• Journal of KIISE:Databases
• /
• v.29 no.5
• /
• pp.358-366
• /
• 2002

Feature-based similarity retrieval become an important research issue in image database systems. The features of image data are useful to discrimination of images. In this paper, we propose the high speed k-Nearest Neighbor search algorithm based on Self-Organizing Maps. Self-Organizing Maps(SOM) provides a mapping from high dimensional feature vectors onto a two-dimensional space and generates a topological feature map. A topological feature map preserves the mutual relations (similarities) in feature spaces of input data, and clusters mutually similar feature vectors in a neighboring nodes. Therefore each node of the topological feature map holds a node vector and similar images that is closest to each node vector. We implemented a k-NN search for similar image classification as to (1) access to topological feature map, and (2) apply to pruning strategy of high speed search. We experiment on the performance of our algorithm using color feature vectors extracted from images. Promising results have been obtained in experiments.

• Archives of design research
• /
• v.17 no.1
• /
• pp.5-14
• /
• 2004

The study addressed a direction that environmental facilities along avenues will make a progress via urban environment as well as location marketing. The space is specified the campus avenue, which is located in Jongro-gu at Seoul. With the emergence of digital information era, both people' life style and behaviors have been changing in many different ways. As the first approach to the direction, the historical study of the avenue is examined by focusing on the change. All possible related status such as location marketing strategy and various spatial characteristics, environment of the avenue and its facilities are investigated and users' characteristics are analyzed. Through these processes, a new direction and role of design are proposed and are believed to improve the avenue' image and to rediscover its own identity and to make the avenue alive as it used to be. The new proposed direction showed how to approach to design as well as to system of environmental facilities along avenues and in addition to highlighting continuous and synthetic plan. Furthermore, It is expected that both the efforts to improve the avenue' image based on its own cultural characteristic and to foster the cultural-commercialized facilities will contribute to the local residents' life standard and its economic status.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.4
• /
• pp.723-729
• /
• 2001

We are able to work on the shared virtual space in Web-based Collaborative Design System using only Internet and Web browser. The users connect to the Solid Modeler Server through m and they create 3D shape and manipulate them variously. Then the users will share 3D objects and two problems can arise. The users must be able to pick the objects effectively which they want to manipulate. When one of the users manipulates a particular object, others should not disturb with the same object. In this paper, picking is implemented not only by computing intersection of mouse pointer with the objects of the virtual world, but also by using capabilities and attributes of scene graph node, by setting bounds intersection testing instead of geometric intersection testing, by limiting the scope of the pick testing, using Java 3D. These methods can reduce the computation of picking and can pick 3D objects effectively and easily using the system of hierarchy. To have effective concurrency, we used shared lock and exclusive lock as the action in work space.

• Journal of KIISE:Databases
• /
• v.31 no.6
• /
• pp.624-640
• /
• 2004

Recently, with the rapid development of location-based techniques, index structures to efficiently manage moving objects have been required. In this paper, we propose a new spatio-temporal index structure that supports a future position retrieval and minimizes a update cost. The proposed index structure combines an assistant index structure that directly accesses current positions of moving objects with KDB-tree that is a space partitioning access method. The internal node in our proposed index structure keeps time parameters in order to support the future position retrieval and to minimize a update cost. Moreover, we propose new update and split methods to maximize the space utilization and the search performance. We perform various experiments to show that our proposed index structure outperforms the existing index structure.

• The KIPS Transactions:PartD
• /
• v.15D no.2
• /
• pp.179-186
• /
• 2008

The converge of location-aware devices, GIS functionalities and the increasing accuracy and availability of positioning technologies pave the way to a range of new types of location-based services. The field of spatiotemporal data mining where relationships are defined by spatial and temporal aspect of data is encountering big challenges since the increased search space of knowledge. Therefore, we aim to propose algorithms for mining spatiotemporal patterns in mobile environment in this paper. Moving patterns are generated utilizing two algorithms called All_MOP and Max_MOP. The first one mines all frequent patterns and the other discovers only maximal frequent patterns. Our proposed approach is able to reduce consuming time through comparison with DFS_MINE algorithm. In addition, our approach is applicable to location-based services such as tourist service, traffic service, and so on.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.735-742
• /
• 2003

In the information retrieval system, document clustering technique is to provide user convenience and visual effects by rearranging documents according to the specific topics from the retrieved ones. In this paper, we clustered documents using K-Means algorithm and present the effect of index terms weighting scheme on the document clustering. To verify the experiment, we applied Latent Semantic Indexing approach to illustrate the clustering results and analyzed the clustering results in 2-dimensional space. Experimental results showed that in case of applying local weighting, global weighting and normalization factor, the density of clustering is higher than those of similar or same weighting schemes in 2-dimensional space. Especially, the logarithm of local and global weighting is noticeable.

• Korean Journal of Remote Sensing
• /
• v.20 no.6
• /
• pp.369-382
• /
• 2004

The purpose of this study is the investigation of applicability of LSMA(Linear Spectral Mixture Analysis) on the geological uses with different radiometric and spatial types of sensor images such as Terra ASTER and LANDSAT 7 ETM+. As for the actual application case, geologic mapping for mineral exploration using ASTER and ETM+ at the Mongolian plateau region was carried out. After the pre-processing such as the geometric corrections and calibration of radiance, 7 endmembers, as spectral classes for geologic rock types, related to spectral signature deviation for the given application was determined by the pre-surveyed geological mapping information and the correlation matrix analysis, and total 20 images of ASTER and ETM+ were used to LSMA processing. As the results, fraction maps showing individual mineral types in the study area are presented. It concluded that this approach based on LSMA using ETM+ and ASTER is regarded as one of the effective schemes for geologic remote sensing.

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.295-300
• /
• 2019

Modern society is the era of convergence, and storytelling requires the necessity of storytelling in which two types of data types, emotional stories and information, are fused. Particularly, in the case of VR contents, the user must directly participate in the content and select the information through the process of freely searching $360^{\circ}$ space, so that the user can interact with the content immediately. Therefore, there is a limit to access to the existing storytelling method, and it is considered that the implementation of 'convergent storytelling' that meets two areas of sensitivity and information is considered to be an urgent genre. In this paper, we focus on the spatial characteristics of VR contents, and then, as a way to effectively implement 'convergent storytelling' in VR contents, We propose a custom system by organizing the type into a circle structure. Based on this, it is expected that the technology will be developed into a research of a personalized system that meets two areas of emotion and information by utilizing the context recognition process for VR content and interaction in the fourth industrial revolution era.

• Journal of the Korean GEO-environmental Society
• /
• v.20 no.1
• /
• pp.35-42
• /
• 2019

Various development works inevitably increase cutting slopes due to land use, and many of trails managed by different authorities are being deteriorated by long-term weathering. Collapse of slopes causes unavoidable damage of property and loss of lives because of its uncertainty and difficulty in predicting its occurrence. In order to overcome the unavoidability, America, Japan, and several European nations analyze the kinetic energy and moving distance when rocks of upper slope move along the inclined plane, via field tests and computerized interpretation of the test results. Also, they are making efforts to develop measures with which the kinetic energy of the rocks moving along the slope is absorbed and fails to reach to specific structures. However, domestic researches just focus on fragmentary prediction of rockfall using existing programs, and there have been few approaches to identify interpretation methods appropriate for domestic cases or determination of parameters. In this context, we in this study defined rockfall types and affecting factors and analyzed effects of parameters using a general-purpose rockfall simulation program to understand principles of rockfall and to estimate effects of various parameters.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.117-124
• /
• 2021

Among growth disorders, 'Short Stature' can be improved through rapid diagnosis and treatment, and for that, it is important to detect early'Short Stature'. It is recommended to measure the height steadily for early detection of 'Short Stature' and checking the kid's growth process, but existing height measurement methods have problems such as time and space limitations, cost occurrence, and difficulty in keeping records. So in this paper, we proposed an 'Development of Kid Height Measurement Application based on Image using computer vision' method using smart phones, a medium that is highly accessible to people. In images taken through a smartphone camera, the kid's height is measured using algorithms from OpenCV, a computer vision library, and the measured heights were printed on the screen through 'a comparison graph with the standard height by gender and age' and 'list by date', made possible to check the kid's growth process. It is expected to measure height anytime, anywhere without time and space limitations and costs through this proposed method, and it is expected to help early detection of 'Short Stature' and other disorder through steady height measurement and confirmation of growth process.