Background: Real-time ergonomic risk assessment in manufacturing environments is challenged by severe class imbalance in high-risk postures and the need for deployment-efficient models. Conventional oversampling techniques may violate biomechanical constraints, limiting their suitability for human motion data. Objectives: This study aimed to compare multiple machine learning models for real-time ergonomic risk assessment while addressing data imbalance using biomechanically appropriate learning strategies and evaluating both predictive performance and deployment efficiency. Design: Comparative study. Methods: A large-scale workplace safety dataset comprising image-based skeletal keypoints was analyzed. To mitigate class imbalance without generating biomechanically implausible samples, cost-sensitive learning and focal loss were employed instead of synthetic oversampling. Subject-wise data splitting was applied to prevent data leakage. Five model families, including Random Forest, convolutional neural networks, and a lightweight graphbased network, were evaluated using accuracy, F1-score, area under the receiver operating characteristic curve (AUC), and high-risk recall. Statistical significance was assessed using bootstrap confidence intervals and McNemar and DeLong tests. Results: The lightweight graph-based model demonstrated competitive classification performance while maintaining reduced computational complexity. Although none of the models achieved the predefined high-risk recall threshold, statistically significant performance differences were observed across model families. Conclusion: The findings suggest that biomechanically informed imbalance handling improves methodological validity in ergonomic risk assessment. While deployment feasibility appears promising, further empirical validation on edge hardware is required.

목적: 본 연구의 목적은 고화질로 인쇄된 사진 형태의 모형안을 이용하여 실시간 영상 기반 안구운동 측정 장비를 개발하고, 반복 측정 실험을 통해 동공 중심 검출 알고리즘의 안정성과 신뢰도를 정량적으로 평가하는 것이다. 기존 상용 eye-tracking 시스템에 비해 저비용 하드웨어와 오픈소스 소프트웨어만으로 구축 가능한 장비의 초기 성능을 검증하고자 하였다. 방법 : XIMEA 고속 카메라를 기반으로 적외선 조명 및 실시간 영상 처리 알고리즘을 구성하여 동공 영역을 검 출하고 중심 좌표(x, y)를 추적하였다. 모형안을 고정된 거리에서 촬영한 후, 동일한 환경에서 10회 반복 측정을 수행하였다. 각 반복 측정은 900프레임으로 구성되었으며, 총 9,000프레임의 동공 영상 데이터를 수집하였다. 동 공 중심 검출 성공률을 산출하였으며, 반복 측정 간 중심 좌표의 변동성을 표준편차로 정량화하여 알고리즘의 안정 성을 평가하였다. 결과 : 총 9,000프레임 중 동공 중심 검출 성공률은 평균 97.3%를 나타냈다. 반복 측정 간 중심 좌표의 변동성 은 x축 표준편차 0.46±0.05 pixel, y축 표준편차 0.52±0.04 pixel로 측정되었으며, 모든 조건에서 중심 좌표의 표준편차가 1 pixel 미만을 유지하였다. 시간 분포 시계열 분석 결과, 중심 좌표는 특정 방향으로의 점진적인 위치 편향이 거의 관찰되지 않았으며, 중심 주변에 밀집된 분포를 보였다. 결론 : 본 연구에서 개발한 실시간 안구운동 측정 장비는 모형안 기반 반복 측정 실험에서 높은 동공 검출 성공 률과 우수한 반복 측정 안정성을 보여주었다. 저비용 장비 구성과 자유로운 알고리즘 수정 가능성은 연구 단계의 eye-tracking 시스템 개발에 유리한 장점을 제공하며, 향후 사람 대상 연구 이전의 초기 장비 검증 모델로 활용 가능하다. 또한 동공 중심뿐만 아니라 동공 지름 변화, 홱보기 검출 등 다양한 시기능 분석 지표로 확장할 수 있는 기술적 기반을 마련하였다.

This study established a method for the simultaneous quantitative analysis of 84 odorous compounds by determining proton transfer reaction rate constants, fragmented ion patterns, and product ion yield ratios through experiments on 33 target compounds and by incorporating previously reported data. In this research, a protontransfer- reaction time-of-flight mass spectrometer (PTR-ToF-MS), a real-time analytical instrument, was employed to quantitatively analyze odorants in process streams and final outlet gases from two wastewater consignment treatment facilities (Facility A and Facility B). The expected odor intensity (EOI) estimation method was further applied to identify the primary odor contributors. Among the final outlet gases, the top five odorcausing substances in Facility A were n-pentanal, acetaldehyde, methylmercaptan, n-hexanol, and n-butanal, while the top five odor-causing substances in Facility B were n-decanal, n-nonanal, acetaldehyde, n-butanal, and n-propanol. The cumulative odor contribution rates of these top five odorants were 94.7% and 91.9% for Facilities A and B, respectively. Although PTR-ToF-MS has inherent limitations in distinguishing isomers and isobars, their individual quantification was achieved through complementary identification and separation by TD-GC-MS. This study provides a basis for simplifying quality control in odor analysis compared with conventional trace-level odor testing methods and proposes a more scientific and effective approach for addressing odor problems.

This study proposes a lightweight algorithm for real-time front-vehicle detection using low-resolution camera footage under various driving conditions. The proposed method first extracts driving lanes using Canny edge detection and the Hough transform, thus enabling efficient lane detection. A forward region of interest (ROI) is delineated based on the extracted lane geometry. Subsequently, YOLOv11 is employed to detect vehicles within each frame, where only those located inside the defined ROI are classified as preceding vehicles. To evaluate the applicability of the proposed method in diverse environments, its performance was assessed across six driving scenarios: normal driving, traffic congestion, complex structural environments, nighttime, tunnel sections, and sharp curves. Experimental results show that the proposed approach maintains a stable detection accuracy across different conditions while offering a low computational cost and a high processing speed. Compared with segmentation-based deep-learning lane-detection models, the proposed method demonstrates superior real-time capability and can operate using only a built-in monocular camera without relying on expensive sensors such as LiDAR, radar, or artificial markers. This study serves as a foundation for vision-based ADASs, front-vehicle-following control, and road-hazard detection systems.

This study aims to explore the creative and technological significance of applying real-time motion capture data to XR (Extended Reality)-based multidisciplinary performances. By analyzing the case of the performance All About Error, which integrated real-time captured movements of dancers with audiovisual content delivered on a media wall (LED screen), the research investigates both the potential and the limitations of creating nonlinear, interactive stage environments. The methodology combines a review of prior XR production cases with an in-depth analysis of the actual production process of the performance. The findings demonstrate that the convergence of technology and art in multidisciplinary performances advances beyond traditional unidirectional and linear formats, fostering bidirectional and multidimensional performances that respond in real time to the performers’ movements. This evolution promotes expanded visual communication and discourse between performers and audiences, illustrating the creative potential to redefine the boundaries of live art. Utilizing real-time motion data on stage not only maximizes audience immersion and active participation but also suggests that real-time, interactive technologies in digital media art can expand into a variety of fields, including performing arts and games. This trend points to new directions and growth opportunities in artistic creation and provides important implications for future research in performing arts and interactive media art.

This study proposes a real-time content design pipeline optimized for Unreal Engine, integrating generative AI-based image creation with AI-assisted 3D modeling tools. The pipeline aims to streamline the production of high-quality assets for real-time applications, including games and simulations. Two types of subjects were selected: a bust combining organic character features, and a stone slab characterized by planar and symmetrical structure. Multi-angle image data were first synthesized using advanced generative AI models to simulate diverse viewpoints. These were then processed using AI-enhanced photogrammetry and modeling tools to reconstruct detailed 3D meshes and extract base textures. Post-processing steps, including mesh decimation, UV unwrapping, and texture baking, were performed to ensure compatibility with Physically Based Rendering (PBR) workflows used in Unreal Engine. The final assets were successfully imported into Unreal Engine, demonstrating visual fidelity and performance suitability in a real-time environment. The study confirms the pipeline’s potential for accelerating asset development and suggests promising future directions in AI-driven digital content creation.

Salmonella spp.는 식중독의 주요 원인균으로, 신속하고 정확한 검출 방법이 요구된다. 본 연구에서는 간소화된 direct multiplex real-time PCR 방법인 FS Finder SL키트 의 분석법 활용 가능성을 평가하고, 평판배지법과의 검출 성능을 비교하였다. 또한, real-time PCR의 검출 효율을 평 가하기 위해 FS Finder SL 키트에서 제공하는 세 가지 전 처리 방법(Method 1, 2, 3)을 비교 분석하였다. 실험 결과, 세 가지 전처리 방법을 이용한 direct multiplex real-time PCR 방법은 Salmonella spp.를 100% 검출할 수 있었으며, Ct 값 비교를 통한 통계적 분석에서도 세 방법 간 유의한 차이가 없는 것으로 나타났다(P>0.05). 반면, 선택 배지를 이용한 검출에서는 2 log CFU/g 이상으로 접종된 샘플에 서만 Salmonella spp.가 검출되었으나 real-time PCR법의 경우 0-3 log CFU/g 범위의 샘플에서 모두 검출이 가능 하였다. 또한, 실험에 사용된 세 가지 즉석섭취식품군(알 가공품, 닭가슴살 제품, 편의점 도시락)에서 자연균총의 영 향을 평가한 결과, 도시락 샘플의 일반세균수가 3.56±0.18 log CFU/g으로 가장 높았으며, 알가공품과 닭가슴살 제품 에서는 검출되지 않았다. 결론적으로 FS Finder SL 키트 를 활용한 real-time PCR 방법은 기존의 평판배지법보다 높은 검출 감도를 보였으며, 검출까지의 소요 시간을 대 폭 단축할 수 있었다. 특히, 복합적인 식품 매트릭스에서 도 신속하고 정밀한 검출이 가능함을 확인하였다. 본 연 구는 즉석섭취식품 중 Salmonella spp. 검출을 위한 효율 적인 direct multiplex real-time PCR 분석법의 적용 가능 성을 제시하며, 향후 식품안전 관리 시스템에서 활용될 수 있는 기초 자료를 제공한다.

본 연구는 선박 기관실 내에 설치된 증기 배관을 대상으로 누설 감지 및 상태 모니터링을 위한 방법론을 다루고 있다. 일반적 으로 기관실 내의 증기 배관은 보온재로 둘러싸여 있으므로, 증기가 누설되더라도 육안으로 식별하기 어려워 초기 대응을 지연시키는 상 황이 발생할 수 있다. 이에 본 논문은 RGB 카메라와 Thermal 카메라를 이용하여 상호보완적 정보 제공이 가능한 센서 시스템을 개발하기 위한 하드웨어 및 소프트웨어의 설계 방법을 제안한다. 보다 세부적으로 제안된 시스템은 카메라 서버 모듈, 카메라 보정 모듈, 영상 정합 모듈, 열-지도 학습 모듈, 추론 및 시각화 모듈로 구성된다. 특히 증기 배관의 누설이 이상 고온을 초래한다는 점을 고려하여, 본 논문은 열-지도의 개념을 정의하고 열-지도의 효과적인 학습, 열-지도에 기반한 이상 고온 감지, 감지된 이상 고온 영역의 시각화를 위한 알고리 즘을 제안한다. 제안된 방법은 선박 증기 배관 시스템을 모사한 실험 장치를 이용하여 다양한 실험을 통해 그 효용성을 입증한다.

The seismic performance of lead-rubber bearings (LRBs) is significantly affected by both the axial force and loading rate they experience. Accurate assessment of LRBs’ seismic performance, therefore, requires realistic simulation of these forces and rates, as well as of the response of the isolated structure during seismic events. This study conducted a series of real-time hybrid simulations (RTHS) to evaluate the seismic behavior of LRBs in such conditions. The simulations focused on a two-span continuous bridge isolated by LRBs atop the central pier, exposed to horizontal and vertical ground motions. In the RTHS framework, the LRBs were physically tested in the laboratory, while the remainder of the bridge was numerically modeled. Findings from these simulations indicated that the vertical ground motion had a minimal effect on the lateral response of the bridge when isolated by LRBs.

본 연구는 생성적 AI와 언리얼 엔진의 MetaHuman 기술을 통합하여 고급 실시간 디지털 휴먼 시스템을 구현하는 것을 탐구한다. Inworld AI의 NPC 시스템 및 NVIDIA의 Avatar Cloud Engine과 같은 기존 기술 통합 사례를 분석하여 연구에 참고하였으며, MetaHuman의 시각적 사실성과 생성적 AI의 동적 행동을 결합한 새로운 아키텍처를 제안한다. 연구 방법론은 캐릭터 제작, AI 모델 통합, 실시간 성능 최적화를 다루고 있다. 시스템은 렌더링 품질, AI 응답 정확 도, 사용자 경험을 기준으로 평가되었으며, 그 결과 이러한 통합이 보다 반응성 높고 사실적인 디지털 휴먼을 구현할 잠재력을 입증했다. 본 연구는 게임, 교육, 가상 비서 분야에서의 시사점 을 논의하고, 현재의 한계점과 향후 연구 방향을 제시한다. 이를 통해 첨단 AI 기능과 최첨단 실시간 렌더링을 결합한 프레임워크를 제공하여 지능형 가상 캐릭터 개발을 한 단계 발전시키 는 데 기여하고자 한다.

This study was conducted to efficiently manage THC, which was previously managed only through self-measurement. Using Selected Ion Flow Tube Mass Spectrometers, a real-time air quality measurement device, VOCs were measured in five industrial complexes, and methyl ethyl ketone was measured at the highest concentration in the industrial complexes. THC measurements were conducted at business sites located in the area. As a result of the measurements, printing processes, drying processes, etc. exceeded the emission standard of 110 ppm in three processes, and the outlets that exceeded the emission standard were instructed to improve prevention facilities such as activated carbon replacement, thereby reducing highconcentration VOC emissions. The results of the study suggest that if inspection agencies measure VOCs in real time and conduct Total Hydro Carbon measurements, etc. mainly in high-concentration areas, VOCs and Total Hydro Carbon, which are the causes of greenhouse gases and odors, can be efficiently reduced.

This study examined the spatiotemporal changes in Jilnal Wetland using satellite image-based time series data and field surveys. The analysis focused on changes in open water surface area and vegetation using the JRC Surface Water Monthly Water History dataset and Landsat imagery from 1984 to 2020. The impact of hydrological changes on vegetation was assessed through surveys conducted before and after the 2023 monsoon season. Results indicated a continuous decrease in open water surface area since the 1980s, with a sharp decline post-2003. NDVI analysis showed an inverse relationship between water area reduction and increased vegetation vigor and coverage. Field surveys revealed that hydrological changes directly affected vegetation structure, leading to new herbaceous communities and greater diversity post-monsoon. These findings highlight significant ecosystem changes driven by anthropogenic factors and natural succession, necessitating a comprehensive conservation strategy, including development control, hydrological management, terrestrialization prevention, and long-term monitoring.

한국의 주택시장은 2020년대에 들어 유례없는 폭등과 폭락을 반복하는 등 매우 민감한 가격 변동을 경험하였다. 특히 2024년 9월 서울특별시에서는 거래량 급감에도 불구하고 역대 최고 아파트 평균 매매가격이 경신되기도 하였다. 하지만 이러한 주택시장의 변동성은 지역에 따라 다소 이질적인 특성을 보이고 있다. 이에 본 연구에서는 최근 10년 간의 시계열적인 매매가격지 수를 기반으로 수도권 아파트의 주택 하위시장을 유형화하고 그 특성을 살펴보고자 한다. 이를 위해 수도권 시군구 단위로 2014-2024년 월간 아파트 매매가격지수 데이터셋을 구축하였고, 자기조직화 지도를 사용하여 매트릭스 형태의 시계열적 가격 변동을 2차원 공간상에 매핑하여 그래프로 작성하였다. 그 후 동적 타임 워핑을 유사성 척도로 하는 K-평균 군집화 및 계층적 밀도 기반 군집화 알고리즘을 이용한 시계열 군집 분석을 수행하여 주택 하위시장을 식별하였다. 연구 결과, 수도권 지역에서는 공통적으로 2014년 이후 아파트 매매가격이 지속적으로 상승하였고, 2020년을 기점으로 폭등한 후 2022년 급락하는 경향을 보였다. 그러나 지역별로 가격 변동의 정도와 패턴, 속도가 상이하였고 이에 대한 유형화를 진행한 결과 최종적으로 계단형(서울 인근 경기도 지역), 단기변동형(경기도 남･북부 지역), 안정형(경기도 서부 지역), 외곽 저속개발(수도권 외곽 및 접경지역), 지속상승(서울 및 인접 경기도 지역) 총 5개의 하위시장을 확인할 수 있었다. 본 연구는 민감한 가격 변동을 보이는 수도권 아파트의 하위시장을 실증적으로 구분하고, 하위시장의 독특한 시공간적 패턴에 대한 이해를 제공함으로써 향후 실효성 있는 지역 특수적 주택 정책 수립에 기여할 것으로 기대된다.

This study proposes a method to evaluate the publicity of real-time, demand-responsive, autonomous public-transportation systems. By analyzing real-time data collected based on publicity evaluation indicators suggested in previous research studies, this study seeks to establish a system that objectively assesses the publicity of public transportation. Thus, the introduction of autonomous public transportation systems is expected to contribute to solving problems in underserved transportation areas and enable more sophisticated public transportation operations. We reviewed evaluation indicators proposed in previous studies. Based on this review, publicity evaluation indicators were derived and specific criteria were selected to assess systematically the publicity of autonomous public transportation. An AHP analysis was conducted to assess the relative importance of each indicator by analyzing the importance of the selected indicators. Additionally, to score the indicators, minimum and maximum target values were established, and a method for assigning scores to each indicator was examined. The most important factor in the publicity evaluation of autonomous demand-responsive transport (DRT) was the “success rate of allocation to weak public transportation service areas,” with a significance level p of 0.204. This was analyzed as a key evaluation criterion because of the importance of service provision in areas with low-public-transportation accessibility. Subsequently, “Accessing distance to a virtual station” (p = 0.145) was evaluated as an important factor representing the convenience of the service. “Waiting time after allocation” (p = 0.134) also appeared as an important evaluation factor, as reducing waiting time considerably affected service quality. Conversely, “compliance rate of velocity” yielded the lowest significance (p = 0.017), as speed compliance was typically guaranteed owing to autonomous driving technology. This study proposed a specific evaluation method based on publicity indicators to provide a strategic direction for improving services and enhancing the publicity of autonomous DRT systems. These results can serve as a foundational resource for improving transportation services in underserved areas and for enhancing the overall quality of public transportation services. However, the study’s limitation was its inability to use real-time autonomous public transportation data, relying instead on I-MoD data from Incheon. This limitation constrained the ability to establish universal benchmarks because data from various municipalities were not included. Future research should collect and analyze data from diverse regions to establish more reliable evaluation indicators.