• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.27-44
• /
• 2020

In order to solve the user's information overload problem, recommender systems infer users' preferences and suggest items that match them. The collaborative filtering (CF), the most successful recommendation algorithm, has been improving performance until recently and applied to various business domains. Visual information, such as book covers, could influence consumers' purchase decision making. However, CF-based recommender systems have rarely considered for visual information. In this study, we propose VizNCS, a CF-based deep learning model that uses visual information as additional information. VizNCS consists of two phases. In the first phase, we build convolutional neural networks (CNN) to extract visual features from image data. In the second phase, we supply the visual features to the NCF model that is known to easy to extend to other information among the deep learning-based recommendation systems. As the results of the performance comparison experiments, VizNCS showed higher performance than the vanilla NCF. We also conducted an additional experiment to see if the visual information affects differently depending on the product category. The result enables us to identify which categories were affected and which were not. We expect VizNCS to improve the recommender system performance and expand the recommender system's data source to visual information.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1121-1125
• /
• 2003

In this paper we deal with visual servoing that can control a robot arm with a camera using information of images only, without estimating 3D position and rotation of the robot arm. Here it is assumed that the robot arm is calibrated and the camera is uncalibrated. We use a pinhole camera model as the camera one. The essential notion can be show, that is, epipolar geometry, epipole, epipolar equation, and epipolar constrain. These play an important role in designing visual servoing. For easy understanding of the proposed method we first show a design in case of the calibrated camera. The design is constructed by 4 steps and the directional motion of the robot arm is fixed only to a constant direction. This means that an estimated epipole denotes the direction, to which the robot arm translates in 3D space, on the image plane.

• Journal of the Korean housing association
• /
• v.10 no.2
• /
• pp.247-257
• /
• 1999

This study is aimed to propose the evaluation model of forecasting visual quality of apartment buildings, which would be a useful tool to make the architectural concepts corresponding to user needs. This study was carried out through the four-step experiments as follows. The first step is to take the user's visual evaluation construct. To do this, the 22 adjective phrases were extracted, which were applicable to all apartment buildings. The second step is to analyze the user's visual preference, which is measured by the user's psychological quantity on the apartment buildings by S. D.(Semantic Differential) Method. The third step is to analyzethe five psychological-factors obtained from the Factor Analysis. The perceptual images on the 41 experimental subjects were checked up through evaluating and analyzing the factor scores of each subjects for each psychological-factor. The fourth step is to analyze, the similarity of various characters in a building, which is mirrored on the user's psychological quantity and how buildings are grouped by it.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.340-344
• /
• 2005

본 연구에서는 도로 빗물받이의 차집효율을 분석하기 위하여 측구 부분을 대상으로 수리모형을 제작하여 실험을 실시하고, 실측된 결과를 FHWA의 범용프로그램인 Visual Urban 모형의 해석결과와 비교하여 이 모형의 국내 적용성을 분석하였다. 실험에는 국내 표준규격인 40x50cm의 쇠살대 유입구(grater inlet)를 사용하였으며, 측구의 유량은 도로의 차선 및 빗물받이의 간격을 고려하여 $4\~13{\ell}/sec$를 선택하였다. 도로의 종경사는 $2,\;4,\;6\%$를 선택하고, 측구의 횡경사는 $4,\;6,\;8\%$를 선택하여, 총 36회의 실험을 실시하였다. Visual Urban 모형을 적용하여 모의한 결과와 실측값을 비교한 결과 종$\cdot$횡경사가 작은 경우에는 오차의 범위가 $6\%$정도였으며 종경사 $4\%$, 횡경사 $8\%$이상이면 비교적 일치하였다.

• KIEAE Journal
• /
• v.3 no.2
• /
• pp.59-66
• /
• 2003

To be the design method supporting aesthetic ability of human, CAAD system should essentially recognize architectural form in the same way of human. In this study, visual perception process of human was analyzed to search proper computational method performing similar step of perception of it. Through the analysis of visual perception, vision was separated to low-level vision and high-level vision. Edge detection and neural network were selected to model after low-level vision and high-level vision. The 24 images of building, tree and landscape were processed by edge detection and trained by neural network. And 24 new images were used to test trained network. The test shows that trained network gives right perception result toward each images with low error rate. This study is on the meaning of artificial intelligence in design process rather than on the design automation strategy through artificial intelligence.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.3
• /
• pp.112-121
• /
• 2002

This paper describes a new bike system for the postural balance rehabilitation training. Virtual environment and three dimensional graphic model is designed with CAD tools such as 3D Studio Max and World Up. For the real time bike simulation, the optimized WorldToolKit graphic library is embedded with the dynamic geometry generation method, multi-thread method, and portal generation method. In this experiment, 20 normal adults were tested to investigate the influencing factors of balancing posture. We evaluated the system by measuring the parameters such as path deviation, driving velocity, COP(center for pressure), and average weight shift. Also, we investigated the usefulness of visual feedback information by weight shift. The results showed that continuous visual feedback by weight shift was more effective than no visual feedback in the postural balance control It is concluded this system might be applied to clinical use as a new postural balance training system.

• Journal of Science of Art and Design
• /
• v.5
• /
• pp.5-34
• /
• 2003

This study aims at the observation of some analytical levels-especially those of syntactico-semantical- of the visual expressions in general. As far as the syntactical parts are concerned, there were two steps to be approached. One is to select the paradigms according to the Saussure-Hambidgean suggestions, the other to derive syntagmas from what is called the 'chaos-system', one of nonlinear dynamics. In result, paradigms could be acquired 5 sorts with its so many varieties, as visual templates(VT), supplemented by their reciprocals(R) and complements(CLE), and syntagmas five orbits from each constant c=0 to c=10. In additional, in connection with semantic parts, the study introduced a Gremasian model of discourses and narratives for the interpretation of signifiers. By this, we could cover the conjunctive relationships(+) and the disjunctive(-) of the whole structure of visual expression. Finally, we certified that the above could be fully approved in terms of recent worldly cognitive scientic psychological discoveries.

• Journal of the Korean housing association
• /
• v.12 no.2
• /
• pp.77-85
• /
• 2001

Along with the development of creative design ideas, how to effectively present design concepts is also an important consideration on housing plan process. This could consequently make it possible to automate presentations. In spite of such needs of presentations any significant efforts for the systematic design presentation have not been made yet. The research goals established in order to solve these problems are to develop structures of presentation and analyze the cases of it. This paper explains structures of housing plan presentations in two ways: the compositional elements of panel presentations and the relationships among the elements. The elements include a project title, a synopsis, design concepts, building layouts, floor plan1 and 2, longitudinal and latitudinal elevations, sections, projection and perspective views, and model photographs. Among various relationships among panel compositional elements this study uses relationships based on the Gestalt theory, the balance theory by Rudolf Arnheim and the optical array theory by Gibson. The relationships investigated on the basis of the visual perception theories include the relationships between compositional elements and background space, visual weight balance, horizontal and vertical balances, grouping, and visual layout patterns.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.629-632
• /
• 1999

In this paper, color coordinate system transformation based visual servo controller has been considered. Mobile robot always has a position error and an orientation error resulted from wheel slipping etc.. Even more, the errors have accumulative properties. So feedback from environments is important. In this paper, by using color model faster land mark extraction can be achieved. And the global position and the orientation of mobile robot can be known by only two land marks positions in image coordinate system. Finally, the adoption of visual information in path tracking problem makes visual servo control.

• Journal of Korean Society of Rural Planning
• /
• v.11 no.2 s.27
• /
• pp.59-69
• /
• 2005

Because of increasing numbers of cars many highways are being constructed lively, and the noise of passing cars has influenced surrounding areas. In consideration of this, some alternatives and researches for soundproof facilities are proceeding, but aesthetic approach hasn't been considered. Therefore, this research is focused on soundproof effects for each types, effectual simulation methods, visual assessment and estimation between the landscape before simulation and the landscape after. Soundproof facilities are divided largely by the soundproof barrier, the soundproof mounding, the soundproof grove. The soundproof grove has three main function. First, leaves and branches absorbs sound vibrations. Second, leaves absorbs sound, and branches obstruct sounds. Third, by means of sounds of shaking leaves, forest can offset noises. This research was proceeded by means of classification of soundproof grove types and investigation of visual simulation methods. We made visual simulation for each types, and estimated the landscape for each types.