• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.367-367
• /
• 2018

전 세계적으로 이상기후에 의한 영향으로 여름철 장마와 같은 우기가 점차 사라지고 집중호우 및 가뭄이 빈번하게 발생하는 등 지하수위 변동성에 따른 물 부족 현상이 발생하고 있다. 특히, 제주특별자치도는 하천수 및 저수지의 수원을 농업용수로 이용하는 내륙지역과는 달리 농업용수의 수원으로 지하수를 이용하고 있어 향후 기후변화로 인한 극단적인 가뭄과 농업형태의 변화등 지하수의 의존도는 가속화 될 전망이다. 따라서, 제주특별자치도는 지하수 관리차원에서 신규관정개발을 최소화 하고 용수공급량의 부족과 불균형을 해소시키기 위하여 2016년부터 농업용수 광역화 사업을 추진하고 있다. 본 연구는 제주특별자치도에서 추진하고 있는 '농업용수 광역화 사업'과 연계하여 용천수를 활용한 농업용 수자원 확보를 위하여 용천수 및 상시하천수의 정량적인 수량파악 및 농업용 수질기준에 적절한 유출수를 선정하고 제주지역 농업용수에 대체수자원을 활용한 지하수 의존비율을 저감시키는데 목표를 두고 수행되었다. 제주특별자치도 서귀포 지역에 분포하고 있는 16개 용천수 및 2개 상시하천을 대상으로 최종 해안으로 유출되는 10개 지점에서 농업용수 활용가능성을 검토한 결과 최소 유량 값은 각 지점별로 속골물 6,313.3($m^3$/일), 조이통물 11,406.3($m^3/day$), 꿩망물 8,402.8($m^3/day$), 선궷내물 4,290.8($m^3/day$), 논짓물 690.8($m^3/day$), 대왕수 1063.0($m^3/day$), 작지물 7,060.4($m^3/day$), 하강물 1,487.6($m^3/day$), 악근천 1,043.6($m^3/day$), 예래천 2,114.4($m^3/day$)로 산정되었으며, 수질 분석에 있어서는 작지물을 제외한 9개 지점에서 농업용수 사용 기준을 충족 하였다. 이상의 결과는 향후 제주특별자치도의 농업용수 공급량의 부족과 불균형 해소 및 지하수 관리차원의 신규관정 개발을 최소화 하는데 보탬이 될 것으로 판단된다.

• Journal of the Economic Geographical Society of Korea
• /
• v.21 no.4
• /
• pp.321-334
• /
• 2018

There are many factors that cause uneven regional developments in the country and one of main factors is outflow of regional income or products. The purpose of this study is to analyze regional production runoff by comparing GRDP and GRNI in basic local governments level. In this study, GRNI of basic local governments are estimated by local income tax data, The results of the study are as follows. Firstly, GRNI is more concentrated than GRDP. The analysis of Moran I showed that the spatial autocor-relation of GRNI is more distinct than that of GRDP. Local Moran I analysis shows that spatial hot spots and cold spots are more apparent in GRNI than GRDP. Secondly, the outflows of GRDP into a small number of regions are apparent. In about 80% of basic local governments, the net outflows of GRDP occur. The large net outflow regions are cities where manufacturing industry has developed and in the 20 lowest net outflow rate regions, 70-80% of GRDP outflows. The large net inflow regions are metropolitan area in Seoul and large local cities. Seocho-gu, Yongsan-gu, and Gangnam-gu in Seoul have a large net inflows and net inflow rates are over 90% of GRDP.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.331-337
• /
• 2023

In this paper, we propose a deep learning model to detect lumbar 3 (L3) CT images to determine the occurrence and degree of sarcopenia. In addition, we would like to propose an optimization technique that uses oversampling ratio and class weight as design parameters to address the problem of performance degradation due to data imbalance between L3 level and non-L3 level portions of CT data. In order to train and test the model, a total of 150 whole-body CT images of 104 prostate cancer patients and 46 bladder cancer patients who visited Gangneung Asan Medical Center were used. The deep learning model used ResNet50, and the design parameters of the optimization technique were selected as six types of model hyperparameters, data augmentation ratio, and class weight. It was confirmed that the proposed optimization-based L3 level extraction model reduced the median L3 error by about 1.0 slices compared to the control model (a model that optimized only 5 types of hyperparameters). Through the results of this study, accurate L3 slice detection was possible, and additionally, we were able to present the possibility of effectively solving the data imbalance problem through oversampling through data augmentation and class weight adjustment.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2018

The study is based on machine learning techniques to increase the accuracy of the forest fire predictive model. It used 14 years of data from 2003 to 2016 in Gang-won-do where forest fire were the most frequent. To reduce weather data errors, Gang-won-do was divided into nine areas and weather data from each region was used. However, dividing the forest fire forecast model into nine zones would make a large difference between the date of occurrence and the date of not occurring. Imbalance issues can degrade model performance. To address this, several sampling methods were applied. To increase the accuracy of the model, five indices in the Canadian Frost Fire Weather Index (FWI) were used as derived variable. The modeling method used statistical methods for logistic regression and machine learning methods for random forest and xgboost. The selection criteria for each zone's final model were set in consideration of accuracy, sensitivity and specificity, and the prediction of the nine zones resulted in 80 of the 104 fires that occurred, and 7426 of the 9758 non-fires. Overall accuracy was 76.1%.

• Microbiology and Biotechnology Letters
• /
• v.50 no.1
• /
• pp.135-146
• /
• 2022

Obesity is closely associated with profound dyslipidemia, insulin resistance, and fatty liver disease. Recent reports have suggested that alterations in gut microbiota can be linked to diet-induced obesity. In this study, the anti-obesity effects of Weissella confusa WIKIM51 isolated from kimchi were investigated, as evidenced by: i) reduced lipid accumulation and downregulated adipogenesis-related genes in 3T3-L1 adipocytes; ii) suppressed gains in body weight and epididymal fat mass; iii) reduced serum lipid levels, for example, triglyceride and total cholesterol; iv) increased serum adiponectin levels and reduced serum leptin levels; v) downregulated lipogenesis and upregulated β-oxidation-related genes in the epididymal fat; and vi) altered microbial communities. The collective evidence indicate the potential value of W. confusa WIKIM51 as a functional food supplement for the prevention and amelioration of obesity.

• Ecology and Resilient Infrastructure
• /
• v.10 no.4
• /
• pp.107-115
• /
• 2023

High turbidity in source water can have adverse effects on water treatment plant operations and aquatic ecosystems, necessitating turbidity management. Consequently, research aimed at predicting river turbidity continues. This study developed a multi-class classification model for prediction of turbidity using LightGBM (Light Gradient Boosting Machine), a representative ensemble machine learning algorithm. The model utilized data that was classified into four classes ranging from 1 to 4 based on turbidity, from low to high. The number of input data points used for analysis varied among classes, with 945, 763, 95, and 25 data points for classes 1 to 4, respectively. The developed model exhibited precisions of 0.85, 0.71, 0.26, and 0.30, as well as recalls of 0.82, 0.76, 0.19, and 0.60 for classes 1 to 4, respectively. The model tended to perform less effectively in the minority classes due to the limited data available for these classes. To address data imbalance, the SMOTE (Synthetic Minority Over-sampling Technique) algorithm was applied, resulting in improved model performance. For classes 1 to 4, the Precision and Recall of the improved model were 0.88, 0.71, 0.26, 0.25 and 0.79, 0.76, 0.38, 0.60, respectively. This demonstrated that alleviating data imbalance led to a significant enhancement in Recall of the model. Furthermore, to analyze the impact of differences in input data composition addressing the input data imbalance, input data was constructed with various ratios for each class, and the model performances were compared. The results indicate that an appropriate composition ratio for model input data improves the performance of the machine learning model.

• Journal of Bio-Environment Control
• /
• v.8 no.1
• /
• pp.42-48
• /
• 1999

This study was executed to see the effects of Ca : K ratios in me.L$^{-1}$ -0:9, 1.5:7.5, 3:6, 4.5:4.5, 6:3 - in the nutrient solution on the photosynthesis, transpiration, growth and incidence of tipburn in butterhead ‘Omega’and Leaf ‘Grand Rapids’lettuce (Lactuca sativa. L) grown in nutrient film technique(NFT). The photosynthesis of both lettuces showed high in the Ca : K ratios of 3:6 and 4.5:4.5 regardless of species. But stomatal resistance of Grand Rapids was higher than that of Omega. The highest transpiration rate of them was shown in the Ca : K ratio of 3:6. The transpiration rate of developing leaves was lower than that of expanded leaves. It was seemed to have relation with incidence of tipbum in the developing leaves. The nutrient solution treatment without Ca developed less growth than that of other treatments, especially growth and development of apical part were inhibited, so that in the both of them incidence of tipburn appeared 100 percent. The incidence of tipburn in Omega appeared 25 percent in the Ca/K ratio of 1.5:7.5, but Grand Rapids did not show it according to the Ca/K ratio in nutrient solution. The highest growth in two species was also shown in the Ca/K ratio of 3:6 except nutrient solution without Ca. This study suggested that the unbalanced ratio of Ca/K affected Ca transport in two species because of the increase of stomatal resistance and diffusive resistance and the decrease of photosynthesis and transpiration.

• Management & Information Systems Review
• /
• v.34 no.3
• /
• pp.101-123
• /
• 2015

Amidst the growing uncertainty in external environments, securing and retaining superior human resources is becoming emphasized as a key means for organizations to achieve competitive advantages. Particularly, star employees-human resources that are characterized by their ability to create extraordinary performance relative to other peers-are increasingly gaining attention in both academia and industry because of its importance in knowledge-based industries. However, despite the prevailing recognition for star employees, few previous literature have attempted to empirically test the direct relationship between the ratio of star employees in an organization and organizational performance. Considering both the potential for positive and negative influence of star employees on organizations, the relationship between the ratio of star employees and organizational performance can not only be a simple linear relationship but can also exist in a curvilinear form. Building on the existing literature on star employees, this paper establishes competing hypotheses for the two possibilities of curvilinear relationship; as the ratio of star employees increases, marginal effects can either increase (i.e., U-shaped curvilinear relationship) or decrease (i.e., inverted U-shaped curvilinear relationship). Employing an unbalanced panel data of 35 Korean brokerage firms between years 2008 and 2013 with 134 observations, the relationship between the ratio of best analysts (i.e. star employees) as selected by Maeil Business Newspaper and financial performance (i.e. organizational performance) of corresponding brokerage firms is examined. Empirical results indicate that while organizational performance increases as the ratio of star employees increases, its positive effect diminishes over time which provides support for the curvilinear relationship with decreasing marginal effects. Our research findings imply that star employees create value in knowledge-based industries; at the same time, implications are given as results calls for caution for excessive dependence on star employees beyond a certain level.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Journal of Korean Society of Transportation
• /
• v.36 no.3
• /
• pp.195-202
• /
• 2018

Jobs-housing balance refers to the situations where the employment (work) and housing (house) opportunity are coincided in certain geographical area. This paper aims to examine the impact of jobs-housing balance to traffic safety. In pursuing the above, this paper particularly focuses on modeling the traffic accidents by metropolitan area. The main results are as follows. First, three generalized linear models which are all statistically significant are developed. Jobs-housing balance factors are judged to significantly influence on traffic accidents in all models. Second, among common variables, the housing supply rate is analyzed to impact to decreasing, and economically active population and commuting trip attraction are analyzed to impact to increasing. Hence, the alleviation of jobs-housing mismatch is evaluated to be important. Finally, the jobs-housing and business trip rates in Seoul metropolitan area, and the cross-commuting rate in Busan-Ulsan metropolitan area are judged to be essential to transportation safety policies