Accurate estimation of vehicle exhaust emissions at urban intersections is essential to assess environmental impacts and support sustainable traffic management. Traditional emission models often rely on aggregated traffic volumes or measures of average speed that fail to capture the dynamic behaviors of vehicles such as acceleration, deceleration, and idling. This study presents a methodology that leverages video data from smart intersections to estimate vehicle emissions at microscale and in real time. Using a CenterNet-based object detection and tracking framework, vehicle trajectories, speeds, and classifications were extracted with high precision. A structured preprocessing pipeline was applied to correct noise, missing frames, and classification inconsistencies to ensure reliable time-series inputs. Subsequently, a lightweight emission model integrating vehicle-specific coefficients was employed to estimate major pollutants including CO and NOx at a framelevel resolution. The proposed algorithm was validated using real-world video data from a smart intersection in Hwaseong, Korea, and the results indicated significant improvements in accuracy compared to conventional approaches based on average speed. In particular, the model reflected variations in emissions effectively under congested conditions and thus captured the elevated impact of frequent stopand- go patterns. Beyond technical performance, these results demonstrate that traffic video data, which have traditionally been limited to flow monitoring and safety analysis, can be extended to practical environmental evaluation. The proposed algorithm offers a scalable and cost-effective tool for urban air quality management, which enables policymakers and practitioners to link traffic operations with emission outcomes in a quantifiable manner.

In the Autonomous Mobility Living Lab, traffic situations with both autonomous vehicles (AVs) and ordinary vehicles driven by humans (HDVs) are explored. Research on countermeasures and efficient transportation management plans has emerged from this context. In this study, we analyzed the effect of AVs with different speeds on signal intersections and road networks to derive efficient traffic operation plans for roads on which various AVs and HDVs with different driving behaviors are mixed in Living Lab cities. To that end, we conducted a simulation-based analysis of the effects of AV mixing rates on continuous signal intersections and the road network in traffic situations where AVs and HDVs were mixed at peak and non-peak driving hours. The simulation scenario was designed by classifying the traffic volume levels at peak and non-peak times and defining various AV mixing rates; we also set the driver behaviors of the AVs as either conservative or aggressive. By performing a small-scale traffic simulation, the average control delay, average stopped delay, average queue length, and average travel time of the signal intersection for each scenario were derived, and the impact of the AV mixing rate on traffic operation was analyzed. The results of the analysis show that higher AV mixing rates were associated with lower measurements of the effectiveness of signal intersections, which had a positive effect on traffic operation. This resulted in a stable and efficient improvement of the traffic flow at intersections as more vehicles passed through at the time of the allocated signal, as the AVs in the simulation could be driven at short intervehicle intervals by receiving real-time traffic information. In the traffic operation on the network, we found that the higher the AV mixing rate, the lower the average travel time, resulting in a greater effect of facilitating the traffic flow of the urban network. These simulated results indicate that higher AV mixing rates were associated with positive outcomes in terms of signal intersections and network traffic operation. We expect that this simulation can be used to establish real traffic operation plans in traffic situations where AVs are mixed at each stage of autonomous driving technology in the future.

With a view towards reducing traffic accidents on roadways, various methods have been considered to predict accidents. In this study, we analyze traffic accident frequency models that employ fixed- and random-parameter negative binomial approaches. Random parameters enable the inclusion of unobserved heterogeneity in traffic accident data, which current popular methods with fixed parameters such as Poisson or negative binomial models cannot consider in terms of time variation or segment-specific effects. A continuous, unbalanced panel of accident histories for 208 four-way signalized intersections on national highways in Seoul was used to estimate a traffic accident occurrence model that considered traffic volumes and various geometric characteristics at intersections. The results revealed that the left-turn exclusive lanes and traffic volumes on minor roads had random parameters that affected the likelihood of accident frequencies differently; the other variables were found to significantly affect traffic safety at the intersections on the national highways as fixed parameters. Based on these results, it can be concluded that the same traffic safety facilities have different effects on traffic accidents on major and minor roads. The insights from this study suggest the need for a broader analysis of integrated guidelines for facilities that impact intersection accident propensities.

하수처리장 유출수의 수질 예측은 수질 사고의 사전 대응 및 처리장의 안정적인 운영을 위해 필수적인 요소이다. 최근 머신러닝을 활용한 예측 모델링에서 예측 성능 향상과 과적합 방지를 위해 다양한 교차 검증법과 하이퍼파라미터 최적화 기법이 활용되고 있으나, 하수처리장 데이터는 시간적 의존성과 급격한 변동성이 내재되어 있어 과적합에 취약하고 안정적인 모델 구축에 어려움이 따른다. 본 연구에서는 이러한 데이터 특성을 효과적으로 반영할 수 있는 최적의 모델링 파이프라인을 구축하고자 하였으며, XGBoost 모델을 기반으로 유출수 내 총질소 농도를 예측하였다. 예측 성능 평가 지표로는 평균 제곱근 오차(Root Mean Square Error, RMSE), 결정계수(coefficient of determination, R2), RMSE 오차 개선율(the rate of improvement on RMSE, RIRRMSE) 그리고 계산 시간을 사용하였다. 기본적인 Hold-out 방식의 성능을 기준으로 K-fold, 시계열 교차 검증(Time Series Cross Validation, TSCV), 블록 시계열 교차 검증(Blocked Time Series Cross Validation, BTSCV) 기법의 예측 성능을 분석한 결과, BTSCV는 인접한 데이터만을 고려하는 방식으로 시간적 의존성과 급변 특성을 효과적으로 반영하여 가장 높은 RIR(36.37%)을 기록하였다. 또한, 하이퍼파라미터 최적화(그리드 서치와 베이지안 최적화) 기법과의 다양한 교차 검증법의 조합을 통해 모델 성능과 과적합 방지 효과를 분석한 결과, BTSCV와 베이지안 최적화의 결합은 짧은 계산 시간(364.64초)과 함께 가장 높은 RIR(64.93%)을 보였으며, 훈련 및 평가 데이터 간 성능 차이도 최소화되어 일반화된 예측 모델로서의 효과성이 입증되었다. 따라서 본 연구는 하수처리장 시계열 데이터의 특성에 적합한 BTSCV와 베이지안 최적화 기법을 결합한 모델링 파이프라인 전략을 제안하며, 향후 실시간 수질 모니터링 및 하수처리장 운영 효율성 제고에 기여할 수 있을 것으로 기대된다.

With the rapid expansion of personal mobility (PM) devices as urban transport alternatives, the associated safety risks have increased significantly. Although previous studies have offered insights into user behavior and accident traits, more integrated approaches that consider spatial and administrative contexts are required to better understand the factors affecting accident severity. This study investigated the factors influencing accident severity involving PM devices in Seoul, South Korea by employing a cross-classified multilevel model (CCMM) to account for both police jurisdiction and regional characteristics. Analyzing the 2021 data from the Traffic Accident Analysis System (TAAS), the model showed strong validity (ICC: 15.8%, DIC: 697.2), outperforming the logistic and hierarchical models. Key predictors of higher severity included crashes in non-standard areas (e.g., other than single roads or intersections), helmet non-use, and older age of victims and perpetrators. Violations, such as exceeding passenger capacity, were negatively associated with severity. Industrial areas and high subway station densities reduced the severity, reflecting the benefits of pedestrian-friendly infrastructure. Larger areas covered by police officers significantly increased the severity, revealing enforcement limitations. The 2021 Road Traffic Act revision has had no statistically significant impact. These results highlight the need for integrated policies that combine infrastructure improvements, enhanced enforcement, and behavioral changes to reduce the severity of PM-related accidents in urban environments.

관상학(Physiognomy)은 오랜 역사에도 불구하고 경험적 검증의 부재로 미신 으로 치부되어 왔으나, 일부 실용 분야에서는 활발히 참조되어 이론과 실제 간의 괴리가 존재했다. 이에 본 연구는 ‘외형이 내면을 반영한다’는 관상학의 핵심 전제를 현대 통계 방법론으로 실증적으로 검증하고자, MBTI의 감정형 (F)-사고형(T) 유형과 관상학적 얼굴 특징 간의 상관관계를 분석하였다. 총 77 명의 참여자로부터 사진 데이터를 수집하여, 관상학 이론에 기반한 6가지 얼 굴 특징(눈 크기, 눈동자 크기, 코끝의 살, 입술 두께 등)을 전문가와 함께 5점 척도로 코딩하였다. 수립된 가설을 검증하기 위해 선형 및 로지스틱 회귀분석 을 적용하였다. 분석 결과, F/T 유형은 ‘눈길이’를 제외한 5가지 특징에서 유의미한 차이를 보였으며, 감정형(F) 집단이 더 큰 눈, 도톰한 입술 등을 갖는 경향을 나타냈 다. 또한, F/T 유형을 예측하는 로지스틱 회귀 모델(Pseudo R²=.462)에서는 ‘눈 동자 크기’, ‘코끝의 살’, ‘입술 두께’가 통계적으로 유의미한 핵심 예측 변수로 확인되었다. 본 연구는 관상학적 특징과 성격 유형 간의 실증적 연관성을 규 명함으로써, 관상학을 탈신비화하고 과학적 탐구의 대상으로 전환할 수 있는 가능성을 제시하며, 이는 관상학이 향후 심리학, 인공지능 등과 융합될 수 있 는 토대를 마련했다는 점에서 학술적 의의를 지닌다.

This study evaluated the short- and long-term prediction performances of a transformer-based trajectory-forecasting model for urban intersections. While a previous study focused on developing the basic structure of a transformer model for future trajectory prediction, the present study aimed to determine a practical prediction sequence length. To this end, multiple transformer models were trained with output sequence lengths ranging from 1 s to 10 s, and their performances were compared. The trajectory data used for training were generated through a microscopic traffic simulation, and the model accuracy was assessed using the metrics average displacement error (ADE) and final displacement error (FDE). The results demonstrate that the prediction accuracy decreases significantly when the output trajectory length exceeds 3 s. Specifically, straight-driving trajectories exhibit rapidly increasing errors, while turning trajectories maintained a relatively stable accuracy. In contrast, for turning-driving trajectories, prediction errors increased sharply during short-term forecasting, but the increase was more gradual in long-term forecasts. Additionally, the long-term prediction models produced higher errors even in the initial 1-second outputs, implying a tendency toward conservative inference under uncertain future scenarios. This conservative behavior is likely influenced by the model’s effort to minimize the overall loss across a broader prediction window, especially when trained with Smooth L1 loss function. This study provides practical insights into model design for edge-computing environments and contributes to the development of reliable short-term trajectory prediction systems for urban ITS applications.

This study evaluated the safety impact of automated traffic enforcement cameras targeting tailgating behavior at signalized intersections by comparing traffic conditions shortly after installation and one year later. The Kukkiwon intersection in Gangnam-gu, Seoul, South Korea was selected as the study site. Individual vehicle speeds, accelerations, and subsequent distances were extracted from video data using YOLOv8 and ByteTrack, which are advanced deep learning-based object detection and tracking algorithms. Surrogate safety measures (SSM), such as time to collision (TTC), modified time to collision (MTTC), and proportion of stopping distance (PSD), were calculated to assess changes in traffic safety. Every SSM indicated an improvement one year after the installation of enforcement cameras, suggesting a reduction in collision risks. In particular, the PSD indicator showed a notable improvement, reflecting a better maintenance of safe following distances. These results highlight the effectiveness of automated enforcement in improving intersection safety and suggest its scalability to other intersections with similar tail-gating issues. Future research should explore the long-term and multisite effects using diverse intersection types and behavioral indicators.

Korea has many test beds where various mobility services are provided by automated vehicles. The test beds are operated in their operational design domain (ODD). However, disengagement frequently occurs, even in the ODDs of automated vehicles. In particular, human drivers have to take control of the automated vehicles at SAE Level 3 whenever the vehicles cannot drive by themselves because of an emergency or unknown factors. This study analyzed the driving safety of right turning at signalized intersections where automated vehicles face selfdriving issues because of potential conflicts with other vehicles, crossing pedestrians, and geometric factors. To conduct this analysis, we categorized right-turning intersections into two types with right-turning lanes and channelization islands and divided them into three sections, with a total of six sections. Subsequently, the six sections were compared with each other by disengagements of the automated vehicles as the key index to investigate their self-driving safety. Their significant differences indicate that ODD-related variables must be considered when designing and updating target test beds for automated vehicles.

미·중 기술패권 경쟁 가운데, 첨단 디지털 기술의 공급망과 데이터 수 집, 유출, 조작, 유포 등의 우려가 제기되면서 공급망안보와 데이터안보 가 교차하는 양상이 두드러지기 시작했다. 데이터안보나 공급망안보 각 각에 대한 기존 연구는 있었으나, 이 둘의 교차점에 초점을 맞춘 연구는 드물다. 이 연구에서 다루는 데이터안보 사안들은 정부뿐 아니라 개인이 나 민간 행위자들이 취급하는 데이터들이 국가안보적 사안으로 전환되는 모습을 보인다. 이러한 신흥위협이 공급망위협과 상호작용하며, 국가안보 적 우려로 비화한 사례로 화웨이의 5G, ZPMC 항만 대형 크레인, 미래 자동차의 핵심 기술 라이다, 중국산 DJI 드론 등이 있다. 본 연구는 이러 한 사례들에 대해 국가 차원에서 어떤 대응이 이루어졌는지 탐구하였다. 특히, 관련 이슈들을 안보화하고 대응책을 앞서 제시하고 있는 미국에 초점을 맞추었다. 또한 기존의 안보화 이론을 보완하여 정치경제적 측면 을 추가하였다. 행정명령, 전략서 발간, 연방 예산안 그리고 새로운 전문 기구들의 창설을 통해 신흥 위협에 대처하고 있으며, 그 과정에서 공급 망 재편, 표준, 규범, 규제의 설립을 통해 변화하는 국가의 안보 제공자 로서의 역할을 조명하였다.

This study aimed to investigate the factors affecting the severity of taxi traffic accidents at intersections in Busan and propose measures to improve traffic safety. This study collected data on taxi traffic accidents that occurred at intersections in the Metropolitan City of Busan during the past 3 years (2020–2022) from Traffic Accident Analysis System(TAAS) and road views, and analyzed factors affecting their severity by employing an ordered probit model. The severity of taxi traffic accidents worsened with violations of (among others) traffic signals and pedestrian protection during January, April, and September. In addition, when a major street was operated with a permissive left turn, the severity of taxi traffic accidents worsened. Measures to improve traffic safety suggested in this study included safety education that focused on particular violations for taxi drivers, mandatory education for transport employees in an experiential format, support of video storage devices for driving records, policy establishment for the promotion and certification of good and bad driving videos, time adjustment of joint safety management inspection, and left-turn signal operation with an unprotected system and P-turn guidance.

This study points out the traffic safety inhibition problem in which the yellow time length at a signal intersection can be set differently depending on the tram, and proposes a way to overcome it. This study proposes a twofold approach for trams to coordinate with the yellow signal phase designated for general vehicles, utilizing a schedule-speed-based operating speed adjustment and departure time control at stations. To validate the proposed method, simulations were conducted for a planned tram corridor in the Wirye District, Seoul. The simulation environment was developed using the simulation of the urban mobility model. The operational characteristics of tram services in the main and branch-line sections were analyzed. In the upstream section of the mainline, the operating speed was 22.04 km/h, with a total dwell time of 400 s across 10 stations, resulting in zero intersection stops. Regarding the downstream section, the operating speed was 17.71 km/h, and one intersection stop was observed. In contrast, for the upstream section of the branch line, the operating speed was 14.73 km/h and there were two intersection stops, while the downstream section yielded an operating speed of 18.12 km/h, and also comprised two intersection stops. This study examined a novel operational strategy for trams near intersections along tram corridors without directly modifying the signal system. This strategy effectively utilizes tram stop dwell time and traffic signal information. It focuses on adjusting tram speeds to ensure smooth and safe passage through signalized intersections and optimizing operations so that trams approach and cross intersections at a consistent speed. Designed as a universal model, this strategy is adaptable to various regions and environments, rather than being limited to a specific area. It is expected to support tram operation planning by considering diverse factors, such as urban structure, traffic density, and intersection characteristics. Moreover, it provides valuable guidance to ensure the punctuality and stability of tram operations in a range of urban and traffic contexts.

PURPOSES : According to government data, the Black Spot Program has resulted in an average 28.8% reduction in traffic accidents within one year of project implementation in areas where road conditions improved. However, there has been a lack of in-depth analysis of the midto- long-term effects, with a predominant focus on short-term results. This study aimed to analyze the mid-to-long-term effects of the Black Spot Program to assess the sustainability of its reported short-term impact. Additionally, the differences in the mid-to-long-term effects were investigated based on the scale of traffic accidents at intersections and the characteristics of these effects are revealed. METHODS : The mid-to-long-term effects of the Black Spot Program were analyzed at 122 intersections in Seoul, Korea, where the program was implemented between 2013 and 2017, using traffic accident data spanning five years before and after implementation. Additionally, the differences in the program's effects were analyzed at the top-100 intersections with the highest traffic accident concentration in Seoul using the chi-square test to identify these differences. To theoretically validate these differences, the Hurst exponent, commonly used in economics, was applied to analyze the regression to the mean of the intersections and reveal the correlation with improvement. RESULTS : Through the Black Spot Program at 122 intersections, a 33.3% short-term accident reduction was observed. However, the midto- long-term effect analysis showed a 25.8% reduction, indicating a slightly smaller effect than previously reported. Specifically, the top-100 intersections exhibit a 15.4% reduction. A chi-square test with a 95% confidence level indicated significant differences in the program’s effects based on the scale of traffic accidents at intersections. The Hurst index (H ) was measured for the top-100 intersections, yielding H = 0.331. This is stronger than the overall H = 0.382 for all intersections in Seoul, suggesting that the regression to the mean is more pronounced, which may lead to a lower effectiveness of the improvement. CONCLUSIONS : The mid-to-long-term effects of the Black Spot Program were relatively lower than its short-term effects, with larger differences in effectiveness observed based on the scale of traffic accidents at intersections. This indicates the need to redefine the criteria for selecting project targets by focusing on intensive improvements at intersections, where significant effects can be achieved.

PURPOSES : This study aimed to derive the factors that contribute to crash severity in mixed traffic situations and suggest policy implications for enhancing traffic safety related to these contributing factors. METHODS : California autonomous vehicle (AV) accident reports and Google Maps based on accident location were used to identify potential accident severity-contributing factors. A decision tree analysis was adopted to derive the crash severity analyses. The 24 candidate variables that affected crash severity were used as the decision tree input variables, with the output being the crash severity categorized as high, medium, and low. RESULTS : The crash severity contributing factor results showed that the number of lanes, speed limit, bus stop, AV traveling straight, AV turning left, rightmost dedicated lane, and nighttime conditions are variables that affect crash severity. In particular, the speed limit was found to be a factor that caused serious crashes, suggesting that the AV driving speed is closely related to crash severity. Therefore, a speed management strategy for mixed traffic situations is proposed to decrease crash severity and enhance traffic safety. CONCLUSIONS : This paper presents policy implications for reducing accidents caused by autonomous and manual vehicle interactions in terms of engineering, education, enforcement, and governance. The findings of this study are expected to serve as a basis for preparing preventive measures against AV-related accidents.

긴급차량 골든타임 확보를 위해 지방자치단체에서는 ‘긴급차량 우선신호’ 시스템을 도입하고 있다. 그러나 긴급차량 우선신호로 인하 여 일반차량의 지체시간은 증가하게 되고 기존 신호주기로 바로 복귀하여 교차로 전체의 지체를 유발할 것으로 예상된다. 해당 지체 를 해결하기 위해 일반차량을 고려한 ‘회복신호 산정’ 연구가 수행되고 있다. 그러나 현재까지 교차로 유형별로 적절한 회복신호는 무 엇인지에 대한 연구는 부족한 상황이다. 본 연구에서는 교차로를 유형별로 구분하여 일반차량 지체도를 감소시키기 위한 회복신호의 필요성을 검증하고자 한다. 우선신호의 경우 긴급차량이 교차로를 통과하기까지 걸리는 시간을 계산하여 부여하였다. 회복신호의 경우 는 우선신호에서 부여한 시간만큼 일반차량에게 보상하는 신호방식을 적용하였으며, 도입 효과를 SUMO 교통 시뮬레이션을 통해 비 교 분석하였다.

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.

Plastics are widely used in industries in human society and because of their structural stability, degradation is a serious global issue. To estimate the degradation of plastic, 31 edible mushrooms were cultured with the selected plastic films (polyethylene [PE], polystyrene [PS], and poly(ethylene terephthalate) [PET]) for 3 months at 25 °C. Measuring the weight of the films showed that four species of mushrooms, namely Porostereum spadiceum, Ganoderma lucidum, Coprinellus micaceus, and Pleurotus ostreatus, exhibited the highest degrees of plastic degradation. In addition, the mushrooms and fungi that exhibited the most significant plastic degradation were cross-cultured to promote this degradation. As a result, cross-cultivation of G. lucidum and Aspergillus niger showed a weight loss of 2.49% for the PET film. For the PS film, Aspergillus nidulans showed a weight loss of 4.06%. Cross-cultivation of A. nidulans and C. micaceus, which showed a weight loss of 2.95%, was noted as an alternative for PS biodegradation, but is harmful to humans. These bio-degradation effects of edible mushroom will contribute to the development of alternatives for eco-friendly plastic degradation.