• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.237-262
• /
• 2022

There has been a growing interest in IPOs (Initial Public Offerings) due to the profitable returns that IPO stocks can offer to investors. However, IPOs can be speculative investments that may involve substantial risk as well because shares tend to be volatile, and the supply of IPO shares is often highly limited. Therefore, it is crucially important that IPO investors are well informed of the issuing firms and the market before deciding whether to invest or not. Unlike institutional investors, individual investors are at a disadvantage since there are few opportunities for individuals to obtain information on the IPOs. In this regard, the purpose of this study is to provide individual investors with the information they may consider when making an IPO investment decision. This study presents a model that uses machine learning and text analysis to predict whether an IPO stock price would move up or down after the first 5 trading days. Our sample includes 691 Korean IPOs from June 2009 to December 2020. The input variables for the prediction are three tone variables created from IPO prospectuses and quantitative variables that are either firm-specific, issue-specific, or market-specific. The three prospectus tone variables indicate the percentage of positive, neutral, and negative sentences in a prospectus, respectively. We considered only the sentences in the Risk Factors section of a prospectus for the tone analysis in this study. All sentences were classified into 'positive', 'neutral', and 'negative' via text analysis using TF-IDF (Term Frequency - Inverse Document Frequency). Measuring the tone of each sentence was conducted by machine learning instead of a lexicon-based approach due to the lack of sentiment dictionaries suitable for Korean text analysis in the context of finance. For this reason, the training set was created by randomly selecting 10% of the sentences from each prospectus, and the sentence classification task on the training set was performed after reading each sentence in person. Then, based on the training set, a Support Vector Machine model was utilized to predict the tone of sentences in the test set. Finally, the machine learning model calculated the percentages of positive, neutral, and negative sentences in each prospectus. To predict the price movement of an IPO stock, four different machine learning techniques were applied: Logistic Regression, Random Forest, Support Vector Machine, and Artificial Neural Network. According to the results, models that use quantitative variables using technical analysis and prospectus tone variables together show higher accuracy than models that use only quantitative variables. More specifically, the prediction accuracy was improved by 1.45% points in the Random Forest model, 4.34% points in the Artificial Neural Network model, and 5.07% points in the Support Vector Machine model. After testing the performance of these machine learning techniques, the Artificial Neural Network model using both quantitative variables and prospectus tone variables was the model with the highest prediction accuracy rate, which was 61.59%. The results indicate that the tone of a prospectus is a significant factor in predicting the price movement of an IPO stock. In addition, the McNemar test was used to verify the statistically significant difference between the models. The model using only quantitative variables and the model using both the quantitative variables and the prospectus tone variables were compared, and it was confirmed that the predictive performance improved significantly at a 1% significance level.

• Journal of the Society of Disaster Information
• /
• v.18 no.1
• /
• pp.104-115
• /
• 2022

Purpose: Infrastructure inspection and its diagnostics technique have been rapidly developing recently. Therefore, it is important to secure the reliability of diagnostic equipment, and this paper deals with inspection of diagnostic equipment, introduction to a certification system and development plans for infrastructure. Method: Several certification systems are established and introduction plans are reviewed through experts by synthesizing the contents of certification research for existing infrastructure diagnosis equipment. In addition, the revision of the law for introduction of the system is reviewed, detailed operation regulations are prepared and phased development plans are reviewed, which are based on the operation scenario. Result: Inspection and certification plans were constructed through four routes in order to consider infrastructure inspection and diagnostic equipment in use, and new diagnostic equipment using state-of-the-art technology. Furthermore, market confusion depending on the introduction of a new certification system is minimized and reliability is secured by transforming a simple inspection system in the short term into a formal certification system in the long term. The law amendments according to the introduction of the system were reviewed and detailed operation regulations were developed. Also, phased development plans, which are based on the long-term development scenario including manpower, infrastructure and specifications, were presented. Conclusion: It is important to secure reliability through the distribution and certification of diagnostic equipment using 4th industrial technology to strengthen the safety management of infrastructure at the national level since the infrastructure is various in type and increasingly large in size. It is also essential to train human resources who can use new technology with inspection and diagnosis system in order to enhance the safety management of all infrastructures. Moreover, it is necessary to introduce a regular inspection system for infrastructure that combines loT technology in the long-term point of view and to promote the introduction by giving active incentives to institutions that actively accept it.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.259-278
• /
• 2022

With the spread of Artificial Intelligence (AI), various AI-based services are expanding in the financial sector such as service recommendation, automated customer response, fraud detection system(FDS), credit scoring services, etc. At the same time, problems related to reliability and unexpected social controversy are also occurring due to the nature of data-based machine learning. The need Based on this background, this study aimed to contribute to improving trust in AI-based financial services by proposing a checklist to secure fairness in AI-based credit scoring services which directly affects consumers' financial life. Among the key elements of trustworthy AI like transparency, safety, accountability, and fairness, fairness was selected as the subject of the study so that everyone could enjoy the benefits of automated algorithms from the perspective of inclusive finance without social discrimination. We divided the entire fairness related operation process into three areas like data, algorithms, and user areas through literature research. For each area, we constructed four detailed considerations for evaluation resulting in 12 checklists. The relative importance and priority of the categories were evaluated through the analytic hierarchy process (AHP). We use three different groups: financial field workers, artificial intelligence field workers, and general users which represent entire financial stakeholders. According to the importance of each stakeholder, three groups were classified and analyzed, and from a practical perspective, specific checks such as feasibility verification for using learning data and non-financial information and monitoring new inflow data were identified. Moreover, financial consumers in general were found to be highly considerate of the accuracy of result analysis and bias checks. We expect this result could contribute to the design and operation of fair AI-based financial services.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.49 no.2
• /
• pp.206-216
• /
• 2022

This study aimed to investigate the frequency of dental visits after coronavirus disease 2019 (COVID-19) in children and adolescents in comparison to that of adults. The data on the number of dental visits on the basis of different classification and treatment codes for all the age groups were provided by the Health Insurance Review and Assessment Service from January 2017 to December 2020. To reduce the impact of the population change, dental visits per 1000 people was used. After the start of the pandemic, dental visits per 1000 people decreased in all age groups when analyzed for the diseases of pulp and periapical tissues classification code and dental visits per 1000 people decreased over 5 years age groups when analyzed for the pulp treatment code. Regarding the restorative treatment code, visits in the 0 - 19 years age group decreased after the pandemic. Based on the comparison of the number of confirmed COVID-19 cases to that of monthly dental visits by treatment codes, the change rate of pulp and restorative treatments gradually decreased after the waves of the pandemic in February and August 2020 in Korea. Furthermore, dental visits per 1000 people for gingivitis and periodontal disease classification code increased after the pandemic in all age groups. The rate of decrease in dental visits per 1000 people for restorative treatments in children and adolescents was higher than that in adults. The rate of decrease in the number of dental visits for multi-visit pulp treatments showed a rapid decrease as compared to that of 1-visit pulp treatments after the pandemic. This study identified changes in the number of dental visits of children and adolescents after COVID-19 transmission in comparison to that observed in adults.

• Journal of Life Science
• /
• v.32 no.4
• /
• pp.271-278
• /
• 2022

The detailed mechanism by which cancer upregulated gene 2 (CUG2) overexpression induces cancer stem cell-like phenotypes is not fully understood. The downregulation of FBXW7 E3 ligase, a tumor suppressor known for its proteolytic regulation of oncogenic proteins such as cyclin E, c-Myc, Notch, and Yap1, has been frequently reported in several types of tumor tissues, including those in the large intestine, cervix, and stomach. Therefore, we investigated whether FBXW7 is involved in CUG2-induced oncogenesis. In this study, the decreased expression of FBXW7 was examined in human lung adenocarcinoma A549 (A549-CUG2) and human bronchial BEAS-2B cells (BEAS-CUG2) overexpressing CUG2 and compared with control cells stably expressing an empty vector (A549-Vec or BEAS-Vec). Treatment with MG132 (a proteosome inhibitor) prevented the degradation of FBXW7 and Yap1 proteins, which are substrates of the FBXW7 E3 ligase. To address the role of Fbxw7 in the development of cancer stem cell (CSC) phenotypes, we suppressed Fbxw7 protein levels using its siRNA. We observed that decreased levels of FBXW7 enhanced cell migration, invasion, and spheroid size and number in A549-Vec and BEAS-Vec cells. The enforced expression of FBXW7 produced the opposite results in A549-CUG2 and BEAS-CUG2 cells. Furthermore, the downregulation of FBXW7 elevated the activities of EGFR, Akt, and ERK1/2 and upregulated β-catenin, Yap1, and NEK2, while the enforced expression of FBXW7 generated the opposite results. We thus propose that FBXW7 downregulation induced by CUG2 confers CSC-like phenotypes through the upregulation of both the EGFR-ERK1/2 and β-catenin-Yap1-NEK2 signaling pathways.

• Journal of the Korean earth science society
• /
• v.43 no.1
• /
• pp.91-109
• /
• 2022

The ocean is a significant sink for atmospheric anthropogenic CO₂, absorbing one-third of the total CO₂ emitted by human activities. In return, oceans have experienced significant declines in seawater pH and the aragonite saturation state also called ocean acidification. This study evaluates the distribution of aragonite saturation state, an indicator to assess the potential threat from ocean acidification, by combining newly obtained data from the west coast of South Korea with previous datasets covering the Yellow Sea, East Sea, northern South China Sea, and southeast coast of South Korea. In general, offshore waters absorb atmospheric CO₂; however, most of the collected water samples show aragonite oversaturation. On the southeast coast, the aragonite saturation state was significantly affected by river discharge and associated variables, such as freshwater input with nutrients, seasonal stratification, biological carbon fixation, and bacterial remineralization. In summer, hypoxia and mixing with relatively acidic freshwater made the Jinhae and Gwangyang Bays undersaturated with respect to aragonite, possibly threatening marine organisms with CaCO₃ shells. However, widespread aragonite undersaturation was not observed on the west coast, which receives considerable river water discharge. In addition, occasional upwelling events may have worsened the ocean acidification in the southwestern part of the East Sea. These results highlight the importance of investigating site-specific ocean acidification processes in coastal waters. Along with the above-mentioned seasonal factors, the dissolution of atmospheric CO₂ and the deposition of atmospheric acidic substances will continue to reduce the aragonite saturation state in Korean waters. To protect marine ecosystems and resources, an ocean acidification monitoring program should be established for Korean waters.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.6
• /
• pp.27-36
• /
• 2021

At a time when the equitable use of urban parks is gradually emerging as a social issue, this study was initiated to expand the influence of urban parks by improving the quality of park services, thereby resolving areas not covered by urban park services. This study targeted the Hangang Park in Seoul, where the qualitative service of parks shows the greatest difference. The influence relationship between the qualitative services of the park and the user's sphere of influence, which indicates the distribution of park users, was proposed to assess the influence of improvements in the quality of service. As a research method, the top three districts and the bottom three districts were selected through the Han River Park user satisfaction survey conducted from 2017 to 2019, and a qualitative service evaluation was carried out. It was derived using the data acquired in September. Afterward, by performing a spatial autocorrelation analysis on the user's sphere of influence, additional verification of the user's sphere of influence was performed numerically and visually. As a result of the study, the user influence in the top three districts, with high-quality service, was stronger and wider than that of the lower three districts. It was confirmed that the quality of service of the park affects the user influence. This shows that to realize park equity, it is necessary to improve the quality of services through continuous management and improvement of individual parks and the creation of new parks. This study has significance in that it recognizes the limitations of research on park services from a supplier's point of view and evaluates the qualitative services of parks from the perspective of actual park users. We propose an alternative to deal with the lower the park deprivation index.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.479-490
• /
• 2021

As a part of Korean accounting reforms through the improvement of the accounting and audit related systems, the amendment bill of 'Act on External Audit of Stock Compamies's was passed in the Natinal Assembly plenary session in 2017, the amended act has been enforced except some regulations since the business year on November 1, 2018, and all the amended matters will be applied from the business year of 2024. The reasons for auditor designation in 2019 are 'pre-IPO' 331 companies, 220 periodic designation companies, 197 companies that had operating loss for three consecutive years, 112 companies with issues for administration, 108 companies with excessive debt ratio and 66 companies with no auditors. Regarding the reasons for the increase of auditor designation, 475 companies were increased in accordance with the new designation standard by the amended bill of Act on External Audit of Stock Companies, 114 companies were increased due to the abolition of the considered designation system of companies to be listed, and 90 companies were increased based on the increase of listed companies incorporated to issues for administration. In 2020, 462 companies had periodical designation (434 listed, 28 non-listed), adding 242 companies (110%) over a year. In terms of direct designation, 'pre-IPO' accounted for the most (362 companies), followed by '3 consecutive years of operating loss' (245 companies), then by companies with administration issues (133 companies), and CEO & largest sharholder replacement. Regarding the designation of auditors according to accounting firms in 2020, A group that includes(top 4) accounting firms(Samil, Samjeong, Hanyeong, Anjin) had 526 companies(34.6%), which ia an incease of 72 companies from the previous year(454 companies, 37.1%), but the weight decreased by 2.5%.

• Journal of Ginseng Culture
• /
• v.5
• /
• pp.32-51
• /
• 2023

Because red ginseng was exported in large quantities to the Qing Dynasty in the 19th century, a large-scale ginseng cultivation complex was established in Kaesong. Sibyunje (時邊制), a privately led loan system unique to merchants in Kaesong, made it possible for them to raise the enormous capital required for ginseng cultivation. The imperial family of the Korean Empire promulgated the Posamgyuchik (包蔘規則) in 1895, and this signaled the start of the red ginseng monopoly system. In 1899, when the invasion of ginseng farms by the Japanese became severe, the imperial soldiers were sent to guard the ginseng farms to prevent the theft of ginseng by the Japanese. Furthermore, the stateled compensation mission, Baesanggeum Seongyojedo (賠償金 先交制度), provided 50%-90% of the payment for raw ginseng, which was paid in advance of harvest. In 1895, rising seed prices prompted some merchants to import and sell poor quality seeds from China and Japan. The red ginseng trade order was therefore promulgated in 1920 to prohibit the import of foreign seeds without the government's permission. In 1906-1910, namely, the early period of Japanese colonial rule, ginseng cultivation was halted, and the volume of fresh ginseng stocked as a raw material for red ginseng in 1910 was only 2,771 geun (斤). However, it increased significantly to 10,000 geun between 1915 and 1919 and to 150,000 geun between 1920 and 1934. These increases in the production of fresh ginseng as a raw material for red ginseng were the result of various policies implemented in 1908 with the aim of fostering the ginseng industry, such as prior disclosure of the compensation price for fresh ginseng, loans for cultivation expenditure in new areas, and the payment of incentives to excellent cultivators. Nevertheless, the ultimate goal of Japanese imperialism at the time was not to foster the growth of Korean ginseng farming, but to finance the maintenance of its colonial management using profits from the red ginseng business.

• Journal of Environmental Impact Assessment
• /
• v.32 no.1
• /
• pp.41-48
• /
• 2023

This study was conducted to confirm the possibility of a new carbon stock in the Sejong National Arboretum, a major urban greenspace in Sejong-si. This study involved field and ground surveys of 1,336 trees, including 794 Pinus densiflora trees with a diameter at breast height (DBH) of above 5.5cm, which are the most planted in the Sejong National Arboretum, Chionanthus retusus 154 trees planted, Metasequoia glyptostroboides 216 trees, and Aesculus turbinata 172 trees as street trees. Measurements were performed from April to November. Based on the results of the survey, the carbon storage and annual carbon stock were calculated using the annual carbon stock estimation equation used in the forest carbon offset projects. As a result of comparing the carbon stock of the 12cm diameter class, which is the most distributed of four major trees, it was found in the order of C. retusus (0.0136tC/tree), P. densiflora (0.0126tC/tree), M. glyptostroboides (0.0092tC/tree), and A. turbinata (0.0076tC/tree). In addition, the field survey measurement data compared with terrestrial LiDAR measurement data for 20 trees showed a difference of 10.0cm in tree height and 1.7cm in diameter at breast height (p<0.05). In the future, additional carbon stock and annual uptake of other species planted in the arboretum are expected to promote the carbon uptake effect of the arboretum and contribute to the achievement of the national NDC. In the long term, it is also necessary to develop the carbon uptake factor of trees and shrubs mainly used to calculate the exact carbon uptake amount of trees mainly used in urban forests and gardens.