값을 나타냈다. 특히, 만 지형이나 섬 주변에서는 상대적으로 낮은 수중시야가 관측된 반면, 대천해수 욕장 해안선을 따라서는 약 3.0m 이상의 높은 수중시야를 보였다. 본 연구를 통해 실측 및 원격탐사 자료를 활용한 수중시야 산출 가능성을 확인하였으며, 위 결과는 향후 해상 실종자 수색 지원을 위한 기초 자료로 활용될 것으로 기 대된다.