In this study, we aim to classify personal mobility (PM)-related traffic crash data into four categories: PM-to-vehicle, PM-to-pedestrian, PM-single, and vehicle-to-PM crashes, and analyze the factors influencing the severity of each crash type. To overcome the limitations of existing studies in explaining the impact of independent variables on ordinal dependent variables, a random forest model was combined with the Shapley additive explanation technique. This approach visualizes the influence of independent variables on a dependent variable, providing clearer insights and enhancing interpretability. The analysis of PM traffic accidents, categorized into at-fault, single-vehicle, and victim accidents, revealed distinct key factors for each type. The main contributors to the severity of crashes caused by PM are traffic violations by teenagers and collisions with elderly pedestrians. Single-vehicle accidents were predominantly caused by overturn incidents, with inadequate driving skills among PM users aged 40 years and older, and significantly increasing severity. Victim accidents primarily occur at intersections, where the behavior of the at-fault driver and age of the PM user are critical factors influencing the severity. We identified various factors influencing the severity of PM crashes by type, highlighting the need for tailored policy measures. Proposed policies include physically separating bicycle–pedestrian shared spaces and strictly regulating illegal PM sidewalk riding, introducing PM licenses for teenagers to ensure compliance with traffic rules, and implementing regular safety education programs for all age groups. Although this study applied a new analytical technique, it relied on limited crash data, thus limiting the results to estimates.

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.

Rapidly changing environmental factors due to climate change are increasing the uncertainty of crop growth, and the importance of crop yield prediction for food security is becoming increasingly evident in Republic of Korea. Traditionally, crop yield prediction models have been developed by using statistical techniques such as regression models and correlation analysis. However, as machine learning technique develops, it is able to predict the crop yield more accurate than the statistical techniques. This study aims at proposing the onion yield prediction framework to accurately predict the onion yield by using various environmental factor data. Temperature, humidity, precipitation, solar radiation, and wind speed are considered as climate factors and irrigation water and nitrogen application rate are considered as soil factors. To improve the performance of the prediction model, ensemble learning technique is applied to the proposed framework. The coefficient of determination of the proposed stacked ensemble framework is 0.96, which is a 24.68% improvement over the coefficient of determination of 0.77 of the existing single machine learning model. This framework can be applied to the particular farmland so that each farm can get their customized prediction model, which is visualized by the web system.

본 논문에서는 마스크 설계에 다양한 위상 최적설계 기법을 적용하고, 광학 근접 보정 성능을 비교한다. 포토리소그래피 공정 중 포토레지스트에 가해지는 빛의 간섭 효과를 보정하는 광학 근접 보정 기술은 반도체 품질을 결정하는 중요한 요소 중 하나이다. 전통 적인 광학 근접 보정 기술에서는 마스크의 일부 요소를 조정하며 보정 효과를 시뮬레이션과 실험으로 확인하면서 설계를 진행한다. 이러한 경험적 설계를 통해 최적의 마스크 형상을 얻는 데는 한계가 있기 때문에, 위상 최적화 기법을 이용한 마스크 설계의 필요성이 증가하고 있으며, 민감도 기반 알고리듬을 이용한 위상 최적설계가 진행되어 왔다. 본 논문에서는 이진 구조 위상 최적설계(TOBS)와 새롭게 고안한 완화된 이진 구조 위상 최적설계(Continuated TOBS)를 이용하여 기존 최적설계와 비교하고, 더 발전된 최적설계 방향 을 제시한다.

본 연구에서는 중속 충돌하중을 받는 RC 벽체의 배면파쇄 영역을 모사할 수 있는 모델링 기법을 범용 유한요소해석 프로그램인 LS-DYNA을 통해 제안하였다. 충돌해석에 주로 사용되는 요소 삭제 기능이 발사체의 하중 전달에 영향을 미치고 이로 인해 배면파 쇄 영역이 과소평가 된다고 판단하였다. 따라서 충돌 위치 주변에는 요소 삭제 기능을 사용하지 않는 모델링 기법을 제안하였다. 제안 된 기법을 적용한 해석이 실험 결과를 근접하게 모사함에 따라, 제안한 기법이 연속적인 충돌에너지의 전달에 효과적임을 확인하였 다. 추가적으로 다른 충돌 조건에 대해 해당 기법의 적용성 검토를 진행한 결과, 대칭 조건을 사용하지 않고, 철근의 결속을 함께 모사 할 경우 RC 벽체의 파괴 거동을 더욱 근접하게 모사할 수 있음을 확인하였다.

건물관리업은 산업현장의 생산설비와 시설로 부터 빌딩, 공동주택까지 영역을 확장하고 있다. 최근 5년간 건물관리업에 종사하는 근로자 수는 지속적으로 증가해 왔으며 해당 산업에 종사하는 재해자 수도 함께 증가하고 있다. 특히 건물관리업에서 발생하는 재해의 약 88.6%가 50인 미만 소규모 사업장에서 발생하며, 사고성 재해가 반복된다는 점에서 소규모 사업장에서 중점적으로 관리해야 하는 위험작업에 대한 정보를 제공하여 집중 관리하도록 할 필요성이 높다. 본 연구는 일의 형태가 다양한 건물관리업의 공정과 단위작 업을 표준화하고, 표준화된 작업의 우선 순위와 중요도를 AHP 기법을 통해 분석한 후 일의 중요도와 업무상 가중치를 제시하여 사업장에서 중점적으로 관리해야 하는 작업을 선별하는데 도움을 주고자 한다. 본 연구에서 제시하는 건물관리업의 표준화된 공정과 단위작업을 기반으로 향후 유해위험요인의 표준평가 모델과 표준가중치 모델을 개발하여 사업장에 적용한다면 건물관리사업의 산업재해 리스크를 체계적으로 관리하는데 도움이 될 것으로 기대한다.

This study systematically analyzed the causes of recurring electric shock accidents using accident analysis techniques and attempted to suggest implications for accident prevention. 124 electrocution death accidents that occurred from 2017 to 2022 were analyzed and classified into four factors(organizational influence, unsafe supervision, preconditions for unsafe acts, and unsafe acts) using the HFACS technique. As a result, First, in terms of organizational influence, many issues related to organizational processes were found, and the main causes were the lack of a safety management manual for electrical work, the lack of risk assessment, and the lack of safety procedures for electrical work. Second, in terms of unsafe supervision, the main causes were inappropriate operations such as not assigning a work supervisor during work or the lack of actual management and supervision. Third, in terms of preconditions for unsafe acts, the main causes were physical and technical problems such as not performing power outage work or not taking protective measures for live parts. Fourth, in terms of unsafe acts, the main causes were analyzed to be violations of safety procedures such as workers mistaking a power outage or not recognizing a current leakage condition, making a wrong judgment of the situation, and shortening the work time and working without safety measures for work convenience. Additionally, when examining whether the personal characteristics of those who died from electric shock had significant differences in unsafe behaviors, it was confirmed that there were significant differences in violations or decision-making errors depending on the industry and electrical-related major.

River discharge is a crucial indicator of climate change and requires accurate and continuous estimation for effective water resource management and environmental monitoring. This study used satellite gravimetry data to estimate river discharge in major basins with high discharge volumes, specifically the Congo and Orinoco basins. By enhancing the spatial resolution of gravity data through advanced post-processing techniques, including forward modeling and river routing schemes, we effectively detected changes in the water mass stored within river channels. Additionally, signals from surrounding regions were statistically removed using the Empirical Orthogonal Function (EOF) analysis to isolate river-specific discharge signals. These refined signals were then converted into river discharge data through seasonal calibration using the modeled discharge data. Our results demonstrate that this method yields accurate and reliable discharge estimates comparable to in-situ measurements from gauge stations, even without ground-based surveys such as an Acoustic Doppler Current Profiler (ADCP) field campaigns. This research highlights the significant potential of satellite-based gravity data as an alternative to traditional ground surveys, providing practical information on the hydrological status of regions associated with large-scale river systems.

본 연구에서는 호흡동조화기법의 대안으로 딥러닝 자유호흡기법에서 b-value 별 겉보기확산계수 값을 평가하고 확 산강조영상과 겉보기확산계수 지도의 해부학적 일치성을 분석하여 적절한 여기횟수 값을 알아보고자 하였다. 연구 방법은 2023년 7월부터 2024년 1월까지 간 자기공명영상 검사가 의뢰된 성인 남녀 35명을 대상으로 하였고 사용 장비는 Magnetom Skyra 3.0T(Siemens, Germany)를 이용하였다. 자유호흡기법의 비교를 위해 b-value 50, 400, 800(s/mm2)의 여기횟수를 각각 딥러닝 호흡동조화기법에서 2,3,4으로 딥러닝을 이용하지 않은 일반 자유호 흡기법에서 4,6,8으로 검사하였다. 딥러닝을 추가한 일반 자유호흡기법에서는 1,2,3 여기횟수, 2,3,4 여기횟수, 3,5,6 여기횟수, 4,6,8 여기횟수로 변화하였다. 연구 결과 딥러닝 자유호흡기법에서 간의 좌엽과 우엽, 담낭의 평균 겉보기확산계수 값은 딥러닝 호흡동조화기법과 비교하여 모두 통계적 유의성을 확인하였다. 한편 정성적 평가의 해 부학적 일치성을 분석한 결과 딥러닝 자유호흡기법의 3,5,6 여기횟수와 4,6,8 여기횟수에서 가장 높은 점수를 얻었 으며 검사 시간에서는 딥러닝 호흡동조화기법과 비교하여 약 51%, 40% 감소하였다. 따라서 간 진단에 있어 딥러닝 자유호흡기법에서 b-value 별 적절한 여기횟수 값을 이용한다면 겉보기확산계수 지도의 정확도 유지와 함께 검사 시간을 감소시킬 수 있어 임상적으로 유용한 검사가 될 것으로 사료된다.

PURPOSES : In this study, a preliminary study on the optimal clustering techniques for the preprocessing of pavement management system (PMS) data was conducted using K-means and mean-shift techniques to improve the correlation between the dependent and independent variables of the pavement performance model. METHODS : The PMS data of Jeju Island was preprocessed using the K-means and mean-shift algorithms. In the case of the K-means method, the elbow method and silhouette score were used to determine the optimal number of clusters (K). Moreover, in the case of the mean-shift method, Scott’s rule of thumb and Silverman’s rule of thumb were used to determine the optimal cluster bandwidth. RESULTS : The optimal cluster sets were selected for the rut depth (RD), annual average daily traffic (AADT), and annual maximum temperature (AMT) for each clustering technique, and their similarities with the original data were investigated. Additionally, the correlation improvement between the dependent and independent variables were investigated by calculating the clustering score (CS). Consequently, the K-means method was selected as the optimal clustering technique for the preprocessing of PMS data. The K-means method improved the correlations of more variables with the dependent variable compared to the mean-shift method. The correlations of the variables related to high temperature—such as the annual temperature change, summer days, and heat wave days—were improved in the case wherein the AMT, a climate factor, was used as an independent variable in the K-means clustering method. CONCLUSIONS : The applicability of the clustering methods to preprocessing of PMS data was identified in this study. Improvements in the pavement performance prediction model developed using traditional statistical methods may be identified by developing a model using clustering techniques in a future study.

In order to maximize the function and increase the compatibility of silicone hydrogel lens, this study compared and analyzed the properties of Amino modified silicone oil using mini and microemulsion technique, respectively. Optical and physical properties were evaluated by spectral transmittance, refractive index, water content, oxygen transmittance and contact angle measurements to evaluate the performance of the manufactured hydrogel lens. The spectral transmittance results revealed the copolymerization method lens showed 31 % of the visible light area, which did not satisfy the basic optical properties. However, the lens using the mini and microemulsion materials showed more than 90 % of the visible light area, satisfying the optical characteristics. In addition, all physical properties were superior to a basic hydrogel lens. The mini and microemulsion techniques effectively improved the stability and function of the ophthalmic hydrogel lens and are considered a promising ways of manufacturing an ophthalmic hydrogel contact lens with increased compatibility and stability.

This study pioneers a transformative approach of discarded orange peels (Citrus sinensis) into highly porous carbon, demonstrating its potential application in energy storage devices. The porous carbon structure offers a substantial surface area, making it conducive for effective ion adsorption and storage, thereby enhancing capacitance. The comprehensive characterization, including X-ray diffraction, Fourier transform infrared, Raman spectroscopy, field emission scanning electron microscopy, and XPS verifies the material’s suitability for energy storage applications by confirming its nature, functional groups, graphitic structure, porous morphology and surface elemental compositions. Moreover, the introduced plasma treatment not only improves the material’s intensity, bending vibrations, and morphology but also increases capacitance, as evidenced by galvanostatic charge–discharge tests. The air plasma-treated carbon exhibits a noteworthy capacitance of 1916F/g at 0.05A/g in 2 M KOH electrolyte. long term cyclic stability has been conducted up to 10,000 cycles, the calculated capacitance retention and columbic efficiency is 92.7% and 97.6%. These advancements underscore the potential of utilizing activated carbon from agricultural waste in capacitors and supercapatteries, offering a sustainable solution for energy storage with enhanced performance characteristics.

본 논문에서는 신뢰성 기반 최적설계(RBDO)에서 성능함수의 비선형성을 고려한 효율적인 차원감소법(DRM)을 제안한다. 차원감 소법은 적분직교점과 가중치를 사용하여 1차 신뢰도법(FORM) 보다 더 정확하게 신뢰도를 평가하는 반면 성능함수를 추가로 해석해 야하기 때문에 적분직교점의 개수가 증가하면 효율성이 저해된다. 본 논문에서는 신뢰성 기반 최적설계에서 성능함수의 비선형도를 평가하고, 비선형도에 따라 적분직교점의 수를 결정하는 기준을 제안한다. 이를 통해 신뢰성 기반 최적설계가 진행될 때 반복마다 적 분직교점의 수를 조절하여 차원감소법의 정확도는 유지하면서 계산의 효율성은 개선하는 방안을 제안한다. 성능함수의 비선형도 평 가는 최대가능목표점(MPTP) 탐색에 사용한 벡터 사이의 각도를 통해 이루어지며, 수치 테스트를 통해 비선형도에 따른 적절한 적분 직교점의 수를 도출하였다. 2차원 수치예제를 통해 개발된 방법이 차원감소법이나 몬테카를로 시뮬레이션(MCS)의 정확도는 유지하 면서 효율성이 향상된다는 것을 확인하였다.