• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.223-230
• /
• 2001

Since self-organizing map (SOM) preserves the topology of ordering in input spaces and trains itself by unsupervised algorithm, it is Llsed in many areas. However, SOM has a shortcoming: structure cannot be easily detcrmined without many trials-and-errors. Structure-adaptive self-orgnizing map (SASOM) which can adapt its structure as well as its weights overcome the shortcoming of self-organizing map: SASOM makes use of structure adaptation capability to place the nodes of prototype vectors into the pattern space accurately so as to make the decision boundmies as close to the class boundaries as possible. In this scheme, the initialization of weights of newly adapted nodes is important. This paper proposes a method which optimizes SASOM with genetic algorithm (GA) to determines the weight vector of newly split node. The leanling algorithm is a hybrid of unsupervised learning method and supervised learning method using LVQ algorithm. This proposed method not only shows higher performance than SASOM in terms of recognition rate and variation, but also preserves the topological order of input patterns well. Experiments with 2D pattern space data and handwritten digit database show that the proposed method is promising.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.970-972
• /
• 2003

Due to rapid increase in the demand of Natural Rubber (NR) few years ago, NR price sore very higher. The rubber plantation in Thailand expanded very fast to non traditional areas with the result Thai become the biggest NR exporting country in the world. However, the average yield is still lower compared to experimental yield of RRIT (Rubber Research Institute of Thailand) or just 60 % (RRIT, 1998). This is due to many of new rubber planting areas, which are not suitable. The Thai Ministry of Agriculture and Cooperatives thus has set 'The complete cycle development strategies for natural rubber' in the medium-term measures by reducing the rubber planting areas by 300,000 rai (1 rai = 0.16ha) through replanting with oil palm. The aim of this study is to find out land having lowest potential for rubber production (R3) but highest for oil palm production (P1). Find areas which are unsuitable for rubber and can be replaced by oil palm in order to get a better agricultural production. The study was applied upon Krabi province, Thailand. Crops requirement, degree of limitation to crops growth, climatic data, crops yield, soil map, topographic map etc., were used to evaluate land potential for both rubber and oil palm production according to FAO framework (Sys, 1992). An Agro-ecological suitability map for rubber and oil palm were produced. This was done by mean of GIS. The database was generated and guide map for the decision makers in view of suitable crop substitution was prepared.

• Genomics & Informatics
• /
• v.17 no.4
• /
• pp.39.1-39.20
• /
• 2019

Analyzing patterns in data points embedded in linear and non-linear feature spaces is considered as one of the common research problems among different research areas, for example: data mining, machine learning, pattern recognition, and multivariate analysis. In this paper, data points are heterogeneous sets of biosequences (composite data points). A composite data point is a set of ordinary data points (e.g., set of feature vectors). We theoretically extend the derivation of the largest generalized eigenvalue-based distance metric D_ij(γ₁) in any linear and non-linear feature spaces. We prove that D_ij(γ₁) is a metric under any linear and non-linear feature transformation function. We show the sufficiency and efficiency of using the decision rule $\bar{{\delta}}_{{\Xi}i}$(i.e., mean of D_ij(γ₁)) in classification of heterogeneous sets of biosequences compared with the decision rules min_𝚵iand median_𝚵i. We analyze the impact of linear and non-linear transformation functions on classifying/clustering collections of heterogeneous sets of biosequences. The impact of the length of a sequence in a heterogeneous sequence-set generated by simulation on the classification and clustering results in linear and non-linear feature spaces is empirically shown in this paper. We propose a new concept: the limiting dispersion map of the existing clusters in heterogeneous sets of biosequences embedded in linear and nonlinear feature spaces, which is based on the limiting distribution of nucleotide compositions estimated from real data sets. Finally, the empirical conclusions and the scientific evidences are deduced from the experiments to support the theoretical side stated in this paper.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.2
• /
• pp.19-32
• /
• 2015

In Korea, significant riparian areas have been developed due to river maintenance projects. Introduction of new riparian facilities can negatively affect wildlife in the riparian areas. This study focuses on selecting core conservation areas for Eurasian Otter(Lutra lutra) to support decision making process for development of riparian areas. For the study, first of all, field data of study site were collected by field surveys. Secondly, stream naturalness was assessed to understand physical environments of the study sites. Thirdly, habitat suitability was assessed using occurrence data of Eurasian Otter and environmental data. Lastly, core areas for conservation was selected by comparing and synthesizing stream naturalness map and habitat suitability map. The selected core areas showed several characteristics. The number of artificial facilities is low in the core areas. Rocks which are preferred by Eurasian Otter to eat and excrete are plentiful in the core areas. Also, the ratio of adjacent farmland is high. Based on the analyses, it is expected that this study can contribute to decision making process for environmental spatial plans to better conserve habitats of Eurasian Otter.

• Journal of Intelligence and Information Systems
• /
• v.14 no.4
• /
• pp.89-101
• /
• 2008

The most used tool for quality control is control chart in manufacturing industry. But it has limitations at current situation where most of manufacturing facilities are automated and several manufacturing processes have interdependent relationship such as CCM assembly line. To Solve problems, we propose quality management system based on data mining that are consisted of monitoring system where it monitors flows of processes at single window and feature extraction system where it predicts the yield of final product and identifies which processes have impact on the quality of final product. The quality management system uses decision tree, neural network, self-organizing map for data mining. We hope that the proposed system can help manufacturing process to produce stable quality of products and provides engineers useful information such as the predicted yield for current status, identification of causal processes for lots of abnormality.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.3
• /
• pp.531-546
• /
• 2015

A non-interactive key exchange protocol provides an efficiency of overall system by eliminating additional communication. However, traditional non-interactive key exchange protocols without updating a private key fail to provide forward secrecy, since there is no usage of ephemeral key for randomness of session key. In 2012, Sang et al. proposed a certificateless non-interactive key exchange(CL-NIKE) protocol, but they do not prove the security of the protocol and it does not provide forward secrecy. In this paper, we propose a new CL-NIKE protocol and it's security model. Then we prove the proposed protocol is secure under the security model based on DBDH(Decision Bilinear Diffie-Hellman) assumption. Moreover, we propose a CL-NIKE protocol with forward secrecy which updates user's private key by using multilinear map and prove it's security.

• Spatial Information Research
• /
• v.12 no.3
• /
• pp.285-298
• /
• 2004

Transportation digital map has built based on NGIS (national geography institute's 1 :5000 digital database) which derived from the aerial photo materials. Transportation digital map is a part of National Transportation Database Building Project carried out by the Korea Transport Institute and Ministry of Construction and Transportation. Transportation digital map for the purpose of transportation plan and investment has been updated and corrected the NGIS database especially for road network. Transportation digital map database is essential basic data fully applied for transportation policy and planning. The database must be reliable and objective to be applied for national transportation policy decision and transportation analysis. In addition, it needs accuracy and currentness to reflect the road network for the survey year. To satisfy the purpose of the database, following steps are necessary first, data Production and building has to be done by guideline of survey and database building. Secondly, geometric and logical errors which can occur during the survey and database building should be carefully detected. Thirdly, sectional guideline for database examination and procedure needs to be set up systematically and coherently This study is about examination guidelines for section and procedure on nodes and links which are essential object in transportation digital map database. According to the type of error, consistent and systematic error examination can lead to quality guarantee for objective and reliable database.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.6
• /
• pp.1011-1021
• /
• 2016

This study performs the potential flood hazard analysis by applying elevation data, soil data and land use data. The susceptibility maps linked to elevation, soil and land use are combined to develop the new types of flood hazard map such as runoff production map and runoff accumulation map. For the development of the runoff production map, land use, soil thickness, permeability, soil erosion and slope data are used as runoff indices. For the runoff accumulation map, elevation, knick point and lowland analysis data are used. To derive an integrated type of flood potential hazard, a TOPSIS (The Technique for Order of Preference by Similarity to Ideal Solution) technique, which is widely applied in MCDM (Multi-Criteria Decision Making) process, is adopted. The indices applied to the runoff production and accumulation maps are considered as criteria, and the cells of analysis area are considered as alternatives for TOPSIS technique. The model is applied to Gamcheon watershed to evaluate the flood potential hazards. Validation with large scale data shows the good agreements between historical data and runoff accumulation data. The analysis procedure presented in this study will contribute to make preliminary flood hazard map for the public information and for finding flood mitigation measures in the watershed.

• Journal of Korean Society of Forest Science
• /
• v.87 no.2
• /
• pp.300-307
• /
• 1998

It is not an easy task for forest managers to make sound decisions on forest management and operations planning because of huge sets of spatial and temporal data and complex decision-making processes involved. However, as an efficient tool, GIS techniques enable them to enhance broad understandings on forest inventory and management conditions. In this study, we developed a GIS model for field use in forest management. In building the model, we have chosen MapInfo version 4.0 as the basic engine of the model. The model also includes an interface module to help forest managers use MapInfo functions easily. It handles MapInfo functions required to manage inventory data and analyze spatial distributions of forest stands. For testing field applicability of the model, we have build field data sets for a district of Chunchun National Forest. Then, we tested functions through quarrying stand attributes and constructing thematic maps. In this paper, the structures and functions of the model as well as the results of field applications are discussed.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.3
• /
• pp.287-294
• /
• 2012

The spread of infectious diseases in the event of livestock is getting faster and the route of spread gets more varied. It is important for the responsible agency to detect early and establish a prevention and surveillance system. If the spread cannot be contained effectively, great damage and loss will be inevitable in terms of social, environment and economic aspects as well as the welfare of the farmers. At present in Korea, a web-based Infectious Livestock Diseases Statistics System (AIMS: Animal Infectious Disease Data Management System) has been already implemented for this purpose and the service is available to the general public. But this system does not provide geospatial information and does not provide support for decision making and does not provide multi-dimensional information. In this study, an open source-based SOLAP (Spatial On-Line Analytical Processing) technology is applied to enable many diverse forms of data analysis from many aspects to support decision making. The SOLAP system was designed to integrate geospatial information and the analysis of information has been largely divided into map-based analysis and table-based analysis.