• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1302-1309
• /
• 2008

Traditional clustering methods, like k-means or fuzzy clustering, are prototype-based methods which are applicable only to convex clusters. On the other hand, spectral clustering tries to find clusters only using local similarity information. Its ability to handle concave clusters has gained the popularity recent years together with support vector machine (SVM) which is a kernel-based classification method. However, as is in SVM, the kernel width plays an important role and has a great impact on the result. Several methods are proposed to decide it automatically, it is still determined based on heuristics. In this paper, we proposed an adaptive method deciding the kernel width based on distance histogram. The proposed method is motivated by the fact that the affinity matrix should be formed into a block diagonal matrix to generate the best result. We use the tradition Euclidean distance together with the random walk distance, which make it possible to form a more apparent block diagonal affinity matrix. Experimental results show that the proposed method generates more clear block structured affinity matrix than the existing one does.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.11
• /
• pp.1429-1436
• /
• 2013

This study presents an approach for designing a vehicle rollover prevention controller using differential game theory and multi-level programming. The rollover prevention problem can be modeled as a non-cooperative zero-sum two-player differential game. A controller as an equilibrium solution of the differential game guarantees the worst-case performance against every possible steering input. To obtain an equilibrium solution to the differential game with a small amount of computational effort, a multi-level programming approach with a relaxation procedure is used. To cope with the loss of maneuverability caused by the active suspension, an electronic stability program (ESP) is adopted. Through simulations, the proposed method is shown to be effective in obtaining an equilibrium solution of the differential game.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.6
• /
• pp.63-74
• /
• 2005

In Electronic Commerce, the latest most of the personalized recommender systems have applied to the collaborative filtering technique. This method calculates the weight of similarity among users who have a similar preference degree in order to predict and recommend the item which hits to propensity of users. In this case, we commonly use Pearson Correlation Coefficient. However, this method is feasible to calculate a correlation if only there are the items that two users evaluated a preference degree in common. Accordingly, the accuracy of prediction falls. The weight of similarity can affect not only the case which predicts the item which hits to propensity of users, but also the performance of the personalized recommender system. In this study, we verify the improvement of the prediction accuracy through an experiment after observing the rule of the weight of similarity applying Vector similarity, Entropy, Inverse user frequency, and Default voting of Information Retrieval field. The result shows that the method combining the weight of similarity using the Entropy with Default voting got the most efficient performance.

• Journal of the HCI Society of Korea
• /
• v.7 no.2
• /
• pp.11-16
• /
• 2012

R&D Strategic Planning plays a crucial role in determining success or failure of R&D. However, current automatic services for supporting the purpose merely provide fragmentary quantitative/qualitative analytics, and force domain experts to carry out further manual analysis by themselves. Thus, this study aims at automatically supporting R&D strategic planning with efficiency and effectiveness. To achieve the goal, we design major services in the viewpoint of the relationship between technology and R&D actor, which are essential elements in R&D. 'Trends and Predictions', 'Technology Levels', 'Relationship Paths', 'Roadmaps', and 'Competitors and Collaborators' services were designed and implemented on about 15 millions papers and patents. Future works will include the support of higher level in the hierarchy of strategic intelligence.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.11
• /
• pp.2055-2061
• /
• 2006

The detection of geometric primitives from a digital image is one of the basic tasks in computer vision area and the Hough transform is a well-known method for detecting analytical shape represented by a number of free parameters. However the basic property of the Hough transform, the one-to-many mapping from an image space to a Hough space, causes the innate problem, the sensitivity to noise. In this paper, we proposed Edge Strength Hough Transform which uses edge strength to reduce the sensitivity to noise and proved the insensitivity using the ratio of peaks in a Mough space. We also experimented the proposed method on lines and got small number of peaks in a Hough space compared to traditional Hough transform, which supports the noise insensitivity of the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.575-581
• /
• 2007

Though the Hough transform is a well-known method for detecting analytical shape represented by a number of free parameters, the basic property of the Hough transform, the one-to-many mapping from an image space to a Hough space, causes the innate problem, the sensitivity to noise. To remedy this problem, Edge Strength Hough Transform (ESHT) was proposed and proved to reduce the noise sensitivity. However the performance of ESHT depends on the size of a Hough space and image and some other parameters which should be decided experimentally. In this paper, we derived formulae to decide 2 parameter values; decreasing parameter and broadening parameter, which play an important role in ESHT. Using the derived formulae, 2 parameter values can be decided only with the pre-determined values, the size of a Hough space and an image, which make it possible to decide them automatically. The experiments with different parameter values also support the result.

• Journal of agriculture & life science
• /
• v.43 no.2
• /
• pp.55-63
• /
• 2009

This paper analyzes the effects of Korea-US FTA on the pork market in Korea. Without distinction of chilled and frozen pork, previous studies that investigate the impacts of FTA posit single category of pork. Moreover, many prior studies assume the domestic pork and imported one are homogenous. This study fills this gap. The simulated influences of Korea-US FTA on the price of domesitc pork are -2.69 to -15.96 percents. The FTA is simulated to result in the fall of domestic production by 1.35 to 5.6 percents.

• Journal of the Korean Society for information Management
• /
• v.30 no.1
• /
• pp.179-191
• /
• 2013

Since information scientists have begun trying to quantify significant research trends in scientific publications, '-metrics' research such as 'bibliometrics', 'scientometrics', 'informetrics', 'webometrics', and 'citation analysis' have been identified as crucial areas of information science. To illustrate the dynamic research activities in these areas, this study investigated the major contributors of '-metrics' research for the last decade at three levels: nations, institutions, and documents. '-metrics' literature of this study was obtained from the Science Citation Index for the years 2001-2011. In this analysis, we used Pathfinder network, PNNC algorithm, PageRank and several indicators based on h-index. In terms of international collaborations, USA and England were identified as major countries. At the institutional level, Katholieke University, Leuven and the University of Amsterdam in Europe and Indiana University and the Office of Naval Research in the USA have led co-research projects in informetrics areas. At the document level, Hirsch's h-index paper and Ingwersen's web impact factor paper were identified as the most influential work by two methods: PageRank and single paper h-index.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.193-204
• /
• 2015

An array DBMS has been expected widely from scientists because it is convenient to store and analyze the data of array type. In this paper, we describe how to handle satellite remote-sensing images in the array DBMS. However, previous works in their visualization have two problems as follows. First, the images are visualized as a state of distorted by the curvature of the earth. Second, it is difficult to apply the results of visualization by pre-written queries to other analyses. Therefore, this paper proposes a three dimensional visualization method of satellite remote-sensing images, not traditional 2D visualization. Our research contents are as follows. First, we describe how to store, process, and analyze the satellite remote-sensing images in the array DBMS. Second, we propose a three-dimensional visualization method for their processed outputs. Lastly, our contributions can be summarized that we propose a method of handling satellite remote-sensing images in the array DBMS and their 3D visualization techniques. It is also expected that their use be available widely in many industrial areas.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.33 no.1
• /
• pp.5-24
• /
• 2022

As a new academic publication model is attempted to improve the transparency, efficiency, and speed of scientific knowledge production and distribution, the open peer review platform for verification and openness of peer review history is also activated. Publons is a global platform for tracking, validating, disclosing, and recognizing the peer-reviewed histories of more than 3 million researchers worldwide. This study analyzed the review activities of 579 researchers from domestic universities who are actively reviewing international journals through Publons. As a result of the analysis, first, researchers from domestic universities who actively review international academic journals were found to be in the fields of medicine and electrical and electronics, and in most fields, assistant professors or higher with high WOS indexed research papers are participating. Second, there was a long-tail phenomenon in which a small number of reviewers with extremely high number of review papers existed in all academic fields, and there was no significant difference in the number of review papers and review report length depending on the nationality, academic status, and age of the reviewers. Lastly, although there was a weak correlation between the amount of papers reviewed by reviewers and the number of published papers, it was found that researchers with an extremely large number of reviews do not necessarily produce as many research papers.