• 한국정보통신학회논문지
• /
• 제25권3호
• /
• pp.396-402
• /
• 2021

최근 스마트 도시를 구축하기 위해 무인 차량 관제 시스템의 보급이 활성화 되고 있다. 본 논문은 적응적 배경영상 모델링 방법을 이용한 불법주정차 무인단속시스템에 관한 것으로서, 적응적 가우시안 혼합 모델로 배경 영상을 모델링할 때, 이동 물체의 상황 변화에 따라 전역적으로 배경 영상을 업데이트하거나 국소적으로 배경 영상을 업데이트하는 방법에 대해 기술한다. 특히, 이동 물체가 배경 영상에 미치는 영향을 최소화하는 방법과 배경 영상을 정확하게 업데이트하기 위한 방법을 제안한다. 본 논문에서는 시스템의 구현을 통해 제안하는 시스템이 이동하고 있는 물체 또는 정지상태의 물체를 신속하고 정확하게 구분할 수 있음을 증명하였다.

• 한국인터넷방송통신학회논문지
• /
• 제22권6호
• /
• pp.83-89
• /
• 2022

최근 정보통신기술의 발전에 따라 사물인터넷 기술이 비약적으로 발전하고 있다. IoT 기술은 다양한 센서들을 활용하여 각 센서의 고유한 데이터를 발생시켜 시스템 상태의 진단을 가능하도록 한다. 하지만, 현재 적용되고 있는 장비운용 시스템은 장비에 문제가 발생한 후 관리자가 해당 문제를 처리해야하는 사후보전 방식의 개념이며, 이는 시스템의 에러로 인한 시스템의 신뢰성 및 가용성 문제점을 의미할 수 있으며, 정비를 위한 시스템 중단으로 생산성에 부정적 영향으로 인한 경제적 손실을 초래할 수 있다. 따라서, 본 연구에서는 지능형 IoT(AIoT) 기술을 적용하여 공장 내 정류기를 보다 효율적으로 운용하기 위한 엣지 컨트롤러 제어 의사 결정 알고리즘과, 정류기 부품별 고장 상황 정보에 대한 도메인 지식 기반의 모델링을 작성하여, 이를 바탕으로 수집된 각 센서 데이터에 대한 상관관계 분석을 통해 시나리오별 Abnormal 데이터에 대하여 적정 수준의 상태 메시지를 출력함을 확인할 수 있었으며, 이를 통한 기존 현장의 장비 운용 시스템의 가용성과 생산성이 향상됨을 확인하였다.

• Journal of Radiation Protection and Research
• /
• 제47권3호
• /
• pp.111-133
• /
• 2022

The exciting advancement related to the "modeling of digital human" in terms of a computational phantom for radiation dose calculations has to do with the latest hype related to deep learning. The advent of deep learning or artificial intelligence (AI) technology involving convolutional neural networks has brought an unprecedented level of innovation to the field of organ segmentation. In addition, graphics processing units (GPUs) are utilized as boosters for both real-time Monte Carlo simulations and AI-based image segmentation applications. These advancements provide the feasibility of creating three-dimensional (3D) geometric details of the human anatomy from tomographic imaging and performing Monte Carlo radiation transport simulations using increasingly fast and inexpensive computers. This review first introduces the history of three types of computational human phantoms: stylized medical internal radiation dosimetry (MIRD) phantoms, voxelized tomographic phantoms, and boundary representation (BREP) deformable phantoms. Then, the development of a person-specific phantom is demonstrated by introducing AI-based organ autosegmentation technology. Next, a new development in GPU-based Monte Carlo radiation dose calculations is introduced. Examples of applying computational phantoms and a new Monte Carlo code named ARCHER (Accelerated Radiation-transport Computations in Heterogeneous EnviRonments) to problems in radiation protection, imaging, and radiotherapy are presented from research projects performed by students at the Rensselaer Polytechnic Institute (RPI) and University of Science and Technology of China (USTC). Finally, this review discusses challenges and future research opportunities. We found that, owing to the latest computer hardware and AI technology, computational human body models are moving closer to real human anatomy structures for accurate radiation dose calculations.

• 한국전산구조공학회논문집
• /
• 제35권3호
• /
• pp.191-196
• /
• 2022

본 연구에서는 3D 프린팅 FDM 방식의 적층 방향에 따라 기계적 물성이 달라지는 이방성 특성을 확인하고 이를 이용하여 위상 최적설계를 수행하였다. 벤치마크 문제인 자동차 현가장치 부품 중 하나인 로어 컨트롤 암에 대하여 밀도법 기반 위상 최적설계를 수행하였으며, 외부 하중과 이방성 특성에 따라 위상 최적결과가 다르게 나타나는 것을 확인하였다. 이를 이용하여 최적화된 모델에 대하여 3D 프린터로 적층 방향을 달리하여 2가지 시험품을 제작하였으며 인장시험을 수행하였다. 시험시 3D 비접촉 변형률 측정기를 이용하여 변형률을 구하였으며 이를 CAE 응답해석으로 얻은 변형률과 비교한 결과가 정량 및 정성적으로 일치하는 것을 확인하였다. 3D 프린팅 적층 방향을 고려한 위상 최적모델의 인장 실험 결과를 통해 해당 최적설계 방법론의 유효성을 검증하였다.

• 한국분말재료학회지
• /
• 제29권1호
• /
• pp.14-21
• /
• 2022

In the powder bed fusion (PBF) process, a 3D shape is formed by the continuous stacking of very fine powder layers using computer-aided design (CAD) modeling data, following which laser irradiation can be used to fuse the layers forming the desired product. In this method, the main process parameters for manufacturing the desired 3D products are laser power, laser speed, powder form, powder size, laminated thickness, and laser diameter. Stainless steel (STS) 316L exhibits excellent strength at high temperatures, and is also corrosion resistant. Due to this, it is widely used in various additive manufacturing processes, and in the production of corrosion-resistant components with complicated shapes. In this study, rectangular specimens have been manufactured using STS 316L powder via the PBF process. Further, the effect of heat treatment at 800 ℃ on the microstructure and hardness has been investigated.

• Steel and Composite Structures
• /
• 제44권2호
• /
• pp.241-254
• /
• 2022

The cables in a cable-stayed bridge are critical load-carrying parts. The potential damage to cables should be identified early to prevent disasters. In this study, an efficient deep learning model is proposed for the damage identification of cables using both a multi-layer perceptron (MLP) and a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), which is a robust program for modeling and analyzing bridge structures with low computational costs. The model based on the MLP and GNN can capture complex nonlinear correlations between the vibration characteristics in the input data and the cable system damage in the output data. Multiple hidden layers with an activation function are used in the MLP to expand the original input vector of the limited measurement data to obtain a complete output data vector that preserves sufficient information for constructing the graph in the GNN. Using the gated recurrent unit and set2set model, the GNN maps the formed graph feature to the output cable damage through several updating times and provides the damage results to both the classification and regression outputs. The model is fine-tuned with the original input data using Adam optimization for the final objective function. A case study of an actual cable-stayed bridge was considered to evaluate the model performance. The results demonstrate that the proposed model provides high accuracy (over 90%) in classification and satisfactory correlation coefficients (over 0.98) in regression and is a robust approach to obtain effective identification results with a limited quantity of input data.

• Advances in nano research
• /
• 제12권1호
• /
• pp.81-99
• /
• 2022

The aim of current work is to evaluate thermo-electrical characteristics of graphene nanoplatelets Reinforced Composite (GNPRC) coupled with magneto-electro-elastic (MEE) face sheet. In this regard, a cylindrical smart nanocomposite made of GNPRC with an external MEE layer is considered. The bonding between the layers are assumed to be perfect. Because of the layer nature of the structure, the material characteristics of the whole structure is regarded as graded. Both mechanical and thermal boundary conditions are applied to this structure. The main objective of this work is to determine critical temperature and critical voltage as a function of thermal condition, support type, GNP weight fraction, and MEE thickness. The governing equation of the multilayer nanocomposites cylindrical shell is derived. The generalized differential quadrature method (GDQM) is employed to numerically solve the differential equations. This method is integrated with Deep Learning Network (DNN) with ADADELTA optimizer to determine the critical conditions of the current sandwich structure. This the first time that effects of several conditions including surrounding temperature, MEE layer thickness, and pattern of the layers of the GNPRC is investigated on two main parameters critical temperature and critical voltage of the nanostructure. Furthermore, Maxwell equation is derived for modeling of the MEE. The outcome reveals that MEE layer, temperature change, GNP weight function, and GNP distribution patterns GNP weight function have significant influence on the critical temperature and voltage of cylindrical shell made from GNP nanocomposites core with MEE face sheet on outer of the shell.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• 한국인터넷방송통신학회논문지
• /
• 제22권1호
• /
• pp.65-70
• /
• 2022

최근 고속 스토리지의 활성화로 인해 하드디스크를 전제로 설계된 메모리 관리 시스템에 대한 재고가 필요한 시점에 이르렀다. 본 논문은 고속 스토리지 환경에서 메모리 접근 시간이 페이지 크기에 민감한 점을 관찰하고, 그 이유가 페이지 폴트율보다 TLB 미스율이 메모리 접근시간에 미치는 영향력이 커졌기 때문임을 확인하였다. 또한, TLB 미스율과 페이지 폴트율이 페이지 크기 변화에 따라 상충관계를 나타냄을 확인하고 이를 모델링하는 함수를 설계하였다. TLB 미스율의 경우 파워 피팅을 통한 모델링을 하였으며, 페이지 폴트율의 경우 2개의 항을 가진 지수 피팅을 통한 모델링을 하였다. 검증 실험을 통해 설계된 모델 함수에 의한 예측치가 실제 결과값을 잘 반영함을 확인하였다.

• 보존과학회지
• /
• 제38권4호
• /
• pp.277-288
• /
• 2022

'Eve 58-1', the subject of this study is a statue made of plaster and its structural stability was evaluated by utilizing the CAE program in order to prevent the risk of damage arising from impact and vibration that are generated during the packaging and transportation process given its material characteristics. CAE is an abbreviation for Computer Applied Engineering for realization by predicting changes at the time of application of virtual physical energy. It is applied by reflecting the physical property conditions and each boundary condition of plaster, and the digital images of the internal and external structure of the work were acquired through 3D scanning and CT analysis for interpretation by executing finite element modeling. When acceleration is applied to the work in the direction of its own weight, the left-right side and the front-rear side, it was possible to confirm a maximum displacement value of 15.24 mm in the head section of the front-rear side direction that has been tilted by approximately 27° from the Y-axis and the largest stress value of 12.46 MPa was at the left ankle section. The corresponding results confirmed that the left ankle section is the most vulnerable area and the section for which precautions need to be exercised and supplemented at the time of transporting the work by means of objective values.