• 한국실내디자인학회논문집
• /
• 제22권4호
• /
• pp.113-120
• /
• 2013

This study aims to determine adolescents' emotional response and preferences for varying interior designs of learning spaces available at community facilities in apartment across Seoul. In particular, the subjects have been fragmented by gender and age for comparative analysis of emotional responses across different demographics of adolescents. A survey on the preferred designs of learning spaces in community facilities revealed that 'elegant,' 'cheerful,' and 'temperate' are the three main emotional words selected for image tool development. Emotional assessment verified the validity of these terms. Between the two genders, adolescent males preferred 'temperate' images more while adolescent females preferred 'cheerful.' In terms of the design of learning space, adolescent females deemed the interior atmosphere and area space to be the most important factors, while adolescent males pointed to the color of furniture and lighting to be the most important. Such results imply that there is a clear difference of emotional response between adolescent males and females. The results also imply that different atmospheres and design priorities must be considered when designing gender-specific spaces.

• Journal of Computing Science and Engineering
• /
• 제11권4호
• /
• pp.121-129
• /
• 2017

Feature selection has been widely established as an efficient technique for microarray data analysis. Feature selection aims to search for the most important feature/gene subset of a given dataset according to its relevance to the current target. Unsupervised feature selection is considered to be challenging due to the lack of label information. In this paper, we propose a novel method for unsupervised feature selection, which incorporates embedded learning and $l_{2,1}-norm$ sparse regression into a framework to select genes in microarray data analysis. Local tangent space alignment is applied during embedded learning to preserve the local data structure. The $l_{2,1}-norm$ sparse regression acts as a constraint to aid in learning the gene weights correlatively, by which the proposed method optimizes for selecting the informative genes which better capture the interesting natural classes of samples. We provide an effective algorithm to solve the optimization problem in our method. Finally, to validate the efficacy of the proposed method, we evaluate the proposed method on real microarray gene expression datasets. The experimental results demonstrate that the proposed method obtains quite promising performance.

• 한국지능시스템학회논문지
• /
• 제11권9호
• /
• pp.817-821
• /
• 2001

본 논문은 분류 문제의 훈련 패턴으로부터 형성되는 커널 공간의 저밀도 표현을 가능하게 하는 커널 방법에 대한 새로운 학습방법론을 제안한다. 선형 판별 함수에 대한 기존의 학습법 중에서 이완 절차가 SVM(Support Vector Machine) 분류기와 동등하게 선형분리 가능 패턴분류 문제의 최대 마진 분리 초평면을 얻을 수 있다. 기존의 이완 절차는 지원 백터에 대한 필요 조건을 만족한다. 본 논문에서는 학습 중 지원 벡터를 확인하기 위한 충분 조건을 제시한다. 순차적 학습을 위하여 기존의 SVM을 확장하고 커널 판별함수를 정의한 후에 체계적인 학습방법을 제시한다. 실험 결과는 새 방법이 기존의 방법과 동등하거나 우수한 분류 성능을 갖고있음을 보여준다.

• 실천공학교육논문지
• /
• 제14권1호
• /
• pp.91-97
• /
• 2022

핵심적인 미래역량(비판적 사고, 의사소통, 협업, 창의성) 개발을 위한 대표적인 교육방법으로 문제중심 학습법(PBL, problem based learning)이 주목받으며 대학에서의 적용이 확산되고 있다. PBL 수업의 중요한 특징 두 가지는 '팀원들과의 협업'과 '상호작용에 기반한 참여형, 자기주도적 학습'이다. 최근 코로나19 팬데믹이 장기화 됨에 따라 비대면 원격수업이 대학교육에서 임시방편이 아닌 필수요소가 되었고, 시공간 제약에 의해 앞서 언급한 두 가지 특징을 충족시키기 어렵다는 한계점에 부딪혔다. 본 논문에서는 기존에 H대학에서 비대면으로 운영했던 PBL 강좌 사례에 대한 한계점을 분석하고, 메타버스 가상공간에서 이루어지는 개선된 PBL 수업 방식을 상세하게 설계하였다. 제안하는 메타버스 활용 PBL 수업에서는 팀에서 진행한 연구 내용들을 담은 자료(이미지, pdf, 동영상 파일 등)를 3차원 가상공간에 갤러리 형태로 자유롭게 꾸미고 전시할 수 있어서 팀원들의 적극적인 참여를 유도할 수 있다. 또한 갤러리를 팀원들의 프로젝트 협업 공간으로 활용할 수도 있고, 최종 프리젠테이션 장소로 활용할 수도 있다. 이 수업 방식은 가능한 빠른 시일 내에 동일 PBL 수업에 적용하여 효과성을 분석하고 개선점을 도출할 것이다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.66-69
• /
• 2003

This paper considers a reinforcement learning(RL) which deals with real environments. Most reinforcement learning studies have been made by simulations because real-environment learning requires large computational cost and much time. Furthermore, it is more difficult to acquire many rewards efficiently in real environments than in virtual ones. The most important requirement to make real-environment learning successful is the appropriate construction of the state space. In this paper, to begin with, I show the basic overview of the reinforcement learning under real environments. Next, 1 introduce a state-space construction method under real environmental which is State Partition Method. Finally I apply this method to a robot navigation problem and compare it with conventional methods.

• International Journal of Aeronautical and Space Sciences
• /
• 제11권2호
• /
• pp.87-97
• /
• 2010

A fault tolerant satellite attitude control scheme with a modified iterative learning law is proposed for dealing with actuator faults. The actuator fault is modeled to reflect the degradation of actuation effectiveness, and the solar array-induced disturbance is considered as an external disturbance. To estimate the magnitudes of the actuator fault and the external disturbance, a modified iterative learning law using only the information associated with the state error is applied. Stability analysis is performed to obtain the gain matrices of the modified iterative learning law using the Lyapunov theorem. The proposed fault tolerant control scheme is applied to the rest-to-rest maneuver of a large satellite system, and numerical simulations are performed to verify the performance of the proposed scheme.

• 교육시설
• /
• 제11권5호
• /
• pp.24-34
• /
• 2004

The purpose of this study is to analyze the planning characteristics of contemporary Japanese elementary schools. Fifteen schools, that have new planning trends or design ideas have been selected and analyzed. The planning characteristics of schools identified by plan analyses are summarized as follows. First, space programs of schools are diverse, especially in support facilities, gymnasiums and auditoriums. These spaces can be used by community members. So it is assumed that needs of communities are reflected in space programs of schools. Second, various types of unit learning spaces consisting of multipurpose spaces and classrooms embodied in case schools tell the differentiation in the structure of unit learning spaces. Third, grouped with gymnasiums or auditoriums, special instructional spaces constitute community zones where school facilities are open to public. Fourth, replacing the monotonous circulation systems by corridors, multipurpose hall-type space organization systems make surrounding spaces more activated and complex and the multipurpose hall itself becomes the central part of schools. Finally, outdoor spaces are designed to have convenient access and approach zones to school precincts are linked with city street.

• Structural Engineering and Mechanics
• /
• 제81권2호
• /
• pp.195-203
• /
• 2022

This paper presents the quantification and location damage detection of plane and space truss structures in a two-phase method to reduce the computations efforts significantly. In the first phase, a proposed damage indicator based on the residual force vector concept is used to get the suspected damaged members. In the second phase, using damage quantification as a variable, a teaching-learning based optimization algorithm (TLBO) is used to obtain the damage quantification value of the suspected members obtained in the first phase. TLBO is a relatively modern algorithm that has proved distinguished in solving optimization problems. For more verification of TLBO effeciency, the classical particle swarm optimization (PSO) is used in the second phase to make a comparison between TLBO and PSO algorithms. As it is clear, the first phase reduces the search space in the second phase, leading to considerable reduction in computations efforts. The method is applied on three examples, including plane and space trusses. Results have proved the capability of the proposed method to precisely detect the quantification and location of damage easily with low computational efforts, and the efficiency of TLBO in comparison to the classical PSO.

• 천문학회보
• /
• 제44권2호
• /
• pp.42.3-42.3
• /
• 2019

We translate Solar Dynamics Observatory/Atmospheric Imaging Assembly (AIA) ultraviolet (UV) multi-channel images into another UV single-channel image using a deep learning algorithm based on conditional generative adversarial networks (cGANs). The base input channel, which has the highest correlation coefficient (CC) between UV channels of AIA, is 193 Å. To complement this channel, we choose two channels, 1600 and 304 Å, which represent upper photosphere and chromosphere, respectively. Input channels for three models are single (193 Å), dual (193+1600 Å), and triple (193+1600+304 Å), respectively. Quantitative comparisons are made for test data sets. Main results from this study are as follows. First, the single model successfully produce other coronal channel images but less successful for chromospheric channel (304 Å) and much less successful for two photospheric channels (1600 and 1700 Å). Second, the dual model shows a noticeable improvement of the CC between the model outputs and Ground truths for 1700 Å. Third, the triple model can generate all other channel images with relatively high CCs larger than 0.89. Our results show a possibility that if three channels from photosphere, chromosphere, and corona are selected, other multi-channel images could be generated by deep learning. We expect that this investigation will be a complementary tool to choose a few UV channels for future solar small and/or deep space missions.

• 천문학회보
• /
• 제44권2호
• /
• pp.70.4-70.4
• /
• 2019

Image super-resolution (SR) is a technique that enhances the resolution of a low resolution image. In this study, we use three SR models (RCAN, ProSRGAN and Bicubic) for enhancing solar SDO/HMI magnetograms using deep learning. Each model generates a high resolution HMI image from a low resolution HMI image (4 by 4 binning). The pixel resolution of HMI is about 0.504 arcsec. Deep learning networks try to find the hidden equation between low resolution image and high resolution image from given input and the corresponding output image. In this study, we trained three models with HMI images in 2014 and test them with HMI images in 2015. We find that the RCAN model achieves higher quality results than the other two methods in view of both visual aspects and metrics: 31.40 peak signal-to-noise ratio(PSNR), Correlation Coefficient (0.96), Root mean square error (RMSE) is 0.004. This result is also much better than the conventional bi-cubic interpolation. We apply this model to a full-resolution SDO/HMI image and compare the generated image with the corresponding Hinode NFI magnetogram. As a result, we get a very high correlation (0.92) between the generated SR magnetogram and the Hinode one.