• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.363-375
• /
• 2000

In this paper we propose a content-based image retrieval method that can search large image databases efficiently by color, texture, and shape content. Quantized RGB histograms and the dominant triple (hue, saturation, and value), which are extracted from quantized HSV joint histogram in the local image region, are used for representing global/local color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Relevance feedback approach, which has coupled proposed features, is used for obtaining better retrieval accuracy. Simulation results illustrate the above method provides 77.5 percent precision rate without relevance feedback and increased precision rate using relevance feedback for overall queries. We also present a new indexing method that supports fast retrieval in large image databases. Tree structures constructed by k-means algorithm, along with the idea of triangle inequality, eliminate candidate images for similarity calculation between query image and each database image. We find that the proposed method reduces calculation up to average 92.9 percent of the images from direct comparison.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.134-140
• /
• 2021

Big data has recently been used in various industries such as tourism, medical care, distribution, and marketing. And it is evolving to the stage of collecting real-time information or analyzing correlations and predicting the future. In the tourism industry, big data can be used to identify the size and shape of the tourism market, and by building and utilizing a large-capacity database, it is possible to establish an efficient marketing strategy and provide customized tourism services for tourists. This paper has begun with anticipation of the effects that would occur when big data is actively used in the tourism field. Because the method of use must have applicability and practicality, the spatial scope will be limited to Seosan, Chungcheongnam-do, and research will be conducted. In this paper, to improve the quality of tourism courses by collecting and analyzing the number of mention data and sentiment index data on social media, which reflect the tourist's interest, preference and satisfaction. Therefore, it is used as basic data necessary for the development of new local tourism courses in the future. In addition, the development of tourism courses will be able to promote tourism growth and also revitalizing the local economy.

• Spatial Information Research
• /
• v.9 no.1
• /
• pp.107-124
• /
• 2001

The purpose of this research is to develop system and to establish methodology for managing spatial Database in Land Management Information System(LMIS). Spatial Database which is used by a various public department such as parcel survey and registry, land use planning and Land value appraisal in local government, is composed of parcel map, topographic map and zoning map. Spatial data has been constructed and managed by various department and then hard to maintain accuracy and coinsistency. So, it is important to establish the basic data management concept that source data(ex : parcel map, topographic map, zoning map, etc.) should be managed by responsible department. at the same time, application data for bussiness (ex : individual parcel price map) must be recomposed from base map by it's own objects. This is, Spatial data management system (SDMS) should be designed, developed according to this concept for managing consistency among data, reducing construction and management cost of database. Our SDMS was developed based on Open LMIS middleware architecture using OpenGIS CORBA specification for standard interface, RUP(Rational Unified Process) for development methodology, UML(Unified Modeling Language) for system design and VisiBroker, C++, CAD system for system implementation.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.425-438
• /
• 1999

In recent days network computing technologies have bee developed rapidly and the extended use of Internet applications for enterprises such as internet/extarnet in and between enterprises has been increased enormously. Therefore the business in the future will be executed by virtual enterprise. Virtual enterprises which is based on information sharing between enterprises are composed of work processes related to information exchange between virtual enterprises, the team members who are representatives of the organizations that are participated in the actual business of virtual enterprises, and members who are representatives of the organizations that are participated in the actual business of virtual enterprises, and environment that are provided by supporting CALS(continuous Acquisition and Life cycle Support or commerce At light Speed). Supporting system of IDE(Integrated Data Environment)for CALS implementation that is provided as an environment of virtual enterprises has to ensure the autonomies of local data and to provide the accessibility of heterogeneous database of enterprises on network transparently for giving user a single global view of data. This paper introduce the design and implementation of the database broker system that can be accessed data transparently by the suers of participated enterprises in the integrated data environment supporting virtual enterprises. The system uses java/CORBA technology in Web environment and Object Query language (OQL) to process the queries of relational database system, object-oriented database system, and file information.

• Journal of Korea Water Resources Association
• /
• v.46 no.1
• /
• pp.47-58
• /
• 2013

Recently, an increase in the occurrence of sudden local flooding of great volume and short duration due to global climate changes has occasioned the significant danger and loss of life and property in Korea as well as most parts of the world. Such a local flood that usually occurs as the result of intense rainfall over small regions rises quite quickly with little or no advance warning time to prevent flood damage. To prevent the local flood damage, it is important to quickly predict the flood severity for flood events exceeding a threshold discharge that may cause the flood damage for inland areas. The aim of this study is to develop the NFI (New Flood Index) measuring the severity of floods in small ungauged catchments for use in local flood predictions by the regression analysis between the NFI and rainfall patterns. Flood runoff hydrographs are generated from a rainfall-runoff model using the annual maximum rainfall series of long-term observations for the two study catchments. The flood events above a threshold assumed as the 2-year return period discharge are targeted to estimate the NFI obtained by the geometric mean of the three relative severity factors, such as the flood magnitude ratio, the rising curve gradient, and the flooding duration time. The regression results show that the 3-hour maximum rainfall depths have the highest relationships with the NFI. It is expected that the best-fit regression equation between the NFI and rainfall characteristics can provide the basic database of the preliminary information for predicting the local flood severity in small ungauged catchments.

• Journal of Environmental Health Sciences
• /
• v.49 no.6
• /
• pp.312-323
• /
• 2023

Background: Environmental concentrations of substances can be estimated by K-CHESAR based on main, industrial, and use categories (MC/IC/UC) and ECETOC TRA based on environmental or specific environmental categories (ERC or spERC). Objectives: Three different systems for estimating environmental concentrations were compared to figure out their order with possible reasons along with relationship of regional predicted environmental concentrations (PEC_regional) and final PEC_local for various uses of a substance. Methods: Typical uses of the case substance and their corresponding ERCs were selected from the webpage of the European Chemical Agency. Proper MC/IC/UC and spERC were assigned to each ERC. Emission fractions were compared for each assessment code from the available database. PECs were calculated by three estimating systems: K-CHESAR using MC/IC/UC, ECETOC TRA using ERC, and ECETOC TRA using spERC with their default values for input parameters. Percentage of PEC_regional to PEC_local were manually calculated for each use. Results: Emission factors decreased in the order of ERC > MC/IC/UC > spERC. Values of the final PEC_local derived as sum of PEC_regional and Clocal decreased in the order of calculations using ECETOC TRA-ERC>KCHESAR with MC/IC/UC>ECETOC TRA-spERC for all environmental media. Percentages of PEC_{regional,water} to PEC_local,water ranged from 0 to 10.3% in industrial uses calculated with MC/IC/UC and ERC but 96.3 to 100% in wide dispersive uses of ERC and spERC where values of C_local,water are estimated to be very low. Conclusions: ECETOC TRA generated the most refined PNEC values with spERC and the least with ERC, while K-CHESAR with MC/IC/UC generated values between the two results. The ratio of PEC_regional to PEC_local can be a good measure for performing suitable estimation of PNECs according to use.

• Clinical and Experimental Pediatrics
• /
• v.52 no.11
• /
• pp.1185-1193
• /
• 2009

An act of children's welfare was made in 1961 for the first time in Korea but it had been nothing but the name in view of practical impact to prevention of child abuse. Real undertakings of Child Abuse Prevention were commenced overtly since 2000 in Korea, when the law for children's welfare was revised to put protective settings for the victims and to establish criterion for children's safety. The history of Child Abuse Prevention is very short in Korea but the reporting cases increased very fast from 4,133 cases in 2001 up to 9,570 cases in 2008 with the enthusiastic activities from people of the associated organizations along with the national supports. But the portion reported by the mandated reporters such as teachers or doctors is still low compared to those of the developed countries. The National Child Protection Agency (NCPA) was founded in 2001 by the Ministry of Health and Welfare to prevent child abuse and to aid recovery of abused and neglected children including their families, through the cooperation of related organizations. NCPA refers reported cases of child abuse to appropriate local centers, operates a computer database system for case management, publicizes national reports of child abuse on a yearly basis and technically supports the Local Child Protection Agency (LCPA) by developing scales for assessment of child abuse and neglect and distributing programs for the education of mandatory reporters. LCPAs operate 24-hour telephone hotline, investigate and visit homes and provide in home services networking with local resources, and operate multidisciplinary teams for screening child abuse victims and supervising case management through multimodal systems. We summarized the present state of child abuse in Korea and reviewed the operating systems for child protection in this country. Through this article, we hope that medical peoples are to be informed on the seriousness of child abuse and to be able to devote themselves for the prevention of child abuse.

• Journal of Intelligence and Information Systems
• /
• v.14 no.2
• /
• pp.193-206
• /
• 2008

Medical diagnosis can be considered a classification task which classifies disease types from patient's condition data represented by a set of pre-defined attributes. This study proposes a hybrid genetic algorithm based classification method to develop classifiers for multidimensional pattern classification problems related with medical decision making. The classification problem can be solved by identifying separation boundaries which distinguish the various classes in the data pattern. The proposed method fits a finite number of regional agents to the data pattern by combining genetic algorithms and local adaptive operations. The local adaptive operations of an agent include expansion, avoidance and relocation, one of which is performed according to the agent's fitness value. The classifier system has been tested with well-known medical data sets from the UCI machine learning database, showing superior performance to other methods such as the nearest neighbor, decision tree, and neural networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.1
• /
• pp.25-44
• /
• 2010

With the increasing popularity of mobile devices, it has become necessary to protect private information and content in these devices. Face recognition has been favored over conventional passwords or security keys, because it can be easily implemented using a built-in camera, while providing user convenience. However, because mobile devices can be used both indoors and outdoors, there can be many illumination changes, which can reduce the accuracy of face recognition. Therefore, we propose a new face recognition method on a mobile device robust to illumination variations. This research makes the following four original contributions. First, we compared the performance of face recognition with illumination variations on mobile devices for several illumination normalization procedures suitable for mobile devices with low processing power. These include the Retinex filter, histogram equalization and histogram stretching. Second, we compared the performance for global and local methods of face recognition such as PCA (Principal Component Analysis), LNMF (Local Non-negative Matrix Factorization) and LBP (Local Binary Pattern) using an integer-based kernel suitable for mobile devices having low processing power. Third, the characteristics of each method according to the illumination va iations are analyzed. Fourth, we use two matching scores for several methods of illumination normalization, Retinex and histogram stretching, which show the best and $2^{nd}$ best performances, respectively. These are used as the inputs of an SVM (Support Vector Machine) classifier, which can increase the accuracy of face recognition. Experimental results with two databases (data collected by a mobile device and the AR database) showed that the accuracy of face recognition achieved by the proposed method was superior to that of other methods.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.816-824
• /
• 2009

In the face space, face images due to illumination and pose variations have a nonlinear distribution. Active Appearance Models (AAM) based on the linear model have limits to the nonlinear distribution of face images. In this paper, we assume that a few clusters of face images are given; we build local AAMs according to the clusters of face images, and then select a proper AAM model during the fitting phase. To solve the problem of updating fitting parameters among the models due to the model changing, we propose to build in advance relationships among the clusters in the parameter space from the training images. In addition, we suggest a gradual model changing to reduce improper model selections due to serious fitting failures. In our experiment, we apply the proposed model to Yale Face Database B and compare it with the previous method. The proposed method demonstrated successful fitting results with strongly illuminated face images of deep shadows.