• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.2
• /
• pp.64-77
• /
• 2021

The purpose of this study is to examine the spatial distribution of highly educated human capital and to identify key factors affecting their spatial distribution. We analyzed the spatial concentration and inequality using Gini's coefficient and exploratory spatial data analysis and identified the economic and amenity factors to affect the spatial concentration of highly educated human capital using spatial regression model. The findings show that the spatial pattern of highly educated human capital is concentrated, imbalanced, and clustered in Capital region and part of Chungcheong and Gangwon region. The spatial concentration were more affected by economic factor than by amenity factors. This study provides some implication on the regional economic strategies to attract the human capital.

• The Southeast Asian review
• /
• v.28 no.3
• /
• pp.43-74
• /
• 2018

There was few research dealing with the cultural property or the arts of Southeast Asia before, however many articles and books on the arts of Southeast Asia were published since 2008. There are more than 50 papers dealing Southeast Asian art during the period. It was Vietnamese ceramics and the Buddhist relics of Indonesia which paid attention among those articles. This was relevant to the launching of the Humanities Korea (HK) project by the National Research Foundation in 2007. A study on Southeast Asian arts from each of eleven countries is difficult to achieve outstanding results in a short period of time. Since art historical approach is quite a professional field, the growth of research is limited. Since art historical approach is a professional field, the growth of research is limited. At this point we can say the research on Southeast Asian art are developed in an unbalanced extent in the limited area focused on ceramics and sculptures. Over the past decade, the research on Southeast Asian art has developed, but we still need more experts in specific regions and fields. For establishing the art history as a field of regional studies, it is imperative to cultivate specialists in each region for the profound and balanced understanding the value of Southeast Asian art.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.1
• /
• pp.415-442
• /
• 2021

This study analyzed YouTube beauty videos that focus on makeup for teens, based on the assumption that the main viewers of the videos are teens. Through looking at the interaction between beauty information providers and receivers, communication among information receivers, and the way people participate in comment thread, the study examined how teens engage in social media. Many teens who posted comments on YouTube beauty videos praised and envied the beauty of beauty gurus, and tried to connect with them. The comment thread shows that teens answered to each other's questions on makeup tips, shared thoughts and experiences on issues around teen wearing makeup, which helped them build a sense of community, and broaden their views on the way of life. Also observed was power dynamics among youth, such as lecturing or verbal abuse against children and pre-teens by older teens.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.295-305
• /
• 2021

In this study, we constructed using Random Forest(RF) by selecting the meteorological factors related to the occurrence of frost. As a result, when constructing a classification model for frost occurrence, even if the amount of data set is large, the imbalance in the data set for development of model has been analyzed to have a bad effect on the predictive power of the model. It was found that building a single integrated model by grouping meteorological factors related to frost occurrence by region is more efficient than building each model reflecting high-importance meteorological factors. Based on our results, it is expected that a high-accuracy frost occurrence prediction model will be able to be constructed as further studies meteorological factors for frost prediction.

• Journal of the Economic Geographical Society of Korea
• /
• v.25 no.1
• /
• pp.41-59
• /
• 2022

Does the industrial complex of Korea leading the growth in manufacturing industry play the role of intensifying agglomeration effects? To answer this question, this study empirically analyzes the moderating effects of industrial complex on the relation between agglomeration externalities and regional productivity, which has not been covered by previous researches. To do so, analysis of panel data has been conducted using the regional level data for the period of 2010 to 2019. Empirical results are provided at different levels including the whole country, capital region and non-capital region. As a result, it was found that in non-capital region, environments to strengthen positive agglomeration externalities stemming from specialization and diversity in manufacturing through industrial complex whithin the region are built up. However, moderating effects of industrial complex is quite limited in capital region. This implies that the role of industrial complex needs to be importantly reconsidered in the perspective of maximization of agglomeration effects in manufacturing, revitalization of non-capital area and manufacturing innovation.

• Journal of the Korean Regional Science Association
• /
• v.38 no.1
• /
• pp.33-44
• /
• 2022

Over the past decades there has been an increasing demand for decentralization in order to promote the balanced regional growth in South Korea. However, several previous studies have raised concerns regarding the disparity between municipalities as the deviation of power from central government could give wealthy municipalities a clear advantage. The purpose of this study is to better understand the relationship between decentralization and balanced regional growth by examining the Great Heisei consolidation in Japan trying to enact largescale municipal restructuring in association with the promotion of decentralization. In particular, much attention is to be paid to the fact that Japanese central clearly understand the municipalities with small population size could be in a disadvantageous position during the decentralization process so that it has a policy of encouraging mergers to make the municipal system more efficient. Lessons from the case study are summarized in this study in relation to the South Korea's efforts towards the decentralization.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.65-76
• /
• 2022

Recently, not only traditional statistical techniques but also machine learning algorithms have been used to make more accurate bankruptcy predictions. But the insolvency rate of companies dealing with financial institutions is very low, resulting in a data imbalance problem. In particular, since data imbalance negatively affects the performance of artificial intelligence models, it is necessary to first perform the data imbalance process. In additional, as artificial intelligence algorithms are advanced for precise decision-making, regulatory pressure related to securing transparency of Artificial Intelligence models is gradually increasing, such as mandating the installation of explanation functions for Artificial Intelligence models. Therefore, this study aims to present guidelines for eXplainable Artificial Intelligence-based corporate bankruptcy prediction methodology applying SMOTE techniques and LIME algorithms to solve a data imbalance problem and model transparency problem in predicting corporate bankruptcy. The implications of this study are as follows. First, it was confirmed that SMOTE can effectively solve the data imbalance issue, a problem that can be easily overlooked in predicting corporate bankruptcy. Second, through the LIME algorithm, the basis for predicting bankruptcy of the machine learning model was visualized, and derive improvement priorities of financial variables that increase the possibility of bankruptcy of companies. Third, the scope of application of the algorithm in future research was expanded by confirming the possibility of using SMOTE and LIME through case application.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.173-182
• /
• 2022

In this paper, we propose a machine learning model that can prevent fraudulent transactions in advance and interpret them using the XAI approach. For the experiment, we collected a real data set of 12,258 mobile phone sales posts from Joonggonara, a major domestic online C2C resale trading platform. Characteristics of the text corresponding to the post body were extracted using Doc2vec, dimensionality was reduced through PCA, and various derived variables were created based on previous research. To mitigate the data imbalance problem in the preprocessing stage, a complex sampling method that combines oversampling and undersampling was applied. Then, various machine learning models were built to detect fraudulent postings. As a result of the analysis, LightGBM showed the best performance compared to other machine learning models. And as a result of SHAP, if the price is unreasonably low compared to the market price and if there is no indication of the transaction area, there was a high probability that it was a fraudulent post. Also, high price, no safe transaction, the more the courier transaction, and the higher the ratio of 0 in the price also led to fraud.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.99-104
• /
• 2022

Artificial intelligence is getting a crucial part of our lives with its incredible benefits. Machines outperform humans in recognizing objects in images, particularly in classifying people into correct age and gender groups. In this respect, age and gender classification has been one of the hot topics among computer vision researchers in recent decades. Deployment of deep Convolutional Neural Network(: CNN) models achieved state-of-the-art performance. However, the most of CNN based architectures are very complex with several dozens of training parameters so they require much computation time and resources. For this reason, we propose a new CNN-based classification algorithm with significantly fewer training parameters and training time compared to the existing methods. Despite its less complexity, our model shows better accuracy of age and gender classification on the UTKFace dataset.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.313-318
• /
• 2022

The feedback voltage detection structure is proposed to alleviate overshoot and undershoot caused by the removal of the existing external output capacitor. Conventional LDO regulators suffer from overshoot and undershoot caused by imbalances in the power supply voltage. Therefore, the proposed LDO is designed to have a more improved transient response to form a new control path while maintaining only the feedback path of the conventional LDO regulator. A new control path detects overshoot and undershoot events in the output stage. Accordingly, the operation speed of the pass element is improved by charging and discharging the current of the gate node of the pass element. LDO regulators with feedback voltage sensing architecture operate over an input voltage range of 3.3V to 4.5V and have a load current of up to 200mA at an output voltage of 3V. According to the simulation result, when the load current is 200mA, it is 73mV under the undershoot condition and 61mV under the overshoot condition.