• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.6
• /
• pp.266-274
• /
• 2022

In this study, a smoothing method was applied to improve the accuracy of peak wave period estimation using the water surface elevation observed from the Oceanographic and Meteorological Observation Tower located on the west coast of the Korean Peninsula. Validation of the application of the smoothing method was per- formed using variance of the surface elevation and total amount wave energy, and then the effect on the application of smoothing was analyzed. As a result of the analysis, the correlation coefficient between variance of the surface elevation and total amount wave energy was 0.9994, confirming that there was no problem in applying the method. Thereafter, as a result of reviewing the effect of smoothing, it was found to be reduced by about 4 times compared to the confidence interval of the existing estimated spectrum, confirming that the accuracy of the estimated peak wave period was improved. It was found that there was a statistically significant difference in proba- bility density between 4 and 6 seconds due to the smoothing application. In addition, for optimal smoothing, the appropriate number of smoothings according to the significant wave height range was calculated using a statistical technique, and the number of smoothings was found to increase due to the unstable spectral shape as the significant wave height decreased.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.43-51
• /
• 2023

As online transactions increase, the image of clothing has a great influence on consumer purchasing decisions. The importance of image information for clothing materials has been emphasized, and it is important for the fashion industry to analyze clothing images and grasp the materials used. Textile materials used for clothing are difficult to identify with the naked eye, and much time and cost are consumed in sorting. This study aims to classify the materials of textiles from clothing images based on deep learning algorithms. Classifying materials can help reduce clothing production costs, increase the efficiency of the manufacturing process, and contribute to the service of recommending products of specific materials to consumers. We used machine vision-based deep learning algorithms ResNet and Vision Transformer to classify clothing images. A total of 760,949 images were collected and preprocessed to detect abnormal images. Finally, a total of 167,299 clothing images, 19 textile labels and 20 fabric labels were used. We used ResNet and Vision Transformer to classify clothing materials and compared the performance of the algorithms with the Top-k Accuracy Score metric. As a result of comparing the performance, the Vision Transformer algorithm outperforms ResNet.

• Journal of Platform Technology
• /
• v.11 no.3
• /
• pp.83-97
• /
• 2023

This research aims to identify startup trends by analyzing a large number of news articles through semantic network analysis. Using the BIGKinds article analysis service provided by the Korea Press Foundation, 330,628 news articles from 19 newspapers from January 2013 to December 2022 were comprehensively analyzed. The study focused on exploring the changes in key issues over the past decade, considering the impact of the social environment and global economic trends on entrepreneurship. We compared the number of news articles and changes in issues before and after the COVID-19 pandemic, and visualized entrepreneurship trends through frequency analysis, relationship analysis, and correlation analysis. The results of the study showed that the top keywords for entrepreneurship-related words are startup activation and commercialization, and the correlation between COVID-19 and entrepreneurship keywords is almost negligible in a linear sense, but the number of news articles decreased during the pandemic, which has an impact. In particular, the most frequently mentioned keywords are Ministry of SMEs and Startups, place is the United States, and person is limited. The agency was the SBA, and the entrepreneurship sector is more affected by social issues than any other sector, with the important characteristics of increased frequency of prompt access. This study supplies essential basic data for understanding and exploring issues and events related to entrepreneurship and suggests future research topics in the field.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.125-144
• /
• 2023

Recently, the use of Large Language Models (LLMs) such as ChatGPT has been increasing in various fields such as interactive commerce and mobile financial services. However, LMMs, which are mainly created by learning existing documents, can also learn various human biases inherent in documents. Nevertheless, there have been few comparative studies on the aspects of bias and discrimination in LLMs. The purpose of this study is to examine the existence and extent of nine types of discrimination (Age, Disability status, Gender identity, Nationality, Physical appearance, Race ethnicity, Religion, Socio-economic status, Sexual orientation) in LLMs and suggest ways to improve them. For this purpose, we utilized BBQ (Bias Benchmark for QA), a tool for identifying discrimination, to compare three large-scale language models including ChatGPT, GPT-3, and Bing Chat. As a result of the evaluation, a large number of discriminatory responses were observed in the mega-language models, and the patterns differed depending on the mega-language model. In particular, problems were exposed in elder discrimination and disability discrimination, which are not traditional AI ethics issues such as sexism, racism, and economic inequality, and a new perspective on AI ethics was found. Based on the results of the comparison, this paper describes how to improve and develop large-scale language models in the future.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.50 no.1
• /
• pp.1-12
• /
• 2023

Function of salivary gland and saliva composition can be an indicator of individual's health status. Recently, saliva has been thought to have a high potential for usage in the biomedical field to diagnose, evaluate, and prevent systemic health due to the technological advances in analyzing and detecting small elements such as immunological and metabolic products, viruses, microorganisms, hormones in saliva. As a diagnostic specimen, saliva has some useful advantages compared to serum. Because of simple non-invasive method, saliva sampling is quite comfort for the patient, and it doesn't require specialists to collect samples. The possibility of infection during the collection process is also low. For this reason, proteins, genetic materials, and various biomarkers in saliva are actively being utilized on studying stress, microbiomics, genetics, and epigenetics. For the research on collecting big data related to systemic health, the needs on biobank has been focused. Regeneration of salivary gland based on tissue engineering has been also on advancement. However, there are still many issues to be solved, such as the standardization of sample collection, storage, and usage. This review focuses on the recent trends in the field of saliva research and highlight the future perspectives in biomedical and other applications.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.50 no.2
• /
• pp.229-238
• /
• 2023

The objective of this study was to investigate trends in ankyloglossia and its surgical treatment among pediatric patients in South Korea from 2011 to 2020. Data from Health Insurance Review and Assessment Service (HIRA)'s Healthcare Bigdata Hub were used for analysis of the ankyloglossia diagnosis rate and frenum surgery rate. Considering annual population change, crude rates per 100,000 were calculated and analyzed. To investigate other factors of frenum surgery incidence besides gender and age, pediatric patient sample data from HIRA were used. The diagnosis rate of ankyloglossia increased from 204.4 in 2011 to 356.6 per 100,000 people in 2020, while the frenum surgery rate increased from 26.8 to 34.3 per 100,000 people. Males were more likely to receive frenum surgery than females. Surgeries were more likely to be done at a hospital instead of a clinic or a general hospital. In the age group of 0 - 4 years, the largest number of frenum surgeries were performed in pediatrics, and in the age group of 5 - 9 years, the largest number of surgeries were conducted in pediatric dentistry. In the older age groups, the largest proportion of frenum surgeries were performed in the departments of conservative dentistry and oral and maxillofacial surgery. The diagnosis of ankyloglossia and the operation of frenum surgery among South Korean children increased during the last decade. Since the function of the tongue can affect maxillofacial development in many aspects, pediatric dentists should pay more attention to the functional management of intraoral soft tissue in growing children.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.639-650
• /
• 2023

Economic development has resulted in the concentration of population and industry in the metropolitan area. Additionally, the Republic of Korea is experiencing this phenomenon, with more than half of the population living in the Seoul capital area. To alleviate this concentration of population, the Korean government implemented the new town development policy. Unfortunately, this has led to an increase in the commuting population, causing an imbalance in transportation services due to financial and policy differences in each region. This paper analyzes the level of user satisfaction with mega commuting in three aspects: mobility, accessibility, and connectivity. To objectively assess the level of user satisfaction, which is qualitative data, the Rasch Model is used to analyze the collinearity of user data. The results indicate that the level of user satisfaction differs by region, and service satisfaction with mobility is lower than that with accessibility and connectivity. Therefore, prior to the introduction of new town policies, it is necessary to develop metropolitan transportation infrastructure.

• Land and Housing Review
• /
• v.14 no.3
• /
• pp.125-135
• /
• 2023

In South Korea, it has been increased the necessity of supplying housing services to meet the needs and desires of various residents by reflecting various demographic and social changes. In particular, various smart device has been widely utilized in South Korea and the smart technologies, such as artificial intelligence and the Internet of Things has been developed rapidly. These smart technologies could support smart housing that allows residents to easily and comfortably employ residential services. However, it is necessary to improve the awareness of users in order to spread the smart housing residential services connected to smart technologies. For this reason, this study observed changes in users' perceptions of smart housing residential service technology using Living Lab. As a result, after experiencing the Living Lab, users' awareness of smart housing housing service increased, and it was observed that the preferred housing service technology was more detailed than before the Living Lab experience. This study shows that it is important to raise users' awareness for the dissemination of smart housing residential service technology, and that Living Lab can be an effective means for this purpose.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.4
• /
• pp.139-147
• /
• 2019

This study conducted bibliometric analysis on studies of Korean intangible cultural heritage dance in the Seoul area and it aimed to figure out the tendencies of that research. For this, a list of Korean intangible cultural heritage dance studies of 24 events was collected and analysis was conducted through the big data analysis solution of TEXTOM. Text mining was used as the method for analysis. Research results showed that first, most of the studies were conducted on the Bongsan Talchum and studies on teaching and learning methods were especially actively conducted. On the other hand, there were not many studies on Gut and the need for research vitalization in that area was confirmed. Second, in studies on Cheoyongmu events, the term'contemporary Cheoyongmu' was used frequently. This can be considered the use of meaningful terms with regard to intangible cultural heritage dance that has changed throughout history. At this, the vitalization of research that can reveal the typicality of dance is demanded from research of other events as well. Third, there was a notable amount of research that compared and analyzed dance styles with regard to the Munmyoilmu. This was seen as the result of discussions in the Korean dancing world regarding archetypal dance styles expanding into academic discussions. Therefore, it was revealed that academic discussions can connect to academic outcomes apart from whether the matter is right or wrong.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.225-227
• /
• 2022

Now In Seoul, about 75,000 CCTVs are installed in 25 district offices. Each ward office in Seoul has built a control center for CCTV control and is building information such as people, vehicle types, license plate recognition and color classification into big data through 24-hour artificial intelligence intelligent image analysis. Seoul Metropolitan Government has signed MOUs with the Ministry of Land, Infrastructure and Transport, the National Police Agency, the Fire Service, the Ministry of Justice, and the military base to enable rapid response to emergency/emergency situations. In other words, we are building a smart city that is safe and can prevent disasters by providing CCTV images of each ward office. In this paper, the CCTV image is designed to extract the characteristics of the vehicle and personnel when an incident occurs through artificial intelligence, and based on this, predict the escape route and enable continuous tracking. It is designed so that the AI automatically selects and displays the CCTV image of the route. It is designed to expand the smart city integration platform by providing image information and extracted information to the adjacent ward office when the escape route of a person or vehicle related to an incident is expected to an area other than the relevant jurisdiction. This paper will contribute as basic data to the development of smart city integrated platform research.