• The Korean Journal of Mycology
• /
• v.34 no.2
• /
• pp.63-72
• /
• 2006

This study was conducted to investigate the diversity of ectomycorrhizal mushroom by surveying sites from June 2004 to October 2005. The obtained results from investigation were as follows. The total of 5 classes 16 orders 63 families 149 genera and 358 species including saprophytic and ectomycorrhizal fungi was investigated. A total of 17 families 36 genera 152 species (1,285ea.) of ectomycorrhizal mushroom was investigated. The mushrooms are classified into 9 families 27 genera and 136 species in Agaricales, 5 families 6 genera and 12 species in Aphyllophorales and 3 families 3 genera and 4 species in Gasteromycetes. Dorminant species were Russulaceae (35 species) followed by Boletaceae (34 species), Amanitaceae(22 species) and Cortinariaceae (21 species). The mushroom occurrence of octomycorrhizal fungi was closely related to climatic conditions such as high air temperature and lots of rainfall from July to September. The environment factors which have a favorable influence of mushroom occurrence were soil pH, available $P_{2}O_{5}$ of soil and rainfall and air temperature of climatic environment.

• 한국지구물리탐사학회:학술대회논문집
• /
• 1999.08a
• /
• pp.1-20
• /
• 1999

In Japan, geophysical exploration methods have been widely applied to civil engineering and construction fields for a long time. In particular, seismic refraction has long played a significant role in geotechnical site investigations for tunnels, dams and landslides. However, our growing interest on the social and natural environment makes the methods available and its application fields diversify. Digital technologies such as personal computer have revolutionized our ability to acquire large volumes of data rapidly, and to produce more reliable results for subsurface image. Also, color graphics easily visualizes survey results In a more understandable manner, These days geophysical methods are essential to assessing grouting effects, predicting the front of tunnel cutting face, monitoring the movement, pollution and purification process of groundwater. Now three-dimensional exploration techniques have developed for the site characterization in civil engineering and construction needs.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.6
• /
• pp.488-496
• /
• 2019

The estimation of block erection work time at a dock is one of the important factors when establishing or managing the total shipbuilding schedule. In order to predict the work time, it is a natural approach that the existing block erection data would be used to solve the problem. Generally the work time per unit is the product of coefficient value, quantity, and product value. Previously, the work time per unit is determined statistically by unit load data. However, we estimate the work time per unit through work time coefficient value from series ships using machine learning. In machine learning, the outcome depends mainly on how the training data is organized. Therefore, in this study, we use 'Feature Engineering' to determine which one should be used as features, and to check their influence on the result. In order to get the coefficient value of each block, we try to solve this problem through the Ensemble learning methods which is actively used nowadays. Among the many techniques of Ensemble learning, the final model is constructed by Stacking Ensemble techniques, consisting of the existing Ensemble models (Decision Tree, Random Forest, Gradient Boost, Square Loss Gradient Boost, XG Boost), and the accuracy is maximized by selecting three candidates among all models. Finally, the results of this study are verified by the predicted total work time for one ship among the same series.

• Journal of Environmental Science International
• /
• v.16 no.3
• /
• pp.277-285
• /
• 2007

The purpose of this study is to analyze seasonal distribution of insects, birds, fishes, and benthos for Gongji stream in Chuncheon and to explore some strategies towards creating a desirable close-to-nature stream. The number of species occurred in the study stream was 23 for butterflies and 149 for other insects, 23 for birds, 15 for fishes, and 47 for benthos. The study stream was dominated by Artogenia rapae, Polygonia caureum, Cyntia cardui for butterflies, and Passer montanus, Anas crecca, Anas platyrhynchos for birds. The dominant species were Rhynchocypris oxycephalus, Zacco plutypus, Carassius auratus for fishes, and Limnodrilus sp. 2, Chiranumus sp. 2, Hydropsyche KUb for benthos. Attracting insect species of higher density requires planting of host plant species and stabilization of plant coverage against disturbances. To enhance species diversify and density of birds, it is desirable to provide diverse habitats including preservation of downstream wetland and natural vegetation, creation of sand bars and islands with sand and gravel, and restriction or traffic passing and parking. Restoring fish and benthos habitats needs improvement of water quality, layout of gravels and stones on sand-dominant streambed, and use of close-to-nature revetment techniques.

• Journal of the Korean Society of Safety
• /
• v.27 no.6
• /
• pp.172-177
• /
• 2012

In areas around Deoksan Li and Deokjeon Li, Inje Eup, Inje Gun, located between $38^{\circ}2^{\prime}55^{{\prime}{\prime}}N$ and $38^{\circ}5^{\prime}50^{{\prime}{\prime}}N$ in latitude and $128^{\circ}11^{\prime}20^{{\prime}{\prime}}E$ and $128^{\circ}18^{\prime}20^{{\prime}{\prime}}E$ in longitude, large-sized avalanche disasters occurred due to Typhoon Ewiniar in 2006. As a result, 29 people were dead or missing, along with a total of 37.25 billion won of financial loss(Gangwon Province, 2006). To evaluate such landslide and debris flow risk areas and their vulnerability, this study applied a technique called 'Weight of Evidence' based on GIS. Especially based on the overlay analysis of aerial images before the occurrence of landslides and debris flows in 2005 and after 2006, this study extracted 475 damage-occurrence areas in a shape of point, and established a DB by using such factors as topography, hydrologic, soil and forest physiognomy through GIS. For the prediction diagram of debris flow and landslide risk areas, this study calculated W+ and W-, the weighted values of each factor of Weight Evidence, while overlaying the weighted values of factors. Besides, the diagram showed about 76% in prediction accuracy, and it was also found to have a relatively high correlationship with the areas where such natural disasters actually occurred.

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.1-13
• /
• 2009

Scene classification and concept-based procedures have been the great interest for image categorization applications for large database. Knowing the category to which scene belongs, we can filter out uninterested images when we try to search a specific scene category such as beach, mountain, forest and field from database. In this paper, we propose an adaptive segmentation method for real-world natural scene classification based on a semantic modeling. Semantic modeling stands for the classification of sub-regions into semantic concepts such as grass, water and sky. Our adaptive segmentation method utilizes the edge detection to split an image into sub-regions. Frequency of occurrences of these semantic concepts represents the information of the image and classifies it to the scene categories. K-Nearest Neighbor (k-NN) algorithm is also applied as a classifier. The empirical results demonstrate that the proposed adaptive segmentation method outperforms the Vogel and Schiele's method in terms of accuracy.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.29 no.1
• /
• pp.100-112
• /
• 2001

The purpose of this study is to construct the evaluation criteria based on the relative importance and various combination of each evaluation index and then to evaluate urban biotope in terms of conservation of species and habitat. After the standard of evaluation had been developed through the literature review, the relative importance of the evaluation index through expert survey was found out, and the evaluation model of biotope value has been established. The results of this study are as follows; 1) We have constructed the nineteen evaluation criteria through literature reviews, and have provided relative importance to each evaluation index of the diversity of typical species in biotope, afforestation rate, stratification, Hemeroby grads, and the diversity of landscape patterns based on the results of expert survey. and then we have constructed the evaluation system using the relative importance criteria. 2) To evluate urban biotope using the evaluation system constructed, we selected 14 sites. The final evaluation results of each site is as follows; The III grade areas are Seohan and Hwasung high-rise apartment at Beummul-Dong, Korea Men Power /Agency in Sungs 대 industrial zone, the adjacent area of St. Tongil, and Hyomyung elementary school. The II grade areas are the farm land behind the third Anshim Jugong apartment, and Ehyun park. The I grade areas are swampy land in front of Kangchon and Anshim construction site, water space with semi-natural style in front of Gangchon Woobang apartment, forest zone near page Temple at mt. Palgong, the edge area of Jisan and Gosan, and the tendril yard against Anshim middle school. The only grade IV area is the commercial zone near Taegu Department 3) It is highly useful to evaluate urban biotope using the evaluation criteria constructed for this research, the evaluation criteria we developed may be difficult to guarantee the ability for reproduction and recovery, the appearance-number of the rare and endangered species are difficult to estimate urban biotopes. In the future, it is highly useful to evaluate biotope in terms of conservation of species and habitat through its valuation criteria developed in this research and it is necessary to develop the evaluation criteria applicable to estimation of biotope inventory and reproduction of biotope.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.2
• /
• pp.104-113
• /
• 2008

Due to the increasing needs of land supply, green space has been continuously encroached and resulted considerable naturality deterioration in Korea. In order to overcome the problem, it is necessary to introduce a integrated system for managing the quantitative and qualitative aspects of green space. With this regard, this study is to derive the feasibility for the adoption of the 'no net loss of green' policy to Korea from German and Japanese experiences. In Germany, natural resources are protected and inevitable damages were compensated through the adoption of 'interference regulation'. In Japanese case, future green space and artificial green foundation should be specified on the green basic plan which pursuit the improvement of naturality. In order to introduce the 'no net loss of green' policy to Korea, not only awareness raising on integrated green management system but also amendment of related regulations are needed. In detail, restoration and recovery on the damaged nature should be clearly elucidated and indicators to evaluate the current naturality and calculation methods for the restoration should be developed. Should this integrated green management system introduced, deterioration of naturality by development activities could be minimized thorough the adoption of land development permission criteria and green space management methodologies.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.14 no.4
• /
• pp.25-40
• /
• 2011

The vascular plants in Jeokjabong, Bogil Island were listed 350 taxa composed of 89 families, 233 genera, 309 species, 1 subspecies, 36 varieties and 4 forms. Divided into woody plants were 142 taxa (40.6%) and herbaceous plants were 208 taxa (59.4%). Based on the list of rare and endangered species by Korea Forest Service and Korea National Arboretum, 3 taxa were recorded; Celtis choseniana, Asarum maculatum, Rubus sorbifolius, and endemic plants, 10 taxa were recorded; Asarum maculatum, Cephalotaxus koreana, Carpinus coreana, Celtis choseniana, Lespedeza maritima, Indigofera koreana, Dendropanax morbifera, Ligustrum quihoui var. latifolium, Weigela subsessilis, Carex okamotoi, and plant species subject to permission for taking abroad, 4 taxa were recorded; Celtis choseniana, Asarum maculatum, Vaccinium oldhami, Carex okamotoi. Based on the list of floristic regional indicator plants by Korean Ministry of Environment were total 64 taxa (18.3% of all 350 taxa of vascular plants); Ligustrum quihoui var. latifolium in class IV, 19 taxa (Stauntonia hexaphylla, Cinnamomum japonicum, Zanthoxylum ailanthoides, Daphniphyllum macropodum, Centella asiatica, Verbena officinalis, Mitchella undulata, etc.) in class III, 5 taxa (Potentilla dickinsii, Ostericum melanotilingia, Sanicula rubriflora, Caryopteris incana, Teucrium veronicoides) in class II and 39 taxa (Gleichenia dichotoma, Cyrtomium fortunei, Aphananthe aspera, Rubus hirsutus, Meliosma myriantha, Hedera rhombea, Ainsliaea apiculata, etc.) in class I. Based on the list of naturalized plants, 5 families, 17 genera, 20 taxa (Phytolacca americana, Lepidium virginicum, Robinia pseudo-acacia, Verbesina alternifolia, Lolium perenne, etc.) and naturalization rate was 5.7% of all 350 taxa of vascular plants. Hereafter natural ecosystem into disturbance on naturalized plants and legal protection species and rare and endangered species distribute in the Bogil Island, precision investigation after management counterplan of the monitoring a point of view be required.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.535-540
• /
• 2016

Coreference resolution is to identify mentions in documents and is to group co-referred mentions in the documents. It is an essential step for natural language processing applications such as information extraction, event tracking, and question-answering. Recently, various coreference resolution models based on ML (machine learning) have been proposed, As well-known, these ML-based models need large training data that are manually annotated with coreferred mention tags. Unfortunately, we cannot find usable open data for learning ML-based models in Korean. Therefore, we propose an efficient coreference resolution model that needs less training data than other ML-based models. The proposed model identifies co-referred mentions using random forests based on sieve-guided features. In the experiments with baseball news articles, the proposed model showed a better CoNLL F1-score of 0.6678 than other ML-based models.