• PNF and Movement
• /
• v.10 no.4
• /
• pp.41-48
• /
• 2012

Purpose : The purpose of his study was to analyze the environmental and the medical selection factor on rehabilition hospital admission. Methods : The subjects were 107 patient and inpatients. The date were collected analyzed using the SPSS window 17.0 program. Results : General hospital select the recommendation 35.5%, medical team professionalism 18%, accessibility 16%, any others 14% appear in the rehabilitation hospital admission selection factor. Conclusion : Rehabilitation hospital admission selection factor is recommend and medical team service approach.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.2
• /
• pp.89-97
• /
• 2021

This paper describes an adaptive hybrid evolutionary firefly algorithm for a topology optimization of truss structures. The truss topology optimization problems begins with a ground structure which is composed of all possible nodes and members. The optimization process aims to find the optimum layout of the truss members. The hybrid metaheuristics are then used to minimize the objective functions subjected to static or dynamic constraints. Several numerical examples are examined for the validity of the present method. The performance results are compared with those of other metaheuristic algorithms.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.1
• /
• pp.61-70
• /
• 2021

This paper describes a novel zero-stress member selecting method for sizing optimization of truss structures. When a sizing optimization method with static constraints is implemented, the member stresses are affected sensitively with changing the variables. However, because some truss members are unaffected by specific loading cases, zero-stress states are experienced by the elements. The zero-stress members could affect the computational cost and time of sizing optimization processes. Feature selection approaches can be then used to eliminate the zero-stress member from the whole variables prior to the process of optimization. Several numerical truss examples are tested using the proposed methods.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.4
• /
• pp.39-48
• /
• 2021

In this paper, a GAN-based data augmentation method is proposed for topology optimization. In machine learning techniques, a total amount of dataset determines the accuracy and robustness of the trained neural network architectures, especially, supervised learning networks. Because the insufficient data tends to lead to overfitting or underfitting of the architectures, a data augmentation method is need to increase the amount of data for reducing overfitting when training a machine learning model. In this study, the Ganerative Adversarial Network (GAN) is used to augment the topology optimization dataset. The produced dataset has been compared with the original dataset.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.237-240
• /
• 2021

Failure of a suspension clamp made of hot dip galvanized cast iron in 154kV transmission tower was investigated. Metallurgical analysis of a crack of the clamp was performed using a digital microscope, an optical microscope, and a scanning electron microscope. It was revealed that the crack surface was covered by continuous zinc layer. Distinctive casting skin was found underneath both the outer surface and crack surface. The result showed that pre-existing crack had been formed in the fabrication, and liquid metal embrittlement during hot dip galvanization may assist crack propagation.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.604-607
• /
• 2022

본 논문은 사용자의 질의에 대한 답변을 제공하는 질의 응답 시스템에서, 제공하는 답변이 사용자의 질의에 대하여 문서에 근거하여 올바르게 대답하였는지 검증하는 QDR validator에 대해 기술한 논문이다. 본 논문의 과제는 문서에 대한 주장을 판별하는 자연어 추론(Natural Language inference, NLI)와 유사한 과제이지만, 문서(D)와 주장(R)을 포함하여 질의(Q)까지 총 3가지 종류의 입력을 받아 NLI 과제보다 난도가 높다. QDR validation 과제를 수행하기 위하여, 약 16,000 건 데이터를 생성하였으며, 다양한 입력 형식 실험 및 NLI 과제 데이터 추가 학습, 임계 값 조절 실험을 통해 최종 83.05% 우수한 성능을 기록하였다

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.109-114
• /
• 2022

질의 생성 모델은 스마트 스피커, 챗봇, QA 시스템, 기계 독해 등 다양한 서비스에 사용되고 있다. 모델을 다양한 서비스에 잘 적용하기 위해서는 사용자들의 실제 질의 특성을 반영한 자연스러운 질의를 만드는 것이 중요하다. 본 논문에서는 사용자 질의 특성을 반영한 간결하고 자연스러운 질의 자동 생성 모델을 소개한다. 제안 모델은 topic 키워드를 통해 모델에게 생성 자유도를 주었으며, 키워드형 질의→자연어 질의→응답으로 연결되는 chain-of-thought 형태의 다중 출력 구조를 통해 인과관계를 고려한 결과를 만들도록 했다. 최종적으로 MRC 필터링과 일관성 필터링을 통해 고품질 질의를 선별했다. 베이스라인 모델과 비교해 제안 모델은 질의의 유효성을 크게 높일 수 있었다.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.221-224
• /
• 2021

본 논문은 WebAssembly 가 도입된 2017 년부터 현재 2021 년까지 발생한 보안 취약점을 분석하고 분류하여, WebAssembly 에 대한 개발자들의 이해도를 높이고 WebAssembly 도입에 생길 수 있는 문제점들을 정리한다. 특히 CVE-2018-6092(Integer Overflow), CVE-2018-6036(Underflow) 사례들을 제공된 PoC 를 통하여 재현하고, PoC 코드, 원인 코드와 대처 코드까지 분석한다.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.2
• /
• pp.91-99
• /
• 2024

In this paper, machine learning models were applied to predict the seismic response of steel frame structures. Both geometric and material nonlinearities were considered in the structural analysis, and nonlinear inelastic dynamic analysis was performed. The ground acceleration response of the El Centro earthquake was applied to obtain the displacement of the top floor, which was used as the dataset for the machine learning methods. Learning was performed using two methods: Decision Tree and Random Forest, and their efficiency was demonstrated through application to 2-story and 6-story 3-D steel frame structure examples.

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2010.04a
• /
• pp.530-531
• /
• 2010