• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.386-390
• /
• 2003

Data mining is a process of discovering useful patterns for decision making from an amount of data. It has recently received much attention in a wide range of business and engineering fields. Classifying a group into subgroups is one of the most important subjects in data mining. Tree-based methods, known as decision trees, provide an efficient way to finding the classification model. The primary concern in tree learning is to minimize a node impurity, which is evaluated using a target variable in the data set. However, there are situations where multiple target variable should be taken into account, for example, such as manufacturing process monitoring, marketing science, and clinical and health analysis. The purpose of this article is to present some methods for measuring the node impurity, which are applicable to data sets with multivariate target variables. For illustration, a numerical cxample is given with discussion.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.369-373
• /
• 2006

A 3D modeling of urban area can be composed the terrain modeling that can express specific and shape of the terrain and the object modeling such as buildings, trees and facilities which are found in urban areas. Especially in a 3D modeling of building, it is very important to make a unit model by simplifying 3D structure and to take a texture mapping, which can help visualize surface information. In this study, the texture mapping technique, based on library for 3D urban modeling, was used for building modeling. This technique applies the texture map in the form of library which is constructed as building types, and then take mapping to the 3D building frame. For effectively apply, this technique, we classified buildings automatically using LiDAR data and made 3D frame using LiDAR and digital map. To express the realistic building texture, we made the texture library using real building photograph.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.12
• /
• pp.1095-1100
• /
• 2007

Visibility of the satellite navigation is related to a environmental condition of a receiver. Obstacles like buildings and trees in urban areas can block signals and have effects on accuracy and reliability of positioning. This paper presents a method of creating 3D analysis model of urban canyon of Seoul using three-Dimensional digital map. Analysis techniques of visible satellites with Ray-Polygon Collision Detection and validation of algorithm through field tests are discussed. We have compared and analyzed the visibility of GPS and Galileo with respect to separate and simultaneous tracking in view of DOP (Dilution of Precision) using the 3D GIS digital map.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.7
• /
• pp.415-422
• /
• 2018

Lycorma delicatula, known as spotted lanternfly, is a planthopper native to Southeast Asia, including Vietnam, India and South China. This species damages local fruit trees and has spread rapidly in South Korea in recent years. The purpose of this study is to present the methods and estimation results pertaining to the risk of invasive species like Lycorma delicatula. We used a partial budget (PB) method to assess direct income reduction of farm households and a partial equilibrium (PE) model to examine social welfare change from the outbreak of Lycorma delicatula. We also estimated the future economic impacts of Lycorma delicatula under various climate scenarios considering habitat suitability. As climate change progresses, domestic ecosystems are expected to become increasingly vulnerable to pest outbreaks leading to further economic damage. We believe that this study can be a base to evaluate efficiency of the national pest control and quarantine system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.531-540
• /
• 2010

In this paper, we present a two-phase shallow semantic parsing method based on a maximum entropy model. The first phase is to recognize semantic arguments, i.e., argument identification. The second phase is to assign appropriate semantic roles to the recognized arguments, i.e., argument classification. Here, the performance of the first phase is crucial for the success of the entire system, because the second phase is performed on the regions recognized at the identification stage. In order to improve performances of the argument identification, we incorporate syntactic knowledge into its pre-processing step. More precisely, boundaries of the immediate clause and the upper clauses of a predicate obtained from clause identification are utilized for reducing the search space. Further, the distance on parse trees from the parent node of a predicate to the parent node of a parse constituent is exploited. Experimental results show that incorporation of syntactic knowledge and the separation of argument identification from the entire procedure enhance performances of the shallow semantic parsing system.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.10 no.3
• /
• pp.147-154
• /
• 2010

This study analyzed the characteristics of sediment produce by landslide triggered by rainfall. One-dimensional unsaturated groundwater model and infinite slope stability analysis were used to estimate the behavior of soil moisture and slope stability according to rainfall, respectively. Slope stability analysis was performed considering on soil depth and characteristics of trees. The results of the analysis on characteristics of sediment produce according to rainfall events showed that the sediment produce by landslide was mainly contributed to rainfall intensity and its temporal clustering. The results of the analysis on characteristics of sediment produce by extreme events showed that remaining rainfall amount of typhoon 'Rusa' was much more than that of the other extreme events, and thus this remaining rainfall was to contribute to sediment transportation. Additionally, only a small number of extreme events were found to cause most amount of sediment produce in a basin.

• KIEAE Journal
• /
• v.9 no.3
• /
• pp.61-68
• /
• 2009

Gwangju Metropolitan Government & Ministry of Environment have signed a model city in response to Climate Change agreement. The agreement calls for Gwangju to cut greenhouse gas emissions 10% below 2005 levels by 2015. Gwangju has seen this agreement as an opportunity to cut pollution and conserve the environment as well as to reinvigorate local economy. According to policy of Gwangju, Gwangju held design competition for Gwangju City Arboretum on march, 2009. The purpose of design competition was to give a wide publicity to Gwangju as Hub City of Asian Culture and construct carbon-neutral arboretum in accordance with the policy of 'Low-Carbon and Green Growth'. First of all, a design concept of arboretum is 'winding, round, overlay 'to reflect the landscape of Nam-do which is surrounded by mountains and river flows through the village. Second, the arboretum has five different places with these themes - Forest of Festivals, Health, Nature, Nostalgia, Education and Future. Each place has a symbolic theme park and different flow planning respectively. Third, the most critical point is that the arboretum is a carbon-neutral park. Gwangju arboretum will soon be developed in metropolitan sanitary landfill and constructed as the O2 arboretum based on low carbon strategy. Fourth, the O2 arboretum suggests specialized issue : 'Energy Saving', 'Recycling System', 'Green Network', 'Water System(rainwater maintenance and wetland development)'. Besides, main buildings(greenhouse, visitor center, Nam-do experience exhibition hall, and forest museum) is designed in consideration of harmony with topography character, surroundings. Also, planting will be a multilayer plant based on native landscape trees in consideration of function and the growth characteristics.

• Journal of KIISE:Software and Applications
• /
• v.36 no.4
• /
• pp.298-305
• /
• 2009

In contrast to content_based filtering systems, collaborative filtering systems not only don't contain information of items, they can not recommend items when users don't provide the information of their interests. In this paper, we propose the recommender agent using association item tree to solve the shortcomings of collaborative filtering systems. Firstly, the proposed method clusters users into groups using vector space model and K-means algorithm and selects group typical rating values. Secondly, the degree of associations between items is extracted from computing mutual information between items and an associative item tree is generated by group. Finally, the method recommends items to an active user by using a group typical rating value and an association item tree. The recommender agent recommends items by combining user information with item information. In addition, it can accurately recommend items to an active user, whose information is insufficient at first rate, by using an association item tree based on mutual information for the similarity between items. The proposed method is compared with previous methods on the data set of MovieLens recommender system.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.3
• /
• pp.22-30
• /
• 2007

It is difficult to generate DTM using aerial photographs because trees usually cover disaster occurred areas. So, this study proposed how to filter by moving window using digital aerial photographs and generate accurate DTM. The results were compared with those of adaptive filtering by commercial digital photogrammetry software (Socet set) to find out the effect of tree removal by window size in forest soil sediment disaster. And then they were compared with DTM generated from LiDAR data. As a result, it was showed that the accuracy of moving filtering DTM was lower than that of LiDAR DTM while it was higher by 6m than that of Adaptive filtering.

• Journal of Forest and Environmental Science
• /
• v.36 no.1
• /
• pp.37-46
• /
• 2020

Vegetation carbon sequestration and regeneration are the two major parameters of forest research. In this study, we analyzed the vegetation carbon stock and regeneration of community-managed pine plantation of Kathmandu, central Nepal. Vegetation data were collected from 40 circular plots of 10 m radius (for the tree) and 1m radius (for seedling) applying a stratified random sampling and nested quadrat method. The carbon stock was estimated by Chave allometric model and estimated carbon stock was converted into CO₂ equivalents. Density-diameter (d-d) curve was also prepared to check the regeneration status and stability of the plantation. A d-d curve indicates the good regeneration status of the forest with a stable population in each size class. Diversity of trees was very low, only two tree species Pinus roxburghii and Eucalyptus citriodora occurred in the sample plots. Pine was the dominant tree in terms of density, basal area, biomass, carbon stock and CO₂ stock than the eucalyptus. The basal area, carbon stock and CO₂ stock of forest was 33±1.0 ㎡ ha^-1, 108±5.0 Mg ha^-1 and 394±18 Mg ha^-1, respectively. Seedling and tree density of the plantation was 4,965 ha^-1 and 339 ha^-1 respectively. The forest carbon stock showed a positive relationship with biomass, tree diameter, height and basal area but no relationship with tree density. Canopy cover and tree diameter have a negative effect on seedling density and regeneration. In conclusion, the community forest has a stable population in each size class, sequestering a significant amount of carbon and CO₂ emitted from densely populated Kathmandu metro city as the forest biomass hence have a potentiality to mitigate the global climate change.