• Journal of the Korean Institute of Landscape Architecture
• /
• v.39 no.2
• /
• pp.10-17
• /
• 2011

The paradigm of the use and management of natural resources is changing. Wise use of natural resources can be achieved by enhancing their conservation value and, at the same time, taking them as an opportunity for regional development. It leads to an idea of pursuing regional development by making good use of natural resources. In this paper, natural resources were classified as living species resources, ecosystem and landscape resources, and non-living resources. The resources were divided into 27 detailed analysis indices. The administrative boundaries of 165 municipalities in Korea were defined as spatial analysis units. Finally, a spatial database of natural resources was built. To classify the regional types, we conducted factor analyses with a detailed index of natural resources and a cluster analysis with the factor value. As the result of the factor analysis, six factors have been deduced as follows: forest resources, landscape resources, coastal ecology resources, inland water resources, landform resources, and ecology visit resources. In addition, the cluster analyses were conducted for the points of the factors drawn. The final classification consists of nine groups, and appropriate methods for each regional development have been suggested. Results of this study will contribute to providing fundamental materials for site selection and objective-setting for regional development policies and planning in consideration of natural resources.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.175-187
• /
• 2011

Since insects play important roles in existence of plants and other animals in the natural environment, they are considered as necessary biological resources from the perspectives of those biodiversity conservation and national utilization strategy. For the conservation and utilization of insect species, an observational learning environment is needed for non-experts such as citizens and students to take interest in insects in the natural ecosystem. The insect identification is a main factor for the observational learning. A current time-consuming search method by insect classification is inefficient because it needs much time for the non-experts who lack insect knowledge to identify insect species. To solve this problem, we proposed an smart phone-based insect identification inference system that helps the non-experts identify insect species from observational characteristics in the natural environment. This system is based on the similarity between the observational information by an observer and the biological insect characteristics. For this system, we classified the observational characteristics of insects into 27 elements according to order, family, and species, and proposed similarity indexes to search similar insects. In addition, we developed an insect identification inference prototype system to show this study's viability and performed comparison experimentation between our system and a general insect classification search method. As the results, we showed that our system is more effective in identifying insect species and it can be more efficient in search time.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.25-39
• /
• 2017

Over 5 million people participate in cycle racing betting and its revenue is more than 2 trillion won. This study predicts the ranking of cycle racing using various statistical analyses and identifies important variables which have influence on ranking. We propose competitive ranking prediction models using various classification and regression methods. Our model can predict rankings with low misclassification rates most of the time. We found that the ranking increases as the grade of a racer decreases and as overall scores increase. Inversely, we can observe that the ranking decreases when the grade of a racer increases, race number four is given, and the ranking of the last race of a racer decreases. We also found that prediction accuracy can be improved when we use centered data per race instead of raw data. However, the real profit from the future data was not high when we applied our prediction model because our model can predict only low-return events well.

• The Journal of Engineering Geology
• /
• v.29 no.2
• /
• pp.99-112
• /
• 2019

Rainfall infiltration through the unsaturated zone is influenced by a range of factors including topography, geology, soil, rainfall intensity, temperature and vegetation; the actual infiltration varies largely in time and space. The infiltration capacity of soil is a critical factor in identifying groundwater recharge and leakage of surface water. It may differ depending on soil types and geological features of a particular basin or territory as well as on the usage of the land. This study was conducted in forest and farmland region of the mid-mountain area (EL. 50~300 m) of Jeju Island to test soil infiltration capacity of the area where rainfall contributes to groundwater. Results were analyzed using the four soil group classification methods presented by Jeong et al. (1995) and NAS (2007) to discover that the method offered by NAS (2007) is more reliable in the mid-mountain area of Jeju Island. The study compares and reviews the existing classification methods using the results of infiltration capacity tests executed on different soil groups throughout the whole region of the Jeju mid-mountain area. It is expected that this work will serve as a guideline for evaluating surface water recharge and hydraulic characteristics of Jeju Island.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.1-11
• /
• 2023

Breast cancer is the disease that affects women the most worldwide. Due to the development of computer technology, the efficiency of machine learning has increased, and thus plays an important role in cancer detection and diagnosis. Deep learning is a field of machine learning technology based on an artificial neural network, and its performance has been rapidly improved in recent years, and its application range is expanding. In this paper, we propose a DNN-SVM hybrid model that combines the structure of a deep neural network (DNN) based on transfer learning and a support vector machine (SVM) for breast cancer classification. The transfer learning-based proposed model is effective for small training data, has a fast learning speed, and can improve model performance by combining all the advantages of a single model, that is, DNN and SVM. To evaluate the performance of the proposed DNN-SVM Hybrid model, the performance test results with WOBC and WDBC breast cancer data provided by the UCI machine learning repository showed that the proposed model is superior to single models such as logistic regression, DNN, and SVM, and ensemble models such as random forest in various performance measures.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.1
• /
• pp.229-249
• /
• 2022

This paper investigates machine learning models for predicting the designation of administrative issues in the KOSDAQ market through various techniques. When a company in the Korean stock market is designated as administrative issue, the market recognizes the event itself as negative information, causing losses to the company and investors. The purpose of this study is to evaluate alternative methods for developing a artificial intelligence service to examine a possibility to the designation of administrative issues early through the financial ratio of companies and to help investors manage portfolio risks. In this study, the independent variables used 21 financial ratios representing profitability, stability, activity, and growth. From 2011 to 2020, when K-IFRS was applied, financial data of companies in administrative issues and non-administrative issues stocks are sampled. Logistic regression analysis, decision tree, support vector machine, random forest, and LightGBM are used to predict the designation of administrative issues. According to the results of analysis, LightGBM with 82.73% classification accuracy is the best prediction model, and the prediction model with the lowest classification accuracy is a decision tree with 71.94% accuracy. As a result of checking the top three variables of the importance of variables in the decision tree-based learning model, the financial variables common in each model are ROE(Net profit) and Capital stock turnover ratio, which are relatively important variables in designating administrative issues. In general, it is confirmed that the learning model using the ensemble had higher predictive performance than the single learning model.

• Journal of Korea Water Resources Association
• /
• v.56 no.4
• /
• pp.261-272
• /
• 2023

In recent years, natural disasters such as heavy rainfall and typhoons have occurred more frequently, and their severity has increased due to climate change. The Korea Meteorological Administration (KMA) currently uses the same criteria for all regions in Korea for watch and warning based on the maximum cumulative rainfall with durations of 3-hour and 12-hour to reduce damage. However, KMA's criteria do not consider the regional characteristics of damages caused by heavy rainfall and typhoon events. In this regard, it is necessary to develop new criteria considering regional characteristics of damage and cumulative rainfalls in durations, establishing four stages: blue, yellow, orange, and red. A classification model, called DSCM (Disaster Severity Classification Model), for the four-stage disaster severity was developed using four machine learning models (Decision Tree, Support Vector Machine, Random Forest, and XGBoost). This study applied DSCM to local governments of Seoul, Incheon, and Gyeonggi Province province. To develop DSCM, we used data on rainfall, cumulative rainfall, maximum rainfalls for durations of 3-hour and 12-hour, and antecedent rainfall as independent variables, and a 4-class damage scale for heavy rain damage and typhoon damage for each local government as dependent variables. As a result, the Decision Tree model had the highest accuracy with an F1-Score of 0.56. We believe that this developed DSCM can help identify disaster risk at each stage and contribute to reducing damage through efficient disaster management for local governments based on specific events.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.6
• /
• pp.38-48
• /
• 2008

This study was conducted to evaluate the vegetation structure of community by the phytosociology method, floristic composition table on coast of South Korea. Form 2007 June until November, $2m{\times}2m$ quadrat was established in native Glehnia littoralis in order to record a dominants and coverage, and it drew the profile. It was found out that the mean temperature in the distributed areas for Glehnia littoralis population was $11^{\circ}C$ or more. The flora of the studied area in Glehnia lottoralis community of coastal dune was listed as 100 species. Glehnia lottoralis community of appearance species of Yeonggwanggun Duwori was many most by 44 species. Carex pumila, Carex Kobomugi, Imperata cylindrica var. koenigii, Ischaemum anthephehoroides and Vitex rotundifolia range all over the studied areas. And the vegetation of Glehnia littoralis community was classified into Vitex rotundifolia subcommunity, Ischaemun anthephephoroides subcommunity and Imperata cylindrica var. koenigii subcommunity. Native Glehnia littoralis was classified into preserve area, natural selection area and artificial destruction area. It must preserve native Glehnia littoralis of Goseong, Yeongdeok, Haenam it was ecological important area.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.30 no.1
• /
• pp.6-16
• /
• 2015

This study established the genetic characterisation of 10 microsporidian isolates infecting non-mulberry silkworms (Antheraea assamensis and Samia cynthia ricini) collected from biogeographical forest locations in the State of Assam, India, using PCR-based markers assays: inter simple sequence repeat (ISSR) and random amplified polymorphic DNA (RAPD). A Nosema type species (NIK-1s_mys) was used as control for comparison. The shape of mature microsporidian spores were observed oval to elongated, measuring 3.80 to $4.90{\mu}m$ in length and 2.60 to $3.05{\mu}m$ in width. Fourteen ISSR primers generated reproducible profiles and yielded 178 fragments, of which 175 were polymorphic (98%), while 16 RAPD primers generated reproducible profiles with 198 amplified fragments displaying 95% of polymorphism. Estimation of genetic distance coefficients based on dice coefficients method and clustering with un-weighted pair group method using arithmetic average (UPGMA) analysis was done to unravel the genetic diversity of microsporidians infecting Indian muga and eri silkworm. The similarity coefficients varied from 0.385 to 0.941 in ISSR and 0.083 to 0.938 in RAPD data. UPGMA analysis generated dendrograms with two microsporidian groups, which appear to be different from each other. Based on Euclidean distance matrix method, 2-dimensional distribution also revealed considerable variability among different identified microsporidians. Clustering of these microsporidian isolates was in accordance with their host and biogeographic origin. Both techniques represent a useful and efficient tool for taxonomical grouping as well as for phylogenetic classification of different microsporidians in general and genotyping of these pathogens in particular.

• Journal of Ecology and Environment
• /
• v.42 no.3
• /
• pp.103-110
• /
• 2018

Backgrounds: In arid grasslands, wells are subject to heavy trampling and grazing pressure, which can increase vulnerability to local land degradation. To investigate trampling and grazing, we surveyed plant communities at three well sites in the desert steppe of Mongolia, using 1600-m line transects from the wells. The sites (Bshrub, Sshrub, and shrubL) differed by concomitant shrub type (big shrub, small shrub, and shrub-limited) and livestock pressure (light, medium, and heavy). A plant classification scheme based on edibility and morphology (rosette or creeping type) was used to separate grazing and trampling effects on plant communities. Results: Edible plants were dominant at all sites but a fraction of grazing- and trampling-tolerant plants increased in the order Bshrub, Sshrub, and shrubL, following livestock pressure. Clear transition zones from inedible to edible plant groups were recognized but at different locations and ranges among the sites. Trampling-tolerant plants explained 90% of inedible plants at Sshrub with camels and horses, but grazing-tolerant plants prevailed (60%) at shrubL with the largest livestock number. Plant coverage increased significantly along the transects at Bshrub and Sshrub but showed no meaningful change at shrubL. Herbaceous plant biomass showed significant positive and negative trends at Bshrub and shrubL, respectively. Conclusions: Both grazing and trampling can produce larger fractions of inedible plants; in this, camel and horses can have considerable effects on desert-steppe plant communities through trampling.