• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.486-487
• /
• 2018

본 논문에서는 다선형 PCA(Principal Component Analysis)를 이용한 키넥트 센서 기반 댄스 모션분류방법을 제안한다. 댄스 모션 분류를 수행하기 위해서, 먼저 키넥트 데이터 깊이 영상과 이진영상을 보간법을 통해 데이터의 크기를 정렬시켜준다. 다음으로 다선형 주성분 분석 기법 (MPCA)을 이용하여 연속된 댄스모션영상들에 대한 특징을 추출하고, 유클리디안 분류기를 통해 클래스 분류한다. 본 실험에 사용된 데이터베이스는 키넥트 센서를 기반으로 전문 댄서 4명을 통해 취득된다. 총 100곡의 K-POP을 선정하였고, 곡마다 2개의 포인트 안무를 통해 총 200개의 포인트 댄스모션 데이터베이스를 구축하였다. 실험결과 제안된 방법은 89.5%의 성능을 나타낸다.

• Earthquakes and Structures
• /
• 제17권5호
• /
• pp.489-499
• /
• 2019

Elastic-plastic behavior of nuclear power plant elbow piping under seismic loads has been conducted in this study. Finite element analyses are performed using classical Bilinear kinematic hardening model (BKIN) and Multilinear kinematic hardening model (MKIN) as well as a nonlinear kinematic hardening model (Chaboche model). The influence of internal pressure and seismic loading on ratcheting strain of elbow pipe is studied by means of the three models. The results found that the predicted results of Chaboche model is maximum, closely followed by the predicted results of MKIN model, and the minimum is the predicted results of BKIN model. Moreover, comparisons of analysis results for each plasticity model against predicted results for a equivalent cyclic loading elbow component and for a simplified piping system seismic test are presented in the paper.

• Computers and Concrete
• /
• 제24권3호
• /
• pp.271-282
• /
• 2019

Concrete undergoes a series of thermo-based physio-chemical changes once exposed to elevated temperatures. Such changes adversely alter the composition of concrete and oftentimes lead to fire-induced explosive spalling. Spalling is a multidimensional, complex and most of all sophisticated phenomenon with the potential to cause significant damage to fire-exposed concrete structures. Despite past and recent research efforts, we continue to be short of a systematic methodology that is able of accurately assessing the tendency of concrete to spall under fire conditions. In order to bridge this knowledge gap, this study explores integrating novel artificial intelligence (AI) techniques; namely, artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA), together with traditional statistical analysis (multilinear regression (MLR)), to arrive at state-of-the-art procedures to predict occurrence of fire-induced spalling. Through a comprehensive datadriven examination of actual fire tests, this study demonstrates that AI techniques provide attractive tools capable of predicting fire-induced spalling phenomenon with high precision.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 추계학술발표대회
• /
• pp.295-297
• /
• 2011

본 논문에서는 동적얼굴영상으로부터 감정인식을 위해 벡터 표현 보다는 직접적인 텐서 표현으로 특징들을 추출하는 텐서 기반 다선형 주성분분석(MPCA: Multilinear Principal Component Analysis) 기법을 사용한다. 사람 6가지의 얼굴 표정을 사용하는데 한 사람의 각 표정마다 5프레임으로 묶어서 텐서 형태로 취하여 특징을 추출하고 인식한다. 시스템의 성능 평가는 CNU 얼굴 감정인식 데이터베이스를 이용하여 특징점 개수와 성능척도에 따른 실험을 수행하여 제시된 방법의 유용성에 관해 살펴본다.

• Structural Engineering and Mechanics
• /
• 제32권5호
• /
• pp.649-665
• /
• 2009

This paper reports part of a comprehensive research study conducted at the University of Queensland on the ability of CFRP web-bonded systems in strengthening an exterior beam-column joint subjected to monotonic loads. One 1/2.2 scaled plain and four CFRP repaired/retrofitted joints subjected to monotonic loads were analysed using the nonlinear finite-element program ANSYS and the results were calibrated against experiments. The ANSYS model was employed in order to account for tension stiffening in concrete after cracking and a modified version of the Hognestad's model was used to model the concrete compressive strength. The stress-strain properties of main steel bars were modelled using multilinear isotropic hardening model and the FRPs were modelled as anisotropic materials. A perfect bond was assumed as nodes were shared between adjacent elements irrespective of their type. Good agreement between the numerical predictions and the experimental observation of the failure mechanisms for all specimens were observed. Closeness of these results proved that the numerical analysis can be used by design engineers for the analysis of web-bonded FRP strengthened beam-column joints with confidence.

• 한국측량학회지
• /
• 제38권2호
• /
• pp.97-107
• /
• 2020

To analyze temporal and spatial changes in vegetation, it is necessary to determine the associated continuous distribution and conduct growth observations using time series data. For this purpose, the normalized difference vegetation index, which is calculated from optical images, is employed. However, acquiring images under cloud cover and rainfall conditions is challenging; therefore, time series data may often be unavailable. To address this issue, La et al. (2015) developed a multilinear simulation method to generate missing images on the target date using the obtained images. This method was applied to a small simulation area, and it employed a simple analysis of variables with lower constraints on the simulation conditions (where the environmental characteristics at the moment of image capture are considered as the variables). In contrast, the present study employs variables that reflect the growth characteristics of vegetation in a greater simulation area, and the results are compared with those of the existing simulation method. By applying the accumulated temperature, the average coefficient of determination (R²) and RMSE (Root Mean-Squared Error) increased and decreased by 0.0850 and 0.0249, respectively. Moreover, when data were unavailable for the same season, R² and RMSE increased and decreased by 0.2421 and 0.1289, respectively.

• 한국자동차공학회논문집
• /
• 제21권6호
• /
• pp.175-182
• /
• 2013

Lately, customers think highly of the emotional satisfaction and as a result, issues on odor are matters of concern. The cases are odor of interior material and air-conditioner of vehicles. In particualar, with respect to the odor of air-conditioner, customers strongly claimed defects with provocative comments : "It smells like something rotten," "It smells like a foot odor," "It stinks like a rag." Generally, it is known that mold of evaporator core in the air-conditioning system decays and this produce VOCs which causes the odor to occur. In this study, partial least squares regression model is applied to predict the strength of the odor and select of important VOCs which affect car air conditioning smell. The PLS method is basically a particular multilinear regression algorithm which can handle correlated inputs and limited data. The number of latent variable is determined by the point which is stabilized mean absolute deviations of VOCs data. Also multiple linear regression is carried out to confirm the validity of PLS method.

• 한국자동차공학회논문집
• /
• 제18권3호
• /
• pp.133-142
• /
• 2010

The present work focuses on the characterization of material parameters of the Overlay(multilinear hardening) model for analyzing the non-isothermal cyclic deformation. In the previous study, all the parameters were especially based on the Overlay theories, and a simple method was suggested to find out the best material parameters for the isothermal cyclic deformation analysis. Based on the previous research this paper f dther improves the isothermal parameters and suggests how to apply the isothermal parameters to the non-isothermal conditions especially for the description of TMF(Thermo-Mechanical Fatigue) hysteresis behavior. The parameters are determined and calibrated using 400 series stainless steel test data in the reference papers. For the implementation into ABAQUS, a user subroutine is developed by means of ABAQUS/UMAT. The finite element results show good agreement with test for the case of uniaxial non-isothermal cyclic loading, signifying the proposed method can be used in the TMF analysis of the converter-inserted heavy duty muffler system and the stainless steel exhaust-manifold system which are to be done in our future research.

• 한국강구조학회 논문집
• /
• 제12권1호통권44호
• /
• pp.29-43
• /
• 2000

본 연구에서는 비탄성 부재들의 좌굴 강도를 결정하기 위한 계산적으로 효율적인 비탄성 좌굴해석 프로그램이 개발되었다. 본 프로그램은 휨 좌굴, 휨-비틂 좌굴 혹은 국부좌굴에 의해 붕괴되는 탄성과 비탄성 부재들의 좌굴 강도 및 형상을 결정할 수 있다. 일축 대칭이나 2축 대칭인 I 형 부재를 해석할 수 있다. 복부판은 판 요소를 이용하여 모델되고, 플랜지는 보 요소로 모델되었다. 재료의 비탄성 응력-변형률 관계를 모사하기 위하여 다선형 등방경화 법칙과 증분이론이 사용되었다. 프로그램은 이론치와 실험값들을 이용하여 입증되었다. 프로그램의 결과는 이론치 및 실험값들과 잘 일치였다.

• Safety and Health at Work
• /
• 제11권3호
• /
• pp.314-321
• /
• 2020

Background: Occupational accidents occur for a variety of reasons, such as unsafe behaviors of workers and insufficient safety equipment at the workplace, but there are also various economic and social factors that can impact working conditions and working environment. This study analyzed the relationship between changes in economic factors and the occurrence of occupational accidents in Korea. Methods: Multilinear regression analysis was used as the analysis model. The general to specific method was also used, which consecutively removes statistically insignificant variables from a general model that includes dependent variables and lagged variables of dependent variables. Results: The frequency of occupational accidents was found to have a statistically significant relationship to economic indicators. The monthly number of cases of occupational injury and disease and fatal occupational injuries were found to be closely related to manufacturing capacity utilization, differences in the production index in the services sector, and commencements of building construction. The increase in equipment investment indicators was found to reduce fatal occupational injuries. Conclusion: The results of this study may be used to develop occupational accident trends or leading indicators, which in turn can be used by organizations that manage and monitor occupational accidents toward taking administrative action designed to reduce occupational accidents. The results also imply that short-term and mid- to long-term economic and social changes that can impact workers, workplaces and working conditions, and workplace organizations must be taken into account if more effective government policies are to be established and implemented toward further prevention of occupational accidents.