본 연구는 자율주행자동차(AV)와 비자율주행자동차(HDV)가 혼재하는 교통환경에서 자율주행 전용차로 도입 시 차로변경구간 길이가 교통소통지표에 미치는 영향을 VISSIM 시뮬레이션을 통해 분석하였다. 분석을 위하여 도로구조 및 교통량, AV All-knowing, Cautious 주행행태를 반영하여 432개 시나리오를 구성하였다. 시뮬레이션 결과, 차로변경구간 길이가 증가할수록 교통 밀도와 지체시간은 유의 미하게 감소하였으며, 속도 및 통과교통량이 증가하는 효과를 보였으나, 자율주행 전용차로 도입 시 밀도와 지체시간이 증가하고 속도 및 통과교통량이 감소하는 등 일부 부정적 영향을 확인할 수 있었다. 향후 실제 도로 데이터를 반영한 분석을 통해 연구 신뢰성을 제 고할 필요성이 존재한다.

인공지능의 발전은 검색엔진, SNS, ChatGPT 등 다양한 분야에서 혁신을 이끌며 사회와 산업 전반에 변화를 가져오고 있다. 특히, 교 통 분야에서는 AI 기반 기술이 교통정보 수집 및 분석 방식에 변화를 주며, 새로운 활용 가능성을 제시하고 있다. 과거 육안 계수 방 식에 의존했던 교통량 조사는 현재 CCTV 영상과 딥러닝 객체 인식 기술을 활용해 신뢰성과 정확성이 크게 향상되었다. AI 기반 교통 솔루션의 도입으로 교통량 조사 데이터는 정책 수립, 운영 개선, 사회간접자본 건설 등 다양한 분야에서 중요한 기초 자료로 활용되고 있다. 이에 본 연구에서는 YOLO v8을 활용하여 차량 축 인식 기반 차종 분류의 정확성을 향상시키고, 기존 촬영 기법과 비교·분석을 통해 최적의 인식기법을 제시하고자 한다.

본 연구는 도로 보수 후 새롭게 도입되거나 개선된 도로안전시설 중 노면표시와, 안전운전에 간접적인 영향을 미치는 도로 노면 상 태에 대한 이용자 만족도를 연령 및 업종별로 분석하고자 수행되었다. 운전자 430명을 대상으로 5점 리커트 척도 설문을 시행하고, SPSS 27.0을 이용해 일원배치 분산분석(ANOVA)과 사후 검정을 실시하였다. 그 결과, 노면표시(크기·선명도·야간시인성)는 업종별(관 리·사무·전문직, 운전직, 학생 등)로 유의미한 차이가 있었고, 연령대별로는 10대가 노면표시 크기에 가장 만족도가 높았으며 고령층으 로 갈수록 낮아졌다. 또한 운전직의 만족도가 전반적으로 낮아 노면표시가 실제 주행에 크게 영향을 주는 것으로 나타났다. 본 연구 결과는 연령별·업종별 특성을 고려한 도로환경 및 정책 개선에 기초 자료로 활용될 수 있을 것이다.

This study addresses the critical challenge of enhancing vehicle classification accuracy in traffic surveys by optimizing the conditions for vehicle axle recognition through artificial intelligence. With current governmental traffic surveys facing issues—particularly the misclassification of freight vehicles in systems employing a 12-category vehicle classification—the research proposes an optimal imaging setup to improve axle recognition accuracy. Field data were acquired at busy intersections using specialized equipment, comparing two camera installation heights under fixed conditions. Analysis revealed that a shooting height of 8.5m combined with a 50°angle significantly reduces occlusion and captures comprehensive vehicle features, including the front, side, and upper views, which are essential for reliable deep learning-based classification. The proposed methodology integrates YOLOv8 for vehicle detection and a CNN-based Deep Sort algorithm for tracking, with image extraction occurring every three frames. The axle regions are then segmented and analyzed for inter-axle distances and patterns, enabling classification into 15 categories—including 12 vehicle types and additional classes such as pedestrians, motorcycles, and personal mobility devices. Experimental results, based on a dataset collected at a high-traffic point in Gwangju, South Korea, demonstrate that the optimized conditions yield an overall accuracy of 97.22% and a PR-Curve AUC of 0.88. Notably, the enhanced setup significantly improved the classification performance for complex vehicle types, such as 6-axle dump trucks and semi-trailers, which are prone to misclassification under lower installation heights. The study concludes that optimized imaging conditions combined with advanced deep learning algorithms for axle recognition can substantially improve vehicle classification accuracy. These findings have important implications for traffic management, infrastructure planning, road maintenance, and policy-making by providing a more reliable and precise basis for traffic data analysis.

As the use of shared kickboards rapidly increases, personal mobility (PM)-related accidents are frequently occurring. These accidents are mainly caused by careless behavior, which is typically indicated by neglecting to wear a helmet, speeding, signal violation, or illegal driving owing to incorrect driving methods. This type of user behavior increases the risk of accidents; for this reason, there is an urgent need to prepare effective measures for the safe use of shared kickboards. To reduce PM accidents, this study proposes a charging model that promotes the safe behavior of shared kickboard users. The core aim of this model is to persuade users to comply voluntarily with safety rules through incentives and penalties. Specifically, by providing a discount rate when wearing a helmet, the user is encouraged to wear a helmet, whereas in the event of an accident, a penalty is imposed to emphasize the disadvantages that occur when the safety rules are violated. This incentive structure is expected to contribute to the development of safer driving habits among shared-kickboard users. To verify the effectiveness of this charging model, simulations and user surveys were conducted in parallel. It was found that the user’s safety behavior improved, and the incidence of accidents decreased considerably. This confirmed that the proposed charging model not only reduced accidents but also naturally formed a safe driving culture for users. The shared key proposed in this study can benefit the operating company, and policymakers can contribute in the future by sharing key issues that are expected to play an important role in presentation and punishment, and provide a new paradigm for sharing key paradigms.

PURPOSES : Recently, interest in radioactive accidents has increased due to domestic and international nuclear power plant accidents. In particular, local residents' concerns are increasing due to safety issues such as radioactive leaks at the Hanbit Nuclear Power Plant in South Korea. As Gwangju Metropolitan City is not included in the emergency planning area set by the Nuclear Safety and Security Commission, there are significant limitations to establishing disaster prevention measures for nuclear power plant accidents. Considering the Fukushima and Hanbit nuclear power plant accidents, the improvement of Gwangju Metropolitan City's radioactive leak accident response manual is urgently required. This study aimed to establish disaster prevention measures to respond to nuclear power plant accidents in Gwangju Metropolitan City in the event of a Hanbit Nuclear Power Plant accident and to improve resident protection measures by estimating the arrival time of radioactive materials and radiation dosage through a nuclear power plant accident simulation. Additionally, we aimed to supplement the on-site action manual for radioactive leaks at the Hanbit Nuclear Power Plant. METHODS : This study focused on establishing disaster prevention measures centered on Gwangju Metropolitan City in the event of a major accident such as a radioactive leak at the Hanbit Nuclear Power Plant. Simulations were conducted assuming a major accident such as a radioactive leak, measures to improve resident protection were established by calculating the arrival time of radioactive materials and radiation dosage in the Gwangju area in the event of a nuclear power plant accident, and on-site response action manuals were supplemented in response to a radioactive leak. RESULTS : This study considered the concerns of local residents due to the Fukushima nuclear power plant accident and the Hanbit nuclear power plant failure, conducted a simulation to derive the impact on Gwangju Metropolitan City, and examined the effectiveness of an on-site response manual for radioactive leaks to derive improvement measures. CONCLUSIONS : In the event of an accident at the Hanbit Nuclear Power Plant in Gwangju Metropolitan City, insufficient portions of the on-site response action manual should be supplemented, and close cooperation with local governments within the emergency planning area should be ensured to respond to radioactive disasters. Therefore, based on the revised on-site response action manual for radioactive leaks, close cooperation and a clear division of roles among local governments will enable effective resident protection measures to be implemented in the event of a radioactive disaster.

고속도로의 제한속도는 교통류, 운행 시간, 에너지 소비, 교통사고 발생률 등에 직접적인 영향을 미치는 중요한 요인이다. 제한속도 의 상향 조정은 운행 시간 단축과 경제적 이점을 가져올 수 있지만, 교통사고 위험성을 높일 수 있으며, 반대로 하향 조정은 사고율을 감소시킬 수 있으나 운행 시간 증가와 교통 혼잡을 초래할 수 있다. 이러한 상반된 영향으로 인해 제한속도 조정이 도로 안전성과 효 율성에 미치는 구체적인 변화를 분석하는 연구가 필요하다. 본 연구는 미시교통시뮬레이션 도구인 VISSIM과 SSAM을 활용하여 제한 속도 및 교통량 변화에 따른 고속도로 구간별 상충횟수를 분석하고, 위험성이 높아지는 구간을 식별하였다. 이를 통해 향후 단속지점 설정과 구간별 맞춤형 개선방안 마련에 실증적인 근거를 제공하고자 한다.