• Economic and Environmental Geology
• /
• v.52 no.2
• /
• pp.199-212
• /
• 2019

In the machine learning techniques, the sampling strategy of the training data affects a performance of the prediction model such as generalizing ability as well as prediction accuracy. Especially, in landslide susceptibility analysis, the data sampling procedure is the essential step for setting the training data because the number of non-landslide points is much bigger than the number of landslide points. However, the previous researches did not consider the various sampling methods for the training data. That is, the previous studies selected the training data randomly. Therefore, in this study the authors proposed several different sampling methods and assessed the effect of the sampling strategies of the training data in landslide susceptibility analysis. For that, total six different scenarios were set up based on the sampling strategies of landslide points and non-landslide points. Then Random Forest technique was trained on the basis of six different scenarios and the attribute importance for each input variable was evaluated. Subsequently, the landslide susceptibility maps were produced using the input variables and their attribute importances. In the analysis results, the AUC values of the landslide susceptibility maps, obtained from six different sampling strategies, showed high prediction rates, ranges from 70 % to 80 %. It means that the Random Forest technique shows appropriate predictive performance and the attribute importance for the input variables obtained from Random Forest can be used as the weight of landslide conditioning factors in the susceptibility analysis. In addition, the analysis results obtained using specific sampling strategies for training data show higher prediction accuracy than the analysis results using the previous random sampling method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.633-642
• /
• 2021

Growing demand for electricity, when combined with the need to limit carbon emissions, drives a huge increase in renewable energy industry. In the electric power system, electricity supply always needs to be balanced with electricity demand and network losses to maintain safe, dependable, and stable system operation. There are three broad challenges when it comes to a power system with a high penetration of renewable energy: transient stability, small signal stability, and frequency stability. Transient stability analyze the system response to disturbances such as the loss of generation, line-switching operations, faults, and sudden load changes in the first several seconds following the disturbance. Small signal stability refers to the system's ability to maintain synchronization between generators and steady voltages when it is subjected to small perturbations such as incremental changes in system load. Frequency stability refers to the ability of a power system to maintain steady frequency following a severe system upset resulting in significant imbalance between generation and load. In this paper, we discusses these stability using system simulation by renewable energy deployment plan, and also analyses the influence of the renewable energy sources to the grid stability.

• Korean Journal of Plant Resources
• /
• v.35 no.5
• /
• pp.675-685
• /
• 2022

A comparative analysis was performed on the soil chemical properties of greenhouse or open field where flower crops were grown from 2018 to 2020. The pH of greenhouse soils was kept slightly higher than the optimum range suggested by Rural Development Administration and that of open field soils was maintained within the optimum range for three years. The contents of organic matter (OM) were within the optimum range without significant change every year in both soils. Available phosphate (Av. P₂O₅) of greenhouse soils was the highest at 560 mg/kg in 2018, but it decreased every year and fell within the appropriate range in 2020. The concentration of Av. P₂O₅ in open field soils have fluctuated for three years, not showing a significant difference. Electrical conductivity (EC) of greenhouse soils was higher every year than the standard, 2.0 dS/m, but EC of open field soils remained below the standard. The contents of exchangeable cations were higher than the standard, showing significant differences among the years in greenhouse soils. In open field soils, other cations except exchangeable K⁺ were maintained higher than the optimal level and only Ca²⁺ showed a significant difference among the years. In Pearson correlation matrices, the value of exchangeable Ca²⁺ had a significantly positive correlation with exchangeable Mg²⁺ content at both greenhouse and open field soils. Based on principal component analysis, the soils of greenhouse were distributed within the range of high concentrations of Av. P₂O₅, EC and exchangeable cations, while the soils of open field were characterized by low contents of OM and exchangeable cations. Therefore, it is essential to lower the concentration of exchangeable cations in greenhouse soils. It is common for the soils of open field to have a low OM content, so that organic fertilizers should be more actively applied to the soils in open field.

• Land and Housing Review
• /
• v.14 no.3
• /
• pp.17-36
• /
• 2023

This research aims to investigate the socio-demographic, financial, and housing statuses of young married couples in Chonsei housing and to analyze the determinants of their residential environment quality and housing expenditure in four districts - Seoul and Gyeonggi-Incheon Area(GIA) of the Seoul Metropolitan Area(SMA), and metropolises and non-metropolises of non-SMA. From the 2020 Korean Housing Survey(KHS), this cross-sectional analysis examined a sample of 691 households, and the findings revealed that most were headed by college-educated, salaried male workers aged 31 years old. While childless dual-earner couples were common in Seoul, single-income families of three were prevalent in non-SMA. The financial status of the couples in Seoul was a lot better than in the other three areas, particularly much higher in Chonsei deposit and total asset value. Further, many lived in a three-bedroom apartment unit sized 60m² and bigger, using a Chonsei loan. Regardless of areas, almost all the households spent a very low portion of their living expenses and income on housing costs. However, dual-earner families positively increased borrowing capacity, which improves the household's financial position that is likely to lead to equity increment in a volatile asset market in the long run. The statistical results indicated that residential environment assessment was influenced by neighborhood quality and housing expenditure was affected by housing size in Seoul, urban amenities in GIA and householder's gender in non-metropolises. Thus, this research proposes that strong measures be considered to mitigate housing inequality embedded in geographical and socio-economic disparities.

• Journal of International Area Studies (JIAS)
• /
• v.13 no.1
• /
• pp.135-156
• /
• 2009

The two waves of EU enlargement in 2004 and 2007, have been milestones of European integration. While research has been conducted into the impact of these events on both the European and the global economies,1 there have been few attempts to assess the effects of EU enlargement and the introduction of the euro on countries such as Russia, which neighbour the EU but currently have no perspective of accession. This paper aims to provide an assessment of the effects that EU enlargement and the introduction of the euro have had on Russia, the largest country neighbouring the EU. In particular, it focuses on trade and investment links between the EU and Russia, as well as the use of the energy by Russian residents and authorities. Economic links between Russia and the EU are found to have strengthened considerably in the areas of trade, investment and other financial flows in recent years. Strong growth, particularly in Russia, as well as the high price of oil and gas, Russia's major export items, has facilitated this expansion of trade and finance. Moreover, available data do not suggest that EU enlargement has had a negative impact on Russia in terms of trade or investment diversion. Thus, the strategic partnership between Russia and the EU has been increasingly underpinned by an expansion of cross-border economic activities. Thus, the paper contributes to two broad strands of literature on this subject, namely the impact of regional trade and economic arrangements on non-member countries and the international role of currencies.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.47-56
• /
• 2024

This paper proposes a method for fine-tuning BERT-based natural language processing models to perform sentiment analysis on Korean review data. By varying the input sequence length during this process and comparing the performance, we aim to explore the optimal performance according to the input sequence length. For this purpose, text review data collected from the clothing shopping platform M was utilized. Through web scraping, review data was collected. During the data preprocessing stage, positive and negative satisfaction scores were recalibrated to improve the accuracy of the analysis. Specifically, the GPT-4 API was used to reset the labels to reflect the actual sentiment of the review texts, and data imbalance issues were addressed by adjusting the data to 6:4 ratio. The reviews on the clothing shopping platform averaged about 12 tokens in length, and to provide the optimal model suitable for this, five BERT-based pre-trained models were used in the modeling stage, focusing on input sequence length and memory usage for performance comparison. The experimental results indicated that an input sequence length of 64 generally exhibited the most appropriate performance and memory usage. In particular, the KcELECTRA model showed optimal performance and memory usage at an input sequence length of 64, achieving higher than 92% accuracy and reliability in sentiment analysis of Korean review data. Furthermore, by utilizing BERTopic, we provide a Korean review sentiment analysis process that classifies new incoming review data by category and extracts sentiment scores for each category using the final constructed model.

• Journal of Nutrition and Health
• /
• v.43 no.5
• /
• pp.513-523
• /
• 2010

The food and nutrient intakes on weekdays and weekends was examined with 196 high school girls residing in Seoul using the 3-day food record. Frequency for skipping breakfast was higher than that for lunch and dinner. Frequencies for skipping breakfast and lunch were significantly higher on weekends than on weekdays (p < 0.05). The daily average food, vegetable food, and animal food intakes were 1,074.8 g, 680.0 g, and 317.3 g, respectively. The total food and vegetable food intakes on weekdays were significantly higher than on weekends (p < 0.05). The daily average dietary variety score (DVS) was 20.5, and was significantly higher on weekdays (23.3) than on weekends (15.1)(p < 0.05). The daily averages of energy, protein, fat and carbohydrate intake were 1,732.9 kcal, 68 g, 56.2 g, and 240.9 g, respectively. Energy, protein, carbohydrate, phosphate, iron, sodium, potassium, thiamin, niacin, folate and vitamin C intakes were significantly higher on weekdays than on weekends (p < 0.05). Fat intake was significantly lower on weekdays than on weekends (p < 0.05). The daily average percentages of energy intake from carbohydrate, protein, and fat were 55.4%, 15.6%, and 29.0%: 56.1%, 15.8%, and 28.2% on weekdays and 54.7%, 15.3%, and 30.1% on weekends, respectively. The percentages of energy intake from carbohydrate on weekdays and weekends were below 60%, and that from fat was above 28% on weekdays and weekends. The daily averages of energy, vitamin A, riboflavin, niacin and phosphate intake were above 80% as compared with the estimated energy requirement (EER) or the recommended intake (RI). The intakes of calcium, potassium and folate were below 50% as compared with the adequate intake (AI) or (RI). The daily average mean adequacy ratio (MAR), an index of overall dietary quality, was 0.77, and significantly high school girls was worse on weekends than on weekdays.

• Korean Journal of Soil Science and Fertilizer
• /
• v.43 no.2
• /
• pp.160-165
• /
• 2010

To reduce the dose of fertilizers is very important to sustainable production of many horticultural crops, including strawberry. In order to practice the environment friendly agriculture of strawberry cultivation in plastic film house, soil chemical properties of 435 soil samples (232 for loam, 83 for sandy loam, and 120 for silt loam) in Chungnam Province from2008 to 2009 were determined. The average of pH, EC, OM, Av. $P_2O_5$, Ex. $K^+$, Ex. $Ca^{2+}$, Ex. $Mg^{2+}$, and Ex. $Na^+$ was 6.5, 2.28 dS $m^{-1}$, 26 g $kg^{-1}$, 910 mg $kg^{-1}$, 1.09 $cmol_c\;kg^{-1}$, 8.3 $cmol_c\;kg^{-1}$, 2.5 $cmol_c\;kg^{-1}$, and 0.58 $cmol_c\;kg^{-1}$, respectively. The content of Av. $P_2O_5$ in sandy loam soil was significantly higher than silt loam soil, whereas other properties showed no difference between soil texture. The kinds of strawberry cultivars showed no difference in soil chemical properties. The frequency distribution within optimum range of soil chemical properties was 30.6%, 35.4%, 37.0%, 5.3%, 8.5%, 8.5%, and 17.9% for pH, EC, OM, Av. $P_2O_5$, Ex. $K^+$, Ex. $Ca^{2+}$, and Ex. $Mg^{2+}$, respectively. Especially, excessive portion of Av. $P_2O_5$, and Ex. $Ca^{2+}$ were high 86.9%, and 86.0%, respectively. EC values of soil samples were significantly positive correlatoin with all chemical properties except soil pH. In principle component analysis of chemical properties in soil samples, the percentage of variance explained by PC 1 was 38.8%, while PC 2 explained 17.8%of the variance, for a cumulative total of 56.6%. These results were able to distinguish between soil textures and strawberry cultivars. Also, these results considered that understanding of soil chemical properties under using principal component analysis be able to improve amounts of fertilizers for sustainable agriculture in plastic film house.

• Korean Journal of Soil Science and Fertilizer
• /
• v.43 no.2
• /
• pp.153-159
• /
• 2010

Nowadays, Korean farmers rely more on chemical fertilizers than low input sustainable agriculture drawn from the farm itself. In order to improve soil nutritional imbalance for environment friendly agriculture in greenhouse, we have carried out a relationship between fertilizer application level, and soil chemical properties for strawberry cultivation at 56 sites in Chungnam Province. Average amount of nitrogen as basal fertilization was 92.3 Mg $ha^{-1}$ which higher 2.6 times compared to standard amount of basal fertilizer. In case of compost application more than 30 Mg $ha^{-1}$, excessive ratio compared to optimum level was higher 1.8 times for EC value, 3.0 times for available phosphate, 2.6 times for exchangeable potassium, 1.7 times for exchangeable calcium, and 1.6 times for exchangeable magnesium, respectively. Amounts of compost application significantly correlated with available phosphate (r=0.370, $p{\leq}0.01$), exchangeable potassium(r=0.429, $p{\leq}0.01$), exchangeable calcium(r=0.404, $p{\leq}0.01$), exchangeable magnesium(r=0.453, $p{\leq}0.01$), and exchangeable sodium(r=0.369, $p{\leq}0.01$), respectively. Our results suggest that soil nutrients management for sustainable agriculture was optimum fertilization based on soil testing for strawberry cultivation in greenhouse.

• Journal of Bio-Environment Control
• /
• v.26 no.1
• /
• pp.7-12
• /
• 2017

This experiment was conducted to analyze the effect of drainage reuse rate on the growth and fruiting of summer paprika in closed hydroponic cultivation. The experiment was carried out for 25 weeks from March to September 2015 with 0, 20, 30, 50% mixing ratio of waste nutrient solution using non - recycling hydroponic cultivation as a control. As a result, stem diameter of the test was different in the groups 1 and 2, but no difference showed as the group progressed more than 3 groups. L.A.I tended to decrease with increasing drainage mixing ratio. The number of nodes in the 50% reuse test group was 1.4 compared to the control group, but there was no significant difference. The number of harvested nodes was significantly different in the control group (11.1 nodes) and the 50% reuse test group (8.7 nodes), and the harvested nodes tended to decrease as the drainage was reused. The ratio of harvest was also the same as that of the harvesting node, and the control was the highest at 33.2% and the lowest at the 50% reuse test at 27.6%. Relative yields were reduced by 30%, 35% and 45% in the control group in the first group, and this tendency was also observed in the second and fourth groups. However, in the 3 and 5 groups, the production of 50% test group increased by 13% and 5%. The ratio of unmarketable fruit was increased 2%, 4%, 4%, and 7% in 0%, 20%, 30% and 50% reuse test, respectively. In conclusion, if the decrease in yield due to the decline in early growth is carefully managed, even if the imbalance of inorganic ions occurs after the mid-term growth, the growth of the crop will enter into a stable period and the re-use will not be worried about the growth and the yield decrease.