Parking lots are environments in which various types of vehicles such as passenger cars, trucks, and personal mobility (PM) devices coexist. Despite numerous studies analyzing parking lot crash characteristics, PM devices have received limited attention. Analyzing parking lot crash characteristics involving PMs is essential, given that the market penetration rate of PM is increasing. This study quantitatively analyzed the severity characteristics of vehicle-to-PM crashes in parking lots by aggregating the number of crashes and identified factors influencing crash severity through the development of an ordered probit model. According to the quantitative analysis results, PM users experienced a higher crash severity owing to insufficient personal protective equipment. Additionally, crashes involving parked or illegally parked PMs tended to have a lower severity than those involving PMs being ridden. The developed crash severity model identified several key factors, including crashes related to illegally parked vehicles, crashes in which a vehicle was at fault for a collision with a parked PM, cases in which the vehicle type of the at-fault driver was a passenger car, and cases in which the at-fault driver was a female. A higher probability of property damage crashes, rather than injury or fatal crashes, was observed in cases involving parked or illegally parked PMs owing to lower relative speeds. Passenger cars generally have shorter braking distances than trucks or buses, allowing quicker responses to sudden situations. A female at-fault driver may experience longer perception–reaction times, potentially increasing the probability of injury or fatal crashes. The findings of this study can provide foundational data for revising ordinances or laws to enhance parking lot safety or preliminary data for developing parking lot management systems. Furthermore, the identified crash severity factors can be prioritized to develop effective measures for crash prevention and severity reduction in parking lots.

This study aims to analyze the mitigation effects of phantom traffic jams on highways in a mixed traffic environment in which autonomous vehicles (AVs) and human-driven vehicles coexist. It focuses on identifying the key factors that contribute to phantom congestion and evaluating the extent to which the introduction of AVs can stabilize traffic flow and alleviate nonrecurring congestion. To achieve this goal, a theoretical analysis was conducted to examine the major causes of phantom traffic jams, including variations in the vehicle speed, road gradients, driver behaviors (for example, acceleration and deceleration), and visual adaptations in tunnel sections. Based on these factors, simulation scenarios were constructed using VISSIM to replicate real-world conditions in highway tunnel segments. The scenarios varied according to the AV penetration rate (0%, 20%, 40%, and 60%) and incorporated key traffic indicators such as the vehicle composition, speed, and headway. Traffic flow stability was evaluated using metrics including the average travel speed, headway consistency, and frequency of acceleration and deceleration events across sections. The simulation results showed that as the proportion of AVs increased, the average travel speed improved, and both the headway stability and flow continuity were enhanced. In particular, tunnel segments with higher AV ratios experienced fewer deceleration events and reduced behavioral variability, contributing to a more stable traffic flow. These findings suggested that AVs could play a critical role in mitigating phantom traffic jams by maintaining steady speeds and safe following distances, thereby reducing the instability caused by human driving behaviors. This study offers a foundational reference for future traffic congestion mitigation strategies and AV policy development, particularly in anticipation of increasingly mixed traffic environments.

Phellinus linteus, a medicinal mushroom with potent antioxidant properties, contains bioactive compounds, such as polyphenols and flavonoids. To optimize the extraction of skin-whitening compounds, ultrasound-assisted extraction combined with statistically based optimization was used to simultaneously extract total polyphenol content (TPC), radical scavenging activity (RSA), and tyrosinase activity inhibition (TAI). Extraction variables, including extraction time (X1:4.8 ~ 55.2 min), extraction temperature (X2:26.4 ~ 93.6oC), and ethanol concentration (X3:13.0 ~ 97.0%), were varied in 17 experimental cycles based on a central composite design. Quadratic regression models for TPC, RSA, and TAI had coefficients of determination (R2) greater than 0.92, demonstrating well-fitted models and statistical significance. Analysis of variance revealed that all three variables significantly influenced extraction efficiency (p < 0.0041), with ethanol concentration (X3) having the most pronounced effect. The optimal extraction conditions were 80.0 min, 82.5oC, and 64.8% ethanol, yielding predicted values of 6.42 mg GAE/g DM for TPC, 73.71% for RSA, and 85.04% for TAI. These results suggest that a moderate ethanol concentration combined with adequate thermal input maximizes the extraction of antioxidant and tyrosinase inhibitory activities specifically associated with skin-whitening effects.

Sanghuang mushroom is highly valued for its medicinal potential, including anticancer, anti-inflammatory, and antioxidant activities, and has recently gained significant economic and pharmacological importance. Despite considerable taxonomic revisions within the genus Sanghuangporus, confusion persists in Korea due to the continued use of outdated names such as Phellinus linteus, P. baumii, and Inonotus baumii, as well as inconsistencies in common names. This study aimed to clarify the species diversity of Sanghuangporus in Korea through integrative approaches combining phylogenetic, morphological, and ecological analyses. Using four genetic markers (ITS, nLSU, RPB2, and TEF1), we analyzed 11 dried specimens preserved at the Seoul National University Fungus Collection and 74 fungal strains maintained by the Korean Agricultural Culture Collection. As a result, we identified eight Sanghuangporus species in Korea: S. baumii, S. mongolicus, S. quercicola, S. sanghuang, S. subbaumii, S. vaninii, S. weigelae, and a novel candidate species, Sanghuangporus sp. 1. Among these, S. mongolicus and S. quercicola were newly recorded species for Korea. By providing diagnostic traits and ITS barcode sequences, this study offers a reliable taxonomic framework for the accurate identification of Sanghuangporus species. It also supports future taxonomic studies, cultivar development, and applied research in pharmaceutical and functional bioactive materials.

Autonomous vehicle technology is targeted for commercialization in 2027. However, a mixed traffic environment of conventional vehicles and autonomous vehicles is expected to be inevitable. In mixed traffic, conventional vehicles drive at reduced speeds due to limited visibility, while autonomous vehicles can drive at normal speeds using sensors. The difference in driving speeds between the two vehicles creates a mismatch in traffic flow, and the risk of congestion and accidents is likely to increase. It is necessary to analyze the impact of the interaction between autonomous vehicles and regular vehicles on traffic safety in advance and develop management measures to mitigate it. In this study, we aim to analyze the effect of reducing the speed deviation between general vehicles and autonomous vehicles by providing the driving speed deceleration level information to autonomous vehicles in the event of fog to induce the same traffic flow and improve the safety level accordingly. We examined the method of delivering the driving speed deceleration level information to autonomous vehicles. When providing speed limit information to autonomous vehicles through systems such as VMS, each country has different ways of recognizing regulatory symbols. Due to these differences, it may not be easy to provide regulatory information to overseas vehicles through external systems such as VMS in Korea. For this reason, there is a possibility that autonomous vehicles may violate laws and regulations by not recognizing them properly, and there are still limitations in defining the responsibility for applying laws and regulations between countries. Therefore, we adopted an information provision approach that encourages autonomous vehicles to maintain a harmonious traffic flow with regular vehicles by sharing safe driving speed information to be encouraged at the public center level. To analyze the effectiveness of these safe driving speed management measures, we used a quantitative indicator, the number of observable conflicts, to distinguish the mixing ratio of regular vehicles and autonomous vehicles. The analysis was divided into early (30%), mid (50%), and late (80%) periods of autonomous vehicle introduction. As a result of giving autonomous vehicles the same traffic flow as regular vehicles, the number of collisions decreased by 128 collisions/hour in the early period, 393 collisions/hour in the mid period, and 337 collisions/hour in the late period. This indicates that the interaction between autonomous vehicles and conventional vehicles becomes more complex as the mixing ratio increases, and the effectiveness of the safe speed management measures proposed in this study increases accordingly. These results can be used as an important basis for transportation policy and design.

This study aims to improve the interpretability and transparency of forecasting results by applying an explainable AI technique to corporate default prediction models. In particular, the research addresses the challenges of data imbalance and the economic cost asymmetry of forecast errors. To tackle these issues, predictive performance was analyzed using the SMOTE-ENN imbalance sampling technique and a cost-sensitive learning approach. The main findings of the study are as follows. First, the four machine learning models used in this study (Logistic Regression, Random Forest, XGBoost, and CatBoost) produced significantly different evaluation results depending on the degree of asymmetry in forecast error costs between imbalance classes and the performance metrics applied. Second, XGBoost and CatBoost showed good predictive performance when considering variations in prediction cost asymmetry and diverse evaluation metrics. In particular, XGBoost showed the smallest gap between the actual default rate and the default judgment rate, highlighting its robustness in handling class imbalance and prediction cost asymmetry. Third, SHAP analysis revealed that total assets, net income to total assets, operating income to total assets, financial liability to total assets, and the retained earnings ratio were the most influential factors in predicting defaults. The significance of this study lies in its comprehensive evaluation of predictive performance of various ML models under class imbalance and cost asymmetry in forecast errors. Additionally, it demonstrates how explainable AI techniques can enhance the transparency and reliability of corporate default prediction models.

This study attempted to solve the problem that the current education does not match the actual working environment of the fishing vessel despite the mandatory lifeboat training of international fishing vessel. The survey analyzed the difficulties of using life rafts and communication facilities and found that the main problems were the launch of life rafts, lack of communication equipment proficiency, and absence of emergency training scenarios. Due to the lack of standards for designated educational institutions, the current Seafarers Act has been discovered to be a problem that the accuracy and reliability of education are not consistent with the international fishing vessel agreement and the merchant vessel agreement. Additionally, the training for retreat and emergency response as stipulated by international agreements were not properly reflected in the domestic curriculum. In particular, the current training consists of general contents without considering the characteristics of the fishing crew, and there was a lack of practical emergency response training manuals. Therefore, based on international agreements, this study proposes the development of customized training contents for fishing vessel that takes into account the special working environment and risk factors of them. In addition, it emphasizes the need for policy support, such as strengthening participation of fishing boats in education and training and establishing a legal basis for the operation of emergency life raft organizations.

PURPOSES : In this study, the existence of an optimal pattern among transition methods applied during changes in traffic signal timing was investigated. We aimed to develop this pattern into an artificial intelligence reinforcement-learning model to assess its effectiveness METHODS : By developing various traffic signal transition scenarios and considering 19 different traffic signal transition situations that can be applied to these scenarios, a simulation analysis was performed to identify patterns through statistical analysis. Subsequently, a reinforcement-learning model was developed to select an optimal transition time model suitable for various traffic conditions. This model was then tested by simulating a virtual experimental center environment and conducting performance comparison evaluations on a daily basis. RESULTS : The results indicated that when the change in the traffic signal cycle length was less than 50% in the negative direction, the subtraction method was efficient. In cases where the transition was less than 15% in the positive direction, the proposed center method for traffic signal transition was found to be advantageous. By applying the proposed optimal transition model selection, we observed that the transition time decreased by approximately 70%. CONCLUSIONS : The findings of this study provide guidance for the next level of traffic signal transitions. The importance of traffic signal transition will increase in future AI-based traffic signal control methods, requiring ongoing research in this field.

PURPOSES : For autonomous vehicles, abnormal situations, such as sudden changes in driving speed and sudden stops, may occur when they leave the operational design domain. This may adversely affect the overall traffic flow by affecting not only autonomous vehicles but also the driving environment of manual vehicles. Therefore, to minimize the traffic problems and adverse effects that may occur in mixed traffic situations involving manual and autonomous vehicles, an autonomous vehicle driving support system based on traffic operation optimization is required. The main purpose of this study was to build a big-data-classification system by specifying data classification to support the self-driving of Lv.4 autonomous vehicles and matching it with spatio-temporal data. METHODS : The research methodology is explained through a review of related literature, and a traffic management index and big-dataclassification system were built. After collecting and mapping the ITS history traffic information data of an actual Living Lab city, the data were classified using the traffic management indexing method. An AI-based model was used to automatically classify traffic management indices for real-time driving support of Lv.4 autonomous vehicles. RESULTS : By evaluating the AI-based model performance using the test data from the Living Lab city, it was confirmed that the data indexing accuracy was more than 98% for the KNN, Random Forest, LightGBM, and CatBoost algorithms, but not for Logistics Regression. The data were severely unbalanced, and it was necessary to classify very low probability nonconformities; therefore, precision is also important. All four algorithms showed similarly good performances in terms of accuracy. CONCLUSIONS : This paper presents a method for efficient data classification by developing a traffic management index to easily fuse and analyze traffic data collected from various institutions and big data collected from autonomous vehicles. Additionally, EdgeRSU is presented to support the driving of Lv.4 autonomous vehicles in mixed autonomous and manual vehicles traffic situations. Finally, a database was established by classifying data automatically indexed through AI-based models to quickly collect and use data in real-time in large quantities.

최근 자율주행 차량의 등장으로 인해 기존의 교통 시스템에 많은 변화가 생길 것으로 보이며, 운전자가 주행하던 차량과는 다른 행태로 인해 기존 비자율주행 차량들이 초래하는 고위험 상황의 요인과는 다른 새로운 요인들이 도출될 것으로 보인다. 하지만, 현 시점 국내 에서는 자율주행 차량이 실제로 주행하고 있지 않기 때문에 주행행태를 포함한 데이터 기반의 주요 요인 분석 및 도출에 한계가 있다. 따라서 현 시점에서 자율주행 차량이 혼재하는 환경에서 고위험한 상황을 정의할 수 있는 요인을 도출하기 위해서는 사례 중심의 분석이 필요하다. 따라서 본 연구에서는 기존 국내·외 자율주행차량과 관련된 다양한 논문 사례를 DB화하여 이를 정량적으로 평가할 수 있는 메타 분석(Meta-Analysis) 기법을 통해 향후 자율주행차량이 혼재하는 교통 네트워크에서 안전성을 증진하기 위한 고위험 유발의 주요 요인을 도출하고자 하였다. 본 연구에서 DB화한 논문은 자율주행 차량과 관련된 총 4가지(사고요인, 시나리오, 예측모델, 법규)에 해당 하는 분야로 분류하여 수집하였으며, 2015년부터 2024년 까지 최근 10개년에 해당 되는 사례를 수집하여 분석을 수행하고 주요 요인을 도출하였다. 본 연구의 결과는 향후 자율주행 차량 혼재 시 고위험 상황의 주요 요인들을 바탕으로 각 요인에 기반한 자율주행차량 혼재 시 고위험 상황에 대한 정의를 할 수 있으며, 이러한 고위험 요인들에 의해 도로교통의 안전성이 저해될 수 있는 요인에 대한 사전 예방을 수행할 수 있을 것으로 기대된다.

인명 사고, 차량 화재, 자연재해, 돌발상황 등 긴급상황 발생 시 신속한 대응을 위해 영향권을 정확하게 분석하는 것이 필수적이다. 특히 도로망을 중심으로 한 영향권은 해당 도로의 교통량, 통제 차로 수, 사고 처리 시간에 따라 달라지며, 이를 관리하기 위한 대책 이 필요하다. 따라서 본 연구는 향후 도로 관리 대책 및 의사결정을 지원하기 위해 대기행렬이론을 기반으로 긴급상황 영향권을 분석 하였다. 본 연구에서 영향권은 공간적인 개념으로서 사고 발생지점으로부터 해당 도로 진행 방향 기준 후방으로 도로 소통에 영향을 끼치는 거리로 정의하였다. 사고 발생지점, 사고 발생 링크의 교통량, 차로 수 및 통제 차로 수, 사고 발생 및 사고 종료 시점 등의 변수를 입력 데이터로 설정하였고 긴급상황으로 인해 발생하는 대기행렬길이를 파악하기 위해 대기행렬이론을 적용하였다. 돌발상황 정보를 분석하여 사고 지속시간의 범위를 도출하였으며 이를 기반으로 여러 가지 상황별 영향권을 산출하였다. 유스 케이스별 영향권 산출을 통해 교통량, 이용 가능한 차로 수, 사고 지속시간 각각이 영향권과 어떠한 관계가 있는지 확인할 수 있었다. 본 연구에서 설정한 영향권을 통해 실시간 교통 데이터를 활용하여 유사 상황에서의 영향권을 신속히 파악할 수 있다. 이는 교통사고와 같은 긴급 상황 발생 시 신속하고 정확한 영향권 파악으로 현장 대응 및 의사결정 지원 시스템의 효율성을 높이는 데 중요한 역할을 할 것으로 기대된다.

일반차량과 자율주행차량이 혼재하는 상황에서 발생가능한 미래 재난상황에 대한 관리방안 준비가 필요하다. 특히 재난 상황 중 안 개 발생 시 시야 확보가 어려운 일반차량 운전자와 센서기반 자율주행차량의 주행 특성이 다를 수 있다. 해당 상황에서의 문제점을 도출하고 이를 극복하기 위해 혼합교통류 관리 방안을 제안하고자 한다. 본 연구에서는 다양한 재난 상황 중 안개를 연구 대상으로 설정하였다. 과거 기상 상황별 일반차량을 주행 특성을 이력자료로 분석한 후, 안전한 교통흐름을 유지하기 위하여 자율주행차에게 정 보를 제공하는 방안을 제안한다.

자율주행차가 보급되어 도로에서 사람 운전자와 함께 운영되는 미래가 다가오고 있다. 사람 중심으로 운영되는 도로 체계가 자율주 행차와 공존하는 형태로 변화하고 있으며, 도로 시스템도 사람 운전자와 자율주행차가 혼재된 혼합교통류를 대상으로 변화하고 있다. 현재 도로에서는 예상하지 못한 상황들이 다양하게 발생한다. 교통사고, 도로 낙하물 등 교통흐름에 영향을 주는 상황들이 발생하며, 대응을 위한 전략들이 각 지방자치단체에서 준비되어 있다. 미래 교통상황에는 도로상에 자율주행차가 혼재되어 있으며 이를 포함하 는 돌발 및 재난상황에 대한 제어전략은 아직 부재하다. 본 연구에서는 돌발 및 재난상황 발생 시 자율주행차 제어전략에 대한 설계 방안을 제안한다. 돌발 및 재난상황 범위에 대해 정의하며, 상황 구분을 위한 기준을 제시하여 각 상황에서 자율주행차가 안전하게 대 응할 수 있도록 제어전략을 제시한다.

운전 시뮬레이션을 통해 3-수준 자율주행 중 차량 전방에 장애물이 출현하는 상황에서 서로 다른 연령대의 운전자 들이 보이는 제어권 전환 반응시간과 상황인식, 그리고 차량통제 수행에서의 차이를 장애물 회피 이전(before the obstacle avoidance: BOA)과 이후(after the obstacle avoidance: AOA) 구간으로 구분하여 분석하였다. 본 연구의 결 과를 요약하면 다음과 같다. 첫째, 실험참가자들의 상황인식은 AOA 구간에 비해 BOA 구간에서, 그리고 청년운전자 집단에 비해 고령운전자 집단에서 더 낮았는데, 이러한 경향은 AOA 구간에 비해 BOA 구간에서 더 뚜렷하였다. 둘째, 제어권 인수 시간은 청년운전자 집단에 비해 고령운전자 집단에서 유의하게 더 느렸다. 셋째, 네 가지 차량통 제 측정치 모두에서 BOA 구간보다는 AOA 구간에서, 그리고 청년운전자 집단보다는 고령운전자 집단에서 더 저하 된 수행이 관찰되었으나 차량통제 수행에서의 연령집단간 차이는 BOA 구간보다는 AOA 구간에서 더 컸다. 이러한 결과는 자율주행 중 제어권을 인수받아 수동으로 운전하여 장애물을 회피하는 상황에서 운전자의 상황인식과 차량 통제는 BOA 구간과 AOA 구간에 따라 달라질 수 있음을 시사한다.

PURPOSES : This study presents a general guideline for the initial management of traffic signal timings in response to traffic incidents, prior to the implementation of specific treatments in detail. The proposed solution includes a set of optimal reductions in the green time rates at three signalized intersections upstream. METHODS : To account for the various traffic and incident conditions that may be encountered, a total of 36 traffic-condition scenarios were prepared. These scenarios encompass a wide range of conditions, from unsaturated to near-saturated conditions, and were designed to provide a comprehensive understanding of the impact of traffic conditions on signal timing. For each of the traffic conditions, all 27 traffic signal timing combinations were subjected to testing. A total of 972 simulation analyses were conducted using the SUMO model. The results indicated that the scenario with the lowest control delay was the optimal choice. RESULTS : The results indicated that the most effective initial management for the traffic incident would be to reduce the green signal timings by 20% at the first two upstream intersections and by 40% at the third intersection. CONCLUSIONS : We propose reducing the green times by 20% at the first and second intersections and by 40% at the third intersection as the initial response of the traffic signal control center when a traffic incident occurs.

PURPOSES : Even when autonomous vehicles are commercialized, a situation in which autonomous vehicles and regular drivers are mixed will persist for a considerable period of time until the percentage of autonomous vehicles on the road reaches 100%. To prepare for various situations that may occur in mixed traffic, this study aimed to understand the changes in traffic flow according to the percentage of autonomous vehicles in unsignalized intersections. METHODS : We collected road information and constructed a network using the VISSIM traffic simulation program. We then configured various scenarios according to the percentage of autonomous vehicles and traffic volume to understand the changes in the traffic flow in the mixed traffic by scenario. RESULTS : The results of the analysis showed that in all scenarios, the traffic flow on major roads changed negatively with the mix of autonomous vehicles; however, the increase or decrease was small. By contrast, the traffic flow on minor roads changed positively with a mix of autonomous vehicles. CONCLUSIONS : This study is significant because it proactively examines and designs traffic flow changes in congested traffic that may occur when autonomous vehicles are introduced.