본 논문에서는 건설 현장 관리의 과제를 다루고 IoT 기술 활용을 위한 기술 적용에 대해 정리하였다. 도로 포장 장비의 유휴 시간을 모니터링하는 IoT 장치를 설계 및 구현하여 효율적인 장비 관리 시스템을 개발하는 것을 목표한다. 또한, 본 연구에서는 통신방식 선 정, 사용자 친화적인 플랫폼 설계, 데이터 수집 및 분석을 위한 진동센서 기반 IoT 디바이스 개발을 통한 실시간 관리에 중점을 두고 있다. 플랫폼을 통해 공사현황을 실시간으로 모니터링하고 장비 유휴시간을 관리해 효율성을 높일 수 있으며, IoT 디바이스는 90% 이 상의 데이터 정확도를 보장한다. 현장 테스트를 통해 장비 사용 추적 효과가 확인되어 보다 효율적인 건설 관리에 기여하고자 한다.

본 연구는 2017년부터 2021년까지 고속도로에서 발생한 약 9,600건의 사고를 분석하여 자율주행 긴급차량의 신속한 대응 능력을 향 상시키고자 하였다. 조사 결과, 2차 사고가 전체 사망자의 16.8%를 차지하며, 이들 중 약 74%가 선행사고와 관련이 있다는 점이 강조 된다. 이러한 통계는 긴급차량의 신속한 대처 능력이 피해를 최소화하는 데 얼마나 중요한지를 보여준다. 연구에서는 사고의 영향권을 정의하고, 이를 기반으로 긴급차량이 보다 안전하고 효율적으로 사고 현장에 접근할 수 있도록 하는 알고리즘을 개발하였다. 실제 교 통사고 데이터를 활용하여 사고 지속 시간과 다양한 변수를 고려한 기초 분석을 실시하였으며, 도로 특성, 사고 종류, 점유 차로 등 여러 요소를 반영하여 대응 기준을 설정했다. 알고리즘은 자율주행 차량이 실시간으로 주변 정보를 수집하고 신속하게 대응 방안을 마련할 수 있도록 설계되었다. 향후 연구에서는 알고리즘의 실제 도로 환경에서의 적용 가능성을 검토하고, 다양한 변수들을 포함한 추가 연구를 통해 성능을 더욱 개선할 계획이다. 이러한 연구 결과는 교통사고로 인한 피해를 줄이는 데 기여하고, 자율주행 기술을 활용하여 2차 사고의 가능성을 감소시키는 데 중요한 역할을 할 것으로 기대된다.

기존 신호제어기법은 과거 주기에 파악된 교통상황을 바탕으로 다음 주기의 교통신호시간을 설계하는 방식으로 신호시간을 설계하기 위해 관측할 때의 교통상황과 신호시간을 제공받는 교통상황 간의 간극이 존재하였다. 또한, 설정된 주기길이 동안 차량이 교차로에 일정하게 도착하는 균일분포를 가정하지만, 실제 교차로에 도착하는 교통량의 행태는 비 균일분포로 실제 교통수요에 대응하기 어렵 다는 한계가 존재한다. 본 연구는 이러한 한계를 극복하기 위해 교차로로 진입하는 상류 교차로의 교통정보를 활용하여 단기 미래 도 착 교통량 예측모델 개발을 통해 관측 시점과 제공 시점 간의 간극을 최소화한다. 또한, 기존 주기길이 동안의 교통량 도착분포를 비 균일분포로 가정하여 주기길이가 고정되지 않는 방식(Acyclic)의 적응식 신호제어 기법(ATC) 개발한다. 제안된 단기 미래 도착 교통 량 예측모델은 실제 스마트교차로 자료를 가공하여 시뮬레이션을 통하여 학습데이터를 구축하여 장단기 메모리(LSTM) 모형과 시간 분산(TimeDistributed) 모형을 적용하여 딥러닝 모델을 개발하였다. 적응식 교통신호제어 기법은 실시간 예측 교통량을 활용하여 교통 류별 예측 지체 산출을 통하여 지체가 최소화되는 현시 종료 지점에서 현시를 종료하고 다음 시간 단계에서 예측된 교통량을 통해 최 적 현시를 재산출하는 롤링 호라이즌(Rolling Horizon)을 수행한다. 제안 신호제어 기법의 평가를 위해 미시적 교통 시뮬레이션을 활 용하여 기존 신호제어 기법인 TOD 신호제어 기법과 제안기법 간의 평가를 수행하였다.

실시간 온라인 게임 서버에서의 게임 상태 동기화는 중요한 문제이며, 기존 동기화 방식은 상황 에 따라 성능이 변동하는 한계가 있다. 본 연구에서는 이를 해결하기 위해 하이브리드 동기화 방 식을 제안한다. 클라이언트 간 거리가 가까울 때는 Lockstep 방식을, 멀 때는 서버 동기화 방식 을 사용하여 일관성과 가용성을 모두 만족시킨다. 술래잡기 게임에서 하이브리드 방식을 적용한 결과, 기존 방식보다 최대 74.6% 향상된 위치 일관성과 23.6% 감소된 응답시간을 달성했다.

This study investigated the characteristics of personal PM2.5 exposure among 109 participants residing in Seoul over a two-month period, from February 2024 to April 2024. The participants were categorized into four sub-populations, and personal exposure to PM2.5 was assessed using portable monitors, GPS, and time-activity diaries. To understand the time-activity patterns, the daily occupancy rate for different microenvironments was calculated. Additionally, daily PM2.5 exposure contribution and integrated exposure were quantified. A time series analysis was conducted to identify differences in time-activity patterns and PM2.5 exposure among the sub-populations. ANOVA analysis indicated statistically significant differences in PM2.5 concentrations across populations and microenvironments (p<0.05). However, post-hoc analysis revealed specific microenvironments within certain sub-populations where PM2.5 concentration differences were not significant (p>0.05). All sub-populations spent more than 90% of their time indoors, and the results for exposure contribution and integrated exposure indicated that the home, which had the highest occupancy rate, was the most significant contributor to PM2.5 exposure. This study is expected to serve as foundational data for future indoor air quality management and the development of personalized strategies for reducing PM2.5 exposure.

본 연구에서는 노인의 건강 증진 및 건강 유지를 위해 노인 맞춤형 운동 애플리케이션 개발을 목표로, 스마트폰을 활용한 실시간 동작 추적 기술과 영상과 사진을 바탕으로 한 AI 학습을 통 해 단계별 동작 인식과 판단이 가능한 운동 동작 모델을 구현하였다. 노인 맞춤형 운동 애플리 케이션은 실시간 피드백을 지원하고, 노인의 운동 능력과 신체 가동 범위에 적합하게 단계적 운동이 가능하도록 구현되어야 할 것이다. 이를 위해 본 논문에서는 골포스트 스퀴즈(Goal Post Squeeze) 운동 동작을 대상으로 하여 이를 일련의 단위 동작으로 설계하고, MoveNet 포 즈 추정 기법을 기반으로 동작 인식 모델을 개발하였다. 구현한 운동 동작 모델에 대한 작동 실험 결과 단계별 데이터 인식과 판단, 정동작과 오동작 판단, 수평유지를 판단하고 이를 바탕 으로 사용자에게 실시간 피드백을 제공할 수 있음을 확인하였다.

In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetration including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder’s status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multivariate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.

As the size of the gaming market continues to grow, game engines like Unity and Unreal are constantly being developed and updated for multi-platform support. In particular, Unity divides the Render Pipeline to be used. Among them, the Universal Render Pipeline (URP) has the advantage of supporting various platforms while improving performance by reducing draw calls and batches at the same quality settings and reducing the load on the CPU and GPU. However, only limited global illumination is supported in the real-time 3D rendering area within URP, such as Baked GI and Enlighten GI, and Enlighten GI will be deprecated after 2024LST, so real-time global illumination is not available in URP, which may reduce the realism and immersion of global illumination in games or applications that use URP. The main objective of this research is to incorporate precomputed spherical harmonics into URP to enable dynamic GI updates in real-time. The approach proposed in this research is to compute the coefficients of spherical harmonics offline and then run them within the URP rendering pipeline, where work exists to effectively simulate dynamic lighting conditions. To demonstrate this, experiments were conducted by changing the rotation and color of the lights, and a comparative analysis was performed to demonstrate the effectiveness of the theory proposed in this work.

이 글은 내가 최근에 종이 위에 작업한 작품들의 개요를 보여주는 데 목적이 있다. 이를 통해 작품들에서의 터치, 시간, 운동의 모든 측면과, 제작 과정과 관람 경험에 대한 발견을 전반적으로 제공하고자 한다. 나는 2022년의 대형 드로잉 작업 <목욕하는 사람들 I>과 2023년의 새로운 디지털 비디오 <그림자 속의 어떤 빛>에서 번역과 변환에 집중하고 있는 데, 손으로 들고 촬영하는 방식으로 터치, 시간, 운동의 요소들이 아이폰 카메라에 어떻게 반영되는지를 보여주기 위해서다. 이때 다양한 해상도와 프레임 속도의 사용은 후반 작업에 서 영상의 속도를 늦추는 방식과 결합하여 새로운 등가물을 만들어 내게 된다. 나는 갤러리 에서의 관람객들의 실시간 시청 경험을 고려하고 탐색하기 위해 스튜디오에서의 활동 결과 를 병렬하고 기록하는 촬영 관행도 개발하였다. 이는 특히 커다란 포맷의 네거티브 이미지 아날로그 사진들을 이용하여 손으로 만든 작품을 치환하는 것을 탐구한 나의 초기 실습을 통해서 맥락화된 결과이다. 나는 또한 이 글에서 19세기 후반의 사진, 광학, 회화의 발전, 특히 조르주 쇠라의 점묘법 작품과 나의 현재 작업 사이의 연관성에 대해 논의했다.

Water utilities are making various efforts to reduce water losses from water networks, and an essential part of them is to recognize the moment when a pipe burst occurs during operation quickly. Several physics-based methods and data-driven analysis are applied using real-time flow and pressure data measured through a SCADA system or smart meters, and methodologies based on machining learning are currently widely studied. Water utilities should apply various approaches together to increase pipe burst detection. The most intuitive and explainable water balance method and its procedure were presented in this study, and the applicability and detection performance were evaluated by applying this approach to water supply pipelines. Based on these results, water utilities can establish a mass balance-based pipe burst detection system, give a guideline for installing new flow meters, and set the detection parameters with expected performance. The performance of the water balance analysis method is affected by the water network operation conditions, the characteristics of the installed flow meter, and event data, so there is a limit to the general use of the results in all sites. Therefore, water utilities should accumulate experience by applying the water balance method in more fields.

High-temperature molten salts not only demonstrate exceptional thermal and chemical stability but also offer significant advantages in catalyzing chemical reactions. Consequently, they have garnered attention as a promising medium for next-generation nuclear reactors and a wide range of electrochemical processes. Nevertheless, the challenging experimental conditions in molten salts make applying conventional analytical methods to understand reaction mechanisms a formidable task. This underscores the imperative need for more intuitive approaches to investigate molten salt chemistry. One of the simplest yet potent methods involves real-time visual monitoring of the reaction system as chemical reactions progress. In light of this, we have developed an experimental system enabling real-time visual monitoring of the internal dynamics of molten salt media. This system can capture high-resolution videos and images within molten salts, surpassing existing methodologies. We have applied this system in various electrochemical experiments using the molten LiCl-KCl eutectic salt medium. Among them, this study primarily focuses on two challenging experimental scenarios that became comprehensible through our proposed system’s application: (1) the transpassivation of Zr metal and the agglomeration of potassium hexachlorozirconate (K2ZrCl6) solid salt, and (2) the solvation of electrons during the oxidation of Li metal within the molten LiCl-KCl eutectic salt.

When decommissioning a nuclear power plant, it is expected that clearance or radioactive waste (e.g., soil, concrete, metal, etc.) below the low-level will be generated in a short period on a large scale. Among the various types of waste, most of the contaminated soil is known to be classified as clearance or the (very) low-level radioactive waste. Accordingly, an accurate measurement and classification of contaminated soil in real-time during the decommissioning process can efficiently reduce the amount of soil waste and the possibility of contamination diffusion. However, in order to apply a system that measures and classifies contaminated soil in real-time according to the level of contamination to the decommissioning site, a demonstration is required to evaluate whether the system is applicable to the site. In this study, to establish requirements for determining the applicability of the system to the decommissioning site, preceding cases from countries with abundant decommissioning experience were investigated. For example, MACTEC of the U.S. demonstrated the developed system at the Saxton nuclear power plant in the U.S. and confirmed that the amount of soil that can be analyzed per hour in the system is affected by radionuclides, minimum detectable activity (MDA), and applicable volume. In the future, therefore, we will utilize the result of this study to develop the requirements of demonstrating the system for measurement and classification of contaminated soil in real-time.

In the realm of dental prosthesis fabrication, obtaining accurate impressions has historically been a challenging and inefficient process, often hindered by hygiene concerns and patient discomfort. Addressing these limitations, Company D recently introduced a cutting-edge solution by harnessing the potential of intraoral scan images to create 3D dental models. However, the complexity of these scan images, encompassing not only teeth and gums but also the palate, tongue, and other structures, posed a new set of challenges. In response, we propose a sophisticated real-time image segmentation algorithm that selectively extracts pertinent data, specifically focusing on teeth and gums, from oral scan images obtained through Company D's oral scanner for 3D model generation. A key challenge we tackled was the detection of the intricate molar regions, common in dental imaging, which we effectively addressed through intelligent data augmentation for enhanced training. By placing significant emphasis on both accuracy and speed, critical factors for real-time intraoral scanning, our proposed algorithm demonstrated exceptional performance, boasting an impressive accuracy rate of 0.91 and an unrivaled FPS of 92.4. Compared to existing algorithms, our solution exhibited superior outcomes when integrated into Company D's oral scanner. This algorithm is scheduled for deployment and commercialization within Company D's intraoral scanner.

On pig farms, the highest mortality rate is observed among nursing piglets. To reduce this mortality rate, farmers need to carefully observe the piglets to prevent accidents such as being crushed and to maintain a proper body temperature. However, observing a large number of pigs individually can be challenging for farmers. Therefore, our aim was to detect the behavior of piglets and sows in real-time using deep learning models, such as YOLOv4-CSP and YOLOv7-E6E, that allow for real-time object detection. YOLOv4-CSP reduces computational cost by partitioning feature maps and utilizing Cross-stage Hierarchy to remove redundant gradient calculation. YOLOv7-E6E analyzes and controls gradient paths such that the weights of each layer learn diverse features. We detected standing, sitting, and lying behaviors in sows and lactating and starving behaviors in piglets, which indicate nursing behavior and movement to colder areas away from the group. We optimized the model parameters for the best object detection and improved reliability by acquiring data through experts. We conducted object detection for the five different behaviors. The YOLOv4-CSP model achieved an accuracy of 0.63 and mAP of 0.662, whereas the YOLOv7-E6E model showed an accuracy of 0.65 and mAP of 0.637. Therefore, based on mAP, which includes both class and localization performance, YOLOv4-CSP showed the superior performance. Such research is anticipated to be effectively utilized for the behavioral analysis of fattening pigs and in preventing piglet crushing in the future.

The cutting process, which is a key processing technology in various industrial fields is achieving continuous growth, and the demand for high-quality cutting surfaces is continuously demanded. Plasma cutting continues to be studied for its excellent workability and productivity, but problems with cutting surface quality such as dross formation occur, so research to secure excellent cutting surface quality through appropriate control of process variables is essential. In this study, we propose a method for predicting surface roughness using real-time current and cutting speed data obtained while performing plasma cutting on A106 B steel pipe. Surface roughness was predicted based on the RBF algorithm applicable to prediction and control models. It was shown that the surface roughness of the plasma cutting surface can be predicted with the arc current waveform and process speed data. This study can be used as a basic study to control the surface roughness of the cut surface in real time.