• 한국음향학회지
• /
• 제18권7호
• /
• pp.17-22
• /
• 1999

본 논문에서는 발화된 문장으로부터 운율 경계 강도를 효과적으로 예측하기 위해 LDA와 tri-tone 모델을 혼합한 방법을 제안하였다. 이 방법은 기존의 LDA 방법을 사용하여 음절과 휴지기의 길이 정보를 운율경계강도 예측에 적용하고 피치정보를 벡터양자화에 적용하여 tri-tone이란 개념을 도입한 혼합형 모형이다. 제안된 방법은 주어진 200문장의 운율경계 강도를 예측하는 실험에서 72%의 정확성을 나타내었다.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2003년도 가을 학술발표회 논문집
• /
• pp.604-607
• /
• 2003

Recently, hybrid concrete structures such as a concrete-filled steel tubular(CFT), a steel reinforced concrete(SRC) and a composite material are popular in structure applications. They also have merit of high strength, high ductility, and large energy absorption capacity. But the analysis of hybrid concrete structures is very difficult owing to the complex behavior of concrete under passive confinement. This paper has analyzed CFT, which receives passive confinement using Tri-Surface concrete model for three dimension finite element analysis. By the result of that, the proposed model was properly forecasted a concrete behavior that receives passive restraint as well as non-linear analysis of concrete which receive uniaxial stress and high active confinement of 400Mpa. If the model through the steady study is set up especially on the factor of concrete under passive confinement, the proposed concrete model will be surely useful for analysis of the hybrid concrete structures.

• 한국정보전자통신기술학회논문지
• /
• 제16권5호
• /
• pp.307-314
• /
• 2023

슈퍼컴퓨팅 기술 및 하드웨어 기술이 발전함에 따라 기후 예측 모델도 고도화되고 있다. 한국 기상청 역시 영국 기상청으로부터 GloSea5을 도입하였고 한국 기상 환경에 맞추어 업데이트된 GloSea6를 운용 중이다. 각 대학 및 연구기관에서는 슈퍼컴퓨터보다는 사양이 낮은 중소규모 서버에서 활용하기 위해 저해상도 결합모델인 Low-GloSea6를 구축하여 사용하고 있다. 본 논문에서는 중소규모 서버에서의 기상 연구의 효율성을 위한 Low-GloSea6 소프트웨어를 분석하여 가장 많은 CPU Time을 점유하는 대기 모델의 tri_sor.F90 모듈의 tri_sor_dp_dp 서브루틴을 Hotspot으로 검출하였다. 해당 함수에 머신러닝의 한 종류인 선형 회귀 모델을 적용하여 해당 기법의 가능성을 확인한다. 이상치 데이터를 제거 후 선형 회귀 모델을 학습한 결과 RMSE는 2.7665e-08, MAE는 1.4958e-08으로 Lasso 회귀, ElasticNet 회귀보다 더욱 좋은 성능을 보였다. 이는 Low-GloSea6 수행 과정 중 Hotspot으로 검출된 tri_sor.F90 모듈에 머신러닝 기법 적용 가능성을 확인하였다.

• 한국안전학회지
• /
• 제33권4호
• /
• pp.46-53
• /
• 2018

This study examined the maximum resistant moment and nonlinear rotational stiffness of wedge joint between the vertical and horizontal members of system supports. To examine the maximum resistant moment and propose the nonlinear rotation stiffness of wedge joint, 6 specimens were tested and additional 3 specimens, where the horizontal member was welded to the vertical member, were tested to compare the moment capacity of wedge joints. The average maximum moment in the tested wedge joint was 1.183 kNm which represented about 70 % of the maximum moment developed in the welded specimens. And, as simulating nonlinear rotational stiffness of the wedge joint, a tri-linear model was suggested. The rotational stiffness was estimated as 23.095 kNm/rad in first stage, 7.945 kNm/rad in second stage, and 3.073 kNm/rad in third stage. For the failure mode, the specimen with the wedge joint showed the failure of joint between vertical and horizontal members. However, the specimen with welded joint represented the yielding of horizontal members.

• Computers and Concrete
• /
• 제5권3호
• /
• pp.261-277
• /
• 2008

This paper presents methodologies for remaining life prediction of plain concrete structural components considering tension softening effect. Non-linear fracture mechanics principles (NLFM) have been used for crack growth analysis and remaining life prediction. Various tension softening models such as linear, bi-linear, tri-linear, exponential and power curve have been presented with appropriate expressions. A methodology to account for tension softening effects in the computation of SIF and remaining life prediction of concrete structural components has been presented. The tension softening effects has been represented by using any one of the models mentioned above. Numerical studies have been conducted on three point bending concrete structural component under constant amplitude loading. Remaining life has been predicted for different loading cases and for various tension softening models. The predicted values have been compared with the corresponding experimental observations. It is observed that the predicted life using bi-linear model and power curve model is in close agreement with the experimental values. Parametric studies on remaining life prediction have also been conducted by using modified bilinear model. A suitable value for constant of modified bilinear model is suggested based on parametric studies.

• Structural Engineering and Mechanics
• /
• 제34권3호
• /
• pp.301-317
• /
• 2010

This paper studies the reliability of an analytical tool for predicting the lateral load-deformation response of RC columns while subjected to lateral cyclic displacements and axial load. The analytical tool in this study is based on a fiber element model implemented into the program DRAIN-2DX (fiber element). The response of RC column under cyclic displacement is defined by the behavior of concrete, and reinforcing steel under general reversed-cyclic loading. A tri-linear stress-strain relationship for the cyclic behavior of steel is proposed and the improvement in the analytical results is studied. This study only considers the behavior of columns with flexural dominant mode of failure. It is concluded that with the implementation of appropriate constitutive material models, the described analytical tools can predict the response of the columns with reasonable accuracy when compared to experimental data.

• Steel and Composite Structures
• /
• 제1권2호
• /
• pp.245-268
• /
• 2001

The analysis of steel-concrete composite joints presents some particular aspects that increase their complexity when compared to bare steel joints. In particular, the influence of slab reinforcement and column concrete encasement clearly change the moment-rotation response of the joint. Starting from an energy approach developed in the context of steel joints, an extension to composite joints is presented in this paper that is able to provide closed-form analytical solutions. In addition, the possibility of tri-linear or non-linear component behaviour is also incorporated in the model, enabling adequate treatment of the influence of cracked concrete in tension and the softening response of the column web in compression. This methodology is validated through comparison with experimental tests carried out at the University of Coimbra.

• Journal of information and communication convergence engineering
• /
• 제22권2호
• /
• pp.165-171
• /
• 2024

In this study, we present a novel approach for enhancing chest X-ray image classification (normal, Covid-19, edema, mass nodules, and pneumothorax) by combining contrastive learning and machine learning algorithms. A vast amount of unlabeled data was leveraged to learn representations so that data efficiency is improved as a means of addressing the limited availability of labeled data in X-ray images. Our approach involves training classification algorithms using the extracted features from a linear fine-tuned Momentum Contrast (MoCo) model. The MoCo architecture with a Resnet34, Resnet50, or Resnet101 backbone is trained to learn features from unlabeled data. Instead of only fine-tuning the linear classifier layer on the MoCopretrained model, we propose training nonlinear classifiers as substitutes for softmax in deep networks. The empirical results show that while the linear fine-tuned ImageNet-pretrained models achieved the highest accuracy of only 82.9% and the linear fine-tuned MoCo-pretrained models an increased highest accuracy of 84.8%, our proposed method offered a significant improvement and achieved the highest accuracy of 87.9%.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1999년도 가을 학술발표회 논문집
• /
• pp.387-394
• /
• 1999

Artificial Neural Network (ANN) is a computational model inspired by the structure and operations of the brain. It is massively parallel system consisting of a large number of highly interconnected and simple processing units. The purpose of this paper is to verify the applicability of ANN to predict experimental results through the use of measured experimental data. Although there have been accumulated data based on hysteretic characteristics of structural element with cyclic loading tests, it is difficult to directly apply them for the analysis of elastic and plastic response. Thus, simple models with mathematical formula such as Bi-Linear Model, Ramberg-Osgood Model, Degrading Tri Model, Takeda Model, Slip type Model, and etc, have been used. To verify the practicality and capability of this study, ANN is adapted to several models with mathematical formula using numerical data To show the efficiency of ANN in nonlinear analysis, it is important to determine the adequate input and output variables of hysteretic models and to minimize an error in ANN process. The application example is Beam-Column joint test using the ANN in modeling of the linear and nonlinear hysteretic behavior of structure.

• Steel and Composite Structures
• /
• 제17권4호
• /
• pp.371-386
• /
• 2014

This paper presents a tri-linear restoring force model based on the test results of 12 circular RC columns strengthened by CFRP strips under low cyclic loading. The pre-stress of CFRP strips and axial load ratio of specimens are considered as the affect parameters of the proposed model. All essential characteristics of the hysteretic behavior of the proposed model, including the hysteretic rules, main performance points, strength degradation, stiffness degradation and confinement effects are explicitly analyzed. The calculated results from the proposed model are in good agreement with the experimental results, which shows that the recommended model can be reliably used for seismic behavior predictions of circular RC columns strengthened by pre-stressed CFRP strips.