• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.12 no.2
• /
• pp.50-60
• /
• 2009

A spatial decision making process is needed when a local government tries to make polices and plans for eco-tourism in urban and regional site scale. This study aimed to suggest an assessment model to support spatial decision making on planning and making polices for eco-tourism. The model composes 6 stages of 'setting up ecogeographic territories'. 'value analysis method as ecotourism resources' 'synthetic assessing', 'grading values', 'selecting main resources for ecotourism' and 'spatial decision making support'. Applying the model to Shiheung city in Kyounggi province, validity was secured. By using the model, it was possible to make some decisions effectively such as selection of ecotourism resources, decision of the priorities of polices for ecotourism, and setting up the type of ecotourism to be introduced. In addition, by visualizing high valued resources and areas for ecotourism it w possible to support to make plans and policies effectively.

• Journal of Fashion Business
• /
• v.12 no.6
• /
• pp.34-45
• /
• 2008

This research was designed to find decision factors through color assortment planning process by Korean women's clothing merchandisers and to look for if there exists difference with American women's clothing merchandisers. A merchandise assortment is a collection of various quantities of styles, colors, sizes, and prices of related merchandise, usually grouped under one classification within a department. The subjects were 20 women's clothing merchandisers who work for clothing retail stores from 5 to 22 years in US and Korea. The authoring process was done for qualitative data analysis. The decision factors of color assortment planning were identified with four stages; information search, qualitative evaluation, quantitative evaluation, and selection. There were differences of color assortment decision factors due to different business types, business sizes, fashion-ability, sourcing ways, and merchandise turnover. Noticeable color assortment decision factor differences caused by country difference were not found except considering the target market ethnicity and skin color in US market. Korea merchandisers seem to be more sensitive to present sales data usages and spot order availability in color assortments because of more local production use than American merchandisers.

• Korean Management Science Review
• /
• v.23 no.1
• /
• pp.63-74
• /
• 2006

Decision tree induction algorithm is one of the most widely used methods in classification problems. However, they could be trapped into a local minimum and have no reasonable means to escape from it if tree algorithm uses top-down search algorithm. Further, if irrelevant or redundant features are included in the data set, tree algorithms produces trees that are less accurate than those from the data set with only relevant features. We propose a hybrid algorithm to generate decision tree that uses genetic programming with sequentially selected features. Correlation-based Feature Selection (CFS) method is adopted to find relevant features which are fed to genetic programming sequentially to find optimal trees at each iteration. The new proposed algorithm produce simpler and more understandable decision trees as compared with other decision trees and it is also effective in producing similar or better trees with relatively smaller set of features in the view of cross-validation accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.827-833
• /
• 2020

In this paper, to reduce the unpaid rate of local governments, the internal data elements affecting the arrears in Water-INFOS are searched through interviews with meter readers in certain local governments. Candidate data affecting arrears from national statistical data were derived. The influence of the independent variable on the dependent variable was sampled by examining the disorder of the dependent variable in the data set called information gain. We also evaluated the higher prediction rates of decision tree and logistic regression using n-fold cross-validation. The results confirmed that the decision tree can find more accurate customer payment patterns than logistic regression. In the process of developing an analysis algorithm model using machine learning, the optimal values of two environmental variables, the minimum number of data and the maximum purity, which directly affect the complexity and accuracy of the decision tree, are derived to improve the accuracy of the algorithm.

• Spatial Information Research
• /
• v.8 no.2
• /
• pp.203-211
• /
• 2000

In the GIS literature, evaluation efforts have also been rare and unsystematic because of the difficulties in measuring impacts, and the lack of developed methodologies and evaluation criteria. Using a survey of the an ten local authorities in Korea, this research examines the benefits of using GIS and analyze the factors which affect the benefits of GIS in local authorities. Following are the major findings of this empirical research. First, most of the local authorities employees surveyed report improvements in operational and decision-making benefits. Second, factors influencing the benefits of GIS include political support and performance of the GIS system.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.10 no.5
• /
• pp.1-9
• /
• 2007

Local government with abundant natural resources should consider the nature conservation oriented planning process for the sustainable development. With this regard, the aim of this study is to provide a substantial methodology to support the decision-making process to designate the conservation areas. The objectives of the proposed methodology is to conserve natural resources in the local government's territory through quantitatively assessing the values of the natural resources based on various ecological factors such as topography, flora and fauna. In order to test the usability of the method, Gangneung City in Kangwon-Do is selected considering the latest data availability. Based on the assessment process land use of the subjected city could be categorized into 4 levels of conservative area, conservative level 1 area, conservative level 2 area, and conservative level 3 area. Among them, conservative area and conservative level 1 area could be combined as natural resources conservation area and the others could be regarded as buffer and transitional area. Especially conservation area is surrounded by conservation level 2 area. Conclusively, the GIS methods adopted in this could be the efficient illustrative tool to assess the local natural resource values with the central government established nature-environmental information systems.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2008.11a
• /
• pp.790-793
• /
• 2008

Recently, Intelligent Excavating System(IES) for earthwork automation is on progress since the end of 2006 as a part of construction technology innovation projects in Ministry of Land, Transport and Maritime Affairs. Task Planning System(TPS), one of the detail core technologies of IES, is an optimal work planning system in conditions of effectiveness, safety and economic efficiency by analyzing the work environment data based on earthwork design and work environment recognition technology. For effective earthwork planning, the location of platform must be the most optimal spot for minimization of time, maximization of productivity and reduction of overlapped work spaces and unnecessariness. Besides, the decision of optimal platform location is to be based on the specifications and then is able to be converted with the local area calculation algorithm. This study explains the decision of optimal platform location on the basis of local area from the work space separate process and judges the effectiveness.

• Agribusiness and Information Management
• /
• v.5 no.1
• /
• pp.31-41
• /
• 2013

The research assesses the impact of a digital procurement (e-purjee) system for sugarcane growers in Bangladesh. The system itself is simple, transmitting purchase orders to local farmers via SMS text notification. It replaces a traditional paper-based system fraught with low reliability and delivery delays. Applying expected value theory, and using decision tree representations to depict growers' decision-making complexity in an information-asymmetric environment, we compute outcomes for the strategies and sub-strategies of ICT vs. traditional paper-based order management from the sugarcane growers' perspective. The study results show that the digital procurement system outperforms the paper-based system by tangibly reducing growers' economic losses. The digital system also appears to benefit growers non-monetarily, because of reduced uncertainty and a higher level of perceived fairness. Sugarcane growers appear to value the non-monetary benefits even higher than the economic advantages of the e-purjee system.

• Proceedings of the KSR Conference
• /
• 2003.10b
• /
• pp.454-459
• /
• 2003

The process of determining whether, when, where and how to intervene, of deciding on optimum allocation of resources and minimizing the cost is a very complex problem: different track sections tend to behave differently under the effects of loading; decision-making processes for maintenance work are closely interrelated technically and economically; decision-making for maintenance plans is based on a large quantity of technical and economic information, extensive knowledge and above all experience. For that reason, It is considered very important to develope objective and computer-aided decision-making support system for track maintenance plan. On this paper, we reviewed ECOTRACK system and present the plan of develope decision-making support system for track maintenance appropriate to local condition.

• Journal of the Korea Society for Simulation
• /
• v.5 no.1
• /
• pp.1-12
• /
• 1996

We propose a new approach to classifying a time series data into one of the autoregressive moving-average (ARMA) models. It is bases on two pattern recognition concepts for solving time series identification. The one is an extended sample autocorrelation function (ESACF). The other is a neural network-driven decision tree classifier(NNDTC) in which two pattern recognition techniques are tightly coupled : neural network and decision tree classfier. NNDTc consists of a set of nodes at which neural network-driven decision making is made whether the connecting subtrees should be pruned or not. Therefore, time series identification problem can be stated as solving a set of local decisions at nodes. The decision values of the nodes are provided by neural network functions attached to the corresponding nodes. Experimental results with a set of test data and real time series data show that the proposed approach can efficiently identify the time seires patterns with high precision compared to the previous approaches.