• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.39-39
• /
• 2018

우리나라는 전체 국토의 약 70%가 산악지형으로 이루어져 있고 연중 강우가 6월에서 9월에 집중되는 기후적 특성을 가지고 있다. 최근 기후변화의 영향까지 더해지면서 시간당 300mm 이상의 집중호우를 보이는 이상강우가 빈번하게 발생하고 있다. 대부분의 도시지역은 하천을 중심으로 발달되어 있어 인구 및 사회기반시설의 집약정도가 매우 높고 하천변 저지대 지역에 주거 및 상업시설이 밀집되어 있다. 기후적 지역적 특성으로 인한 홍수피해를 미연에 방지하고 피해를 최소화하기 위하여 치수 중심의 수자원 관리를 위해 노력하고 있다. 하지만 우리나라의 하천관리는 시기별 하천 수량의 급격한 변동으로 어려움을 겪고 있다. 이러한 어려움을 극복하고 효율적인 수자원 관리 및 홍수피해 저감을 위해 수계를 중심으로 20개의 다목적댐을 건설하여 운영 관리 중에 있다. 특히, 홍수기 시 댐 운영은 예상 강우에 따라 적절한 예비방류와 강우 시 효율적인 댐 운영계획이 필수적이다. 본 연구에서는 강우가 집중되는 홍수기 댐 운영 시에 예상 강우량에 따라 댐 유역 내 유량 증가에 기여하는 정도를 예측할 수 있는 유출율 예측 회귀식을 개발하였다. 유출율은 강우와 유출량의 비로 지역특성, 강우특성, 관개여부, 선행강우량, 강우이동 방향 등 다양한 요인에 의해 복잡한 메케니즘을 갖는다. 단순히 예상되는 총강우량에 따른 유출율 만으로 상호관계를 정의하기가 쉽지 않기 때문에 한국수자원공사에서 개발한 댐군 홍수조절 연계운영시스템(COSFIM)인 수문학적 연계운영모형을 활용하였다. 최근 10년간 홍수기에 발생한 강우사상별 시간단위의 수문자료(총강우량, 기저유량, 유출율, 무강우일수, 강우지속시간 등) 분석을 실시하였다. COSFIM 모형을 통한 결과를 토대로 고려항목 간 교차검증을 통해 사분위수범위의 이상치 경계를 설정하고 상관분석 결과에 따라 0.5 이상의 상관성이 높은 항목을 활용하여 예측 강우량에 따른 유출율 예측 회귀식을 도출하였다. 본 연구에서 개발한 예측 강우에 따른 유출율 예측 산정식은 댐 유역에 예상되는 강우량에 대하여 하천의 유량 증가 예측 정도를 정량적으로 제시할 수 있으며, 실제 홍수기 댐 운영 시 예상 강우량에 따라 신속하고 적절한 수문 방류 계획 수립에서 용이하게 활용할 수 있을 것으로 기대한다.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.97-117
• /
• 2021

Predicting term deposit subscriptions is one of representative financial marketing in banks, and banks can build a prediction model using various customer information. In order to improve the classification accuracy for term deposit subscriptions, many studies have been conducted based on machine learning techniques. However, even if these models can achieve satisfactory performance, utilizing them is not an easy task in the industry when their decision-making process is not adequately explained. To address this issue, this paper proposes an explainable scheme for term deposit subscription forecasting. For this, we first construct several classification models using decision tree-based ensemble learning methods, which yield excellent performance in tabular data, such as random forest, gradient boosting machine (GBM), extreme gradient boosting (XGB), and light gradient boosting machine (LightGBM). We then analyze their classification performance in depth through 10-fold cross-validation. After that, we provide the rationale for interpreting the influence of customer information and the decision-making process by applying Shapley additive explanation (SHAP), an explainable artificial intelligence technique, to the best classification model. To verify the practicality and validity of our scheme, experiments were conducted with the bank marketing dataset provided by Kaggle; we applied the SHAP to the GBM and LightGBM models, respectively, according to different dataset configurations and then performed their analysis and visualization for explainable term deposit subscriptions.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1149-1161
• /
• 2021

With a trend of the utilization of computer vision for satellite images, cloud detection using deep learning also attracts attention recently. In this study, we conducted a U-Net cloud detection modeling using SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset with the image data augmentation and carried out 10-fold cross-validation for an objective assessment of the model. Asthe result of the blind test for 1800 datasets with 512 by 512 pixels, relatively high performance with the accuracy of 0.821, the precision of 0.847, the recall of 0.821, the F1-score of 0.831, and the IoU (Intersection over Union) of 0.723. Although 14.5% of actual cloud shadows were misclassified as land, and 19.7% of actual clouds were misidentified as land, this can be overcome by increasing the quality and quantity of label datasets. Moreover, a state-of-the-art DeepLab V3+ model and the NAS (Neural Architecture Search) optimization technique can help the cloud detection for CAS500 (Compact Advanced Satellite 500) in South Korea.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.137-144
• /
• 2021

The purpose of this study is to analyze the factors affecting the education experience, education needs, and knowledge level of calculation criteria for dental workers. It was conducted on dental workers in Daegu and Gyeongbuk province and an online survey was conducted using Google Survey. We used frequency analysis, crossover analysis, and ANOVA analysis method to find out general characteristic, education experience, education needs, and knowledge level according to education experience and education needs of candidates. As a result of in the knowledge level survey of dental health insurance, there were high rates of incorrect answers to the calculation criteria when the claim program automatically processes it or notifies you through an error window. The level of knowledge of candidates who are experienced, on a claim, and with experience in dental insurance training in the last six months was high. In conclusion, it seems that accurate and correct insurance claims are possible when the dental workers are familiar with the calculation criteria changed through regular dental health insurance education. We look forward to this study providing basic data in preparation of education system for professional dental insurance claims for dental workers.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1507-1515
• /
• 2021

If chlorophyll-a is estimated through ocean color remote sensing, it is able to understand the global distribution of phytoplankton and primary production. However, there are missing data in the ocean color observed from the satellites due to the clouds or weather conditions. In thisstudy, the missing data of the GOCI (Geostationary Ocean Color Imager) chlorophyll-a product wasreconstructed by using DINEOF (Data INterpolation Empirical Orthogonal Functions). DINEOF reconstructs the missing data based on spatio-temporal data, and the accuracy was cross-verified by removing a part of the GOCI chlorophyll-a image and comparing it with the reconstructed image. In the study area, the optimal EOF (Empirical Orthogonal Functions) mode for DINEOF wasin 10-13. The temporal and spatialreconstructed data reflected the increasing chlorophyll-a concentration in the afternoon, and the noise of outliers was filtered. Therefore, it is expected that DINEOF is useful to reconstruct the missing images, also it is considered that it is able to use as basic data for monitoring the ocean environment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.419-429
• /
• 2021

This study examined the differentiation and influence of socio-demographic factors that affect the daily living ability of the elderly living in urban and rural areas. The research data is 「Korean Social Life, Health and Aging Project」. The analysis target was 400 urban elderly people (K-gu, Seoul: surveyed Apr. ~ Jun. 2017) and 524 rural elderly people (B-myeon, Gyeonggi-do: surveyed Dec. 2015 ~ Feb. 2016). The research methods included descriptive statistical analysis, chi-square test through cross-analysis, correlation analysis, and logit analysis. The summary of the research results is as follows. First, the ratio of 'complete independence' in ADL/IADL was 'ADL(city)> ADL(rural)> IADL(city)> IADL(rural)". Second, the probability that the elderly living in rural areas will experience a lower ADL level and lower IADL level was 7.1 times and 3.25 times higher than that of the urban elderly. Lastly, the statistically significant variable affecting the ADL level of urban elderly was depression, and the IADL level was gender, age, economic activity, spouse presence, and depression. Age and economic activity were statistically significant variables for the ADL level of the rural elderly, and the IADL level was gender, age, and economic activity.

• Korean Journal of Environment and Ecology
• /
• v.32 no.6
• /
• pp.618-638
• /
• 2018

This study examined the vegetation structure in the ridge of the Hannamgeumbuk-Jeongmaek and Geumbuk-Jeongmaek by selecting 7 sites(2 sites at Hannamgeumbuk-Jeongmaek and 5 sites at Geumbuk-Jeongmaek) in consideration of the environmental conditions and artificial influences and conducting the vegetation survey in the selected sites. The community classification based on TWINSPAN categorized the vegetation at Hannamgeumbuk-Jeongmaek into 8 groups: Quercus variabilis-Q. acutissima community, Pinus densiflora-Q. mongolica community, Pinus densiflora community, P. densiflora-Q. mongolica-Q. variabilis community, P. densiflora-Deciduous oaks community, P. koraiensis community, Q. mongolica-Q. variabilis community, and Larix kaempferi-P. koraiensis community. It also categorized the vegetation at Geumbuk-Jeongmaek into 9 groups: Quercus variabilis community, Deciduous broad-leaved community, Q. mongolica community, Pinus densiflora-Q. mongolica-Q. variabilis community, Q. acutissima community, P. densiflora-Q. acutissima-Q. variabilis community, P. densiflora-Q. mongolica-P. rigida community, P. densiflora-P. thunbergii-Deciduous oaks community, and P. koraiensis community. Two species, Quercus mongolica and Pinus densiflora, which are widely distributed in the ridges of the Jeongmaeks and Baekdudaegan in South Korea, were dominant in many of the surveyed sites. The appearance of planted Castanea crenata in some plots, although not in high population, suggests human intervention in most regions of the Hannamgeumbuk-Jeongmaek and Geumbuk-Jeongmaek in the past. The Gayasan area, which is part of the Geumbuk-Jeongmaek and where the maritime climate and continental climate overlap, showed Pinus thunbergii, reflecting the local climate characteristics.

• Korean Journal of Environment and Ecology
• /
• v.32 no.6
• /
• pp.582-590
• /
• 2018

Although there are many studies of the effect of climate change on the breeding phenology and community diversity of amphibians, the studies of variations in reproductive population size of individual species according to climate change are still lacking. We examined the effect of climate change on the reproductive population size of Rana huanrenensis and Hynobius leechii, which bred in mountain valleys, by surveying the reproductive population of the two species between 2005 and 2012 and analyzing the correlation between the variation of the outdoor population and the surrounding climate change factors, obtained from a meteorological observatory located at 5.6 km from the study site. The size of the reproductive population of the two species commonly fluctuated with aan pproximately 3.5-year cycle. That of H. leechii, in particular, decreased significantly over eight years. The air temperature tended to more closely relate with the reproductive population size of R. huanrenensis as was the case of the precipitation with that of H. leechii. The yearly mean highest temperature and spring mean temperature variation consistently decreased over the eight years, and the latter was related with the significantly decreased size of H. leechii reproductive population. These results showed that recent climate change directly could affect the reproductive population size of amphibians, particularly H. leechii, which breeds in mountain valleys.

• Korean Journal of Family Social Work
• /
• no.56
• /
• pp.197-224
• /
• 2017

The purpose of this study was to examine how various dimensions of social exclusion experienced by married immigrant women are affected longitudinally. Autoregressive cross-lagged analysis between sub-dimensions of social exclusion of married immigrant women was conducted to investigate the direction of interrelationships. The data were collected each year through a three-wave longitudinal survey from 2011 to 2013. The results showed that statically significant autoregressive effects appeared among economic exclusion, community exclusion, educational exclusion, and ethnic exclusion. The cross-lagged effects of the sub-dimensions of social exclusion showed that married immigrant women with higher levels of the economic exclusion tend to experience higher levels of the educational exclusion, and ethnic exclusion at the later measurement point, even when controlling for their previous level of social exclusion. It was found that economic exclusion as a more fundamental precedent factor positively predicted other dimensions of social exclusion. The results suggested that financial support and job-related services should be strengthened for active social inclusion of married immigrant women, and early intervention to prevent chronicization of social exclusion should be needed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.82-92
• /
• 2019

The purpose of this study was to analyze the relationship and degree of agreement between the six types of Geometry Psychological Assessment (GEOPIA) and four functions of the Myers-Briggs Type Indicator (MBTI) personality test, and to investigate the appropriate level of vocational aptitude commonly recommended by each tool. A total of 377 adult men and women from Korea, aged between 19 and 70 years, were tested using GEOPIA and the MBTI. Cronbach's alpha was calculated to verify the validity and reliability of the measuring tools, and the mean and standard deviation of each variable were calculated. Also, a cross-sectional analysis was conducted to examine the relationship between GEOPIA and the MBTI. The results showed that Round/Triangle (RT) types, Round/Box (RB) types, Triangle/Box (TB) types and Box/Curve (BC) types among the GEOPIA personality types are highly related to MBTI's Sensing/Thinking (ST) types. GEOPIA RC types were related to Intuition/Feeling (NF) and Sensing/Feeling (SF) types, and TC types were highly related to Intuition/Thinking (NT) types. Based on the common characteristics of the two tests, the findings suggest appropriate levels of vocational aptitude. Through this research, it was confirmed that GEOPIA (a Korean psychology and personality test) can be used in counseling, coaching, and education, and above all, is a reliable tool for vocational psychological assessment to search for career aptitude.