• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.270-279
• /
• 1997

The conversion of printed maps into computerized databases is an enormous task. Thus the automation of the conversion process is essential. Efficient computer representation of printed maps and line drawings depends on codes assigned to characters, symbols, and vector representation of the graphics. In many cases, maps are constructed in a number of layers, where each layer is printed in a distinct color, and it represents a subset of the map information. In order to properly represent the character layer from color map images, an interactive clustering and character extraction technique is proposed. Character is usually separated from graphics by extracting and classifying connected components in the image. But this procedure fails, when characters touch or overlap lines-something that occurs often in land register maps. By vectorizing line segments, the touched characters and numbers are extracted. The algorithm proposed in this paper is intended to contribute towards the solution of the color image clustering and touched character problem.

• Journal of KIISE
• /
• v.44 no.10
• /
• pp.1026-1033
• /
• 2017

In this paper a Bayesian modeling and duration-based prediction method is proposed for health clinic time series data using the Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM). HDP-HMM is a Bayesian extension of HMM which can find the optimal number of health states, a number which is highly uncertain and even difficult to estimate under the context of health dynamics. Test results of HDP-HMM using simulated data and real health clinic data have shown interesting modeling behaviors and promising prediction performance over the span of up to five years. The future of health change is uncertain and its prediction is inherently difficult, but experimental results on health clinic data suggests that practical long-term prediction is possible and can be made useful if we present multiple hypotheses given dynamic contexts as defined by HMM states.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.10
• /
• pp.2201-2206
• /
• 2010

The shortage of fossil fuel drives researchers to find a new way to increases energy efficiency. In this paper, we propose a method to control the direction and speed of an air conditioner using a thermal image and fuzzy controlling method, which results in the increase of energy efficiency. The thermal image is first converted into a color temperature image which represents the temperature range from $24.0^{\circ}C$ to $27.0^{\circ}C$. The temperature image is divided into 5 columns and the distribution of them is used to analyze room temperature and control an air conditioner. The proposed method was applied to 300 by 400 thermal images. When the performance of the proposed method was compared to existing systems in energy efficiency, the proposed method was better than existing methods, which is clear from experimental results.

• KIISE Transactions on Computing Practices
• /
• v.23 no.2
• /
• pp.104-109
• /
• 2017

We propose a new machine learning algorithm which analyzes daily activity patterns of users from multi-modal wearable sensor data. The proposed model learns and extracts activity patterns using input from wearable devices in real-time. Inspired by cue integration of human's property, we constructed gated multi-modal neural networks which integrate wearable sensor input data selectively by using gate modules. For the experiments, sensory data were collected by using multiple wearable devices in restaurant situations. As an experimental result, we first show that the proposed model performs well in terms of prediction accuracy. Then, the possibility to construct a knowledge schema automatically by analyzing the activation patterns in the middle layer of our proposed model is explained.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.88-93
• /
• 2009

e-Portfolio in e-Learning environment is defined as the results which either teachers or learners systematically manage global contents related to their teaching and learning, respectively. When the e-Portfolio is applied to their work including teaching and learning, it is very useful for both teachers and learners to prepare their teaching plan, and to get the opportunity of their reflection by checking out their learning output, respectively. To generate e-Portfolios, there are two ways; one for collecting it directly from teachers and learners and another for collecting it automatically as a result of learning activities through e-learning system. In this paper, for efficient management of e-Portfolio, the data is layered, classified, restructured, and provided for users' purposes and various situations. Users can construct their own e-Portfolios by adding their own logic with their purposes in different situations.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.6
• /
• pp.625-630
• /
• 2010

With regard to the examples of establishing various sorts of information security, it can be seen that there are gradual, developmental procedures including Firewall and VPN (Virtual Private Network), IDS (Intrusion Detection System), or ESM(Enterprise Security Management). Each of the security solutions and equipments analyzes both defense and attack for information security with the criteria of classifying the problems of security policies by TCP/IP layers or resulted from attack patterns, attack types, or invasion through specialized security technology. The direction of this study is to examine latency time vulnerable to invasion which occurs when L2-stratum or lower grade equipments or policies are applied to the existing network through TCP/IP layer's L3-stratum or higher grade security policies or equipments and analyze security holes which may generate due to the IP preoccupation in the process of establishing policies to limit particular IP area regarding the policies for security equipments to figure out technological problems lying in it.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.3
• /
• pp.13-23
• /
• 2001

In this paper, we design and implement a virtual environment which forms the basis of constructing a virtual world in a systematic fashion. Though virtual environments have been developed in several systems using the virtual reality, they are designed without a systematic method of constructing. In our framework, a virtual environment is structured in six layers according to their functions and ranges based on a classification of environmental factors of which the real world is composed. These layers compose a universal environment in our virtual world by operating independently and exchanging information with one another periodically. The designed environment shows that it Can provide diverse real life situations and is easily extensible to enhance its functionalities. We present effective design schemes for several important environmental factors. We demonstrate viability of our framework through implementing a plausible virtual world based on the proposed schemes.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.4 s.34
• /
• pp.59-65
• /
• 2005

It is very important to detect land cover/land use change from the past and to use it for future urban plan. This paper investigated the application of Landsat satellite imagery for detecting urban growth and assessing its impact on surface temperature in the region. Land cover/land use change detection was carried out by using 30m resolution Landsat satellite images and hierarchial approach was introduced to detect more detail change on the changing area through high resolution aerial photos. Also, surface temperature according to land cover/land use was calculated from Landsat TM thermal infrared data and compared with real temperature to analyze the relationship between urban expansion and surface temperature. As a result, the urban expansion has raised surface radiant temperature in the urbanized area. The method using remote sensing data based on GIS was found to be effective in monitoring and analysing urban growth and in evaluating urbanization impact on surface temperature.

• Journal of Digital Convergence
• /
• v.13 no.4
• /
• pp.51-59
• /
• 2015

In this study, we derived key factors required for the activation of the domestic e-book market and evaluated its importance. Specifically, we derived key evaluation items of C-P-N-D ecosystem perspective through literature review. In addition, we analyzed the implications by evaluating the importance depending on AHP after derived items were modified and classified together with the publisher working group. As the results of analysis, experts considered price(0.785), quality(0.149) and service(0.066) as the important items among three items derived as the primary upper class. A total of 23 factors were derived as the secondary lower class. The importance depending on C-P-N-D areas is as follows: contents(0.43), platform(0.35), device(0.11) and network(0.05). Among the entire sub-factors, three items such as 'distribution of profits with platform', 'profitability of product costs of contents' and 'appropriate rental price of contents and streaming service' showed significantly higher importance than that of other 20 items.

• Journal of Korean Society of Transportation
• /
• v.21 no.6
• /
• pp.77-88
• /
• 2003

This paper proposes a solution algorithm for solving a multi-class analytical DTA model. In the DTA model, three traveler classes are classified according to different assumptions of traveler's route choice behavior: including fixed route, Stochastic Dynamic User Optimum(SDUO), and Dynamic User Optimum(DUO). To solve this DTA model, variables of link flow and exit flow are represented solely by inflow. The resulting Linear Program(LP) subproblem in the inner iteration is solved as a typical time-dependent shortest route problem over a physical network. Accordingly, the required time-space network expansion in solving DTA models is no longer needed.