• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.148-155
• /
• 2024

Despite the increasing importance of irony and sarcasm detection in the field of natural language processing, research on the Korean language is relatively scarce compared to other languages. This study aims to experiment with various models for irony detection in Korean text. The study conducted irony detection experiments using KoBERT, a BERT-based model, and ChatGPT. For KoBERT, two methods of additional training on sentiment data were applied (Transfer Learning and MultiTask Learning). Additionally, for ChatGPT, the Few-Shot Learning technique was applied by increasing the number of example sentences entered as prompts. The results of the experiments showed that the Transfer Learning and MultiTask Learning models, which were trained with additional sentiment data, outperformed the baseline model without additional sentiment data. On the other hand, ChatGPT exhibited significantly lower performance compared to KoBERT, and increasing the number of example sentences did not lead to a noticeable improvement in performance. In conclusion, this study suggests that a model based on KoBERT is more suitable for irony detection than ChatGPT, and it highlights the potential contribution of additional training on sentiment data to improve irony detection performance.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.19-24
• /
• 2024

The future military combat environment is rapidly expanding the role and importance of artificial intelligence (AI) in defense, aligning with the current trends of declining military populations and evolving dynamics. Particularly, in the civilian sector, AI development has surged into new domains based on foundation models, such as OpenAI's Chat-GPT, categorized as Super-Giant AI or Hyperscale AI. The U.S. Department of Defense has organized Task Force Lima under the Chief Digital and AI Office (CDAO) to conduct research on the application of Large Language Models (LLM) and generative AI. Advanced military nations like China and Israel are also actively researching the integration of Super-Giant AI into their military capabilities. Consequently, there is a growing need for research within our military regarding the potential applications and fields of application for Super-Giant AI in weapon systems. In this paper, we compare the characteristics and pros and cons of specialized AI and Super-Giant AI (Foundation Models) and explore new application areas for Super-Giant AI in weapon systems. Anticipating future application areas and potential challenges, this research aims to provide insights into effectively integrating Super-Giant Artificial Intelligence into defense operations. It is expected to contribute to the development of military capabilities, policy formulation, and international security strategies in the era of advanced artificial intelligence.

• Journal of the Korean Society of Radiology
• /
• v.85 no.1
• /
• pp.36-53
• /
• 2024

As the number of spinal surgeries being performed expands, the number of medical imaging procedures such as radiography, CT, and MRI is also increasing, and the importance of their interpretation is becoming more significant. Herein, we present the radiological findings of a variety of complications that can occur after spinal surgery and discuss how effectively and accurately they can be diagnosed through imaging. In particular, this study details the characteristic imaging findings specific to the early and long-term postoperative periods. Early complications of spinal surgery include improper placement of surgical instruments (instrument malpositioning), seromas, hematomas, pseudomeningoceles, and infections in the region surrounding the surgical site. Conversely, long-term complications may include osteolysis around surgical instruments, failure of fusion, adjacent segment disease, and the formation of epidural fibrosis or scar tissue. A precise understanding of the imaging assessments related to complications arising after spinal surgery is crucial to ensure timely and accurate diagnosis, which is necessary to achieve effective treatment.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.12 no.1
• /
• pp.167-174
• /
• 2008

Number of long-span bridge construction has been increased recently so that seismic consideration of design has become significant. To adapt such significance to design, seismic design in the newly revised 'Cable Steel Bridge Design Handbook' specifies some of wave travelling effect and local site effect. In this study, a cable-stayed bridge with main span of 500m is analysed having variables of uniform excitation, wave travelling effect, and wave travelling effect plus local site effect. Result shows that wave travelling effect in cable-stayed bridge affects considerably to its seismic response under weak soil condition even though the span length is relatively short. What's more, regardless of soil type, the seismic response has become higher for analysis with wave travelling effect and local site effect than with wave travelling effect only. Consequently, in seismic response analysis of long-span bridge, consideration should be given to application of wave travelling effect and local site effect.

• Journal of the Health Care and Life Science
• /
• v.10 no.1
• /
• pp.89-98
• /
• 2022

This study conducted a survey using a Google questionnaire targeting 380 male and female college students to find out the perceptions of college students about health masks at the time of transition from the COVID-19 pandemic to the recovery stage. As a result, at the time when the obligation to wear an outdoor mask was relaxed, they still wore an outdoor mask (3.63±1.34). As for the reasons for wearing a mask, 27.8% said 'wearing a mask became a habit' and 'fear of infection' was 19.4%. Hand washing to prevent COVID-19 was observed well (4.07±1.00), and when infection was suspected, they showed an attitude of checking for infection with a home kit or rapid antigen test (3.88±1.17). In addition, it was recognized that COVID-19 is not threatening (3.19±1.28) and that it will recover easily after infection (3.19±1.28). In a situation where the number of COVID-19 infections continues to decrease, the government is pushing for a gradual recovery of new daily life. Therefore, it is necessary to provide correct information that affects individual awareness and to promote it through various media, and I would like to emphasize the importance of education on the autonomous practice of individual quarantine rules.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.763-780
• /
• 2024

As the domestic and international landscape undergoes rapid changes, the importance of implementing security measures in response to the growing threats that businesses face is increasing. In this context, the need for Security by Design (SbD), integrating security from the early design stages, is becoming more pronounced, with threat modeling recognized as a fundamental tool of SbD. Particularly, to save costs and time by detecting and resolving security issues early, the application of the Shift Left strategy requires the involvement of personnel with limited security expertise, such as software developers, in threat modeling. Although various automated threat modeling tools have been released, their lack of user-friendliness for personnel lacking security expertise poses challenges in conducting threat modeling effectively. To address this, we conducted an analysis of research related to threat modeling tools and derived usability evaluation criteria based on the GQM(Goal-Question-Metric) approach. An expert survey was conducted to validate both the validity and objectivity of the derived criteria. We performed usability evaluations of three threat modeling tools (MS TMT, SPARTA, PyTM), and the evaluation results led to the conclusion that MS TMT exhibited superior usability compared to other tools. This study aims to contribute to the creation of an environment where personnel with limited security expertise can effectively conduct threat modeling by proposing usability evaluation criteria.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.83-92
• /
• 2024

Recently, the importance of HR analytics for data-based decision-making in establishing and operating an effective human resource management system for companies is increasing. In addition, there is growing interest in the effect of employees' perceptions of organizational justice on positive organizational behavior. Therefore, in this study, among the various factors affecting teamwork behavior, we analyzed the impact on teamwork behavior such as perception of organizational justice and organizational culture. Organizational justice has a significant impact on the formation of members' attitudes, but its meaning may vary depending on the organizational context. In this study, we divided organizational justice into four types (procedural, distributive, interpersonal, and informational fairness) and confirmed their impact on teamwork behavior. In addition, organizational culture was divided into hierarchy culture and innovation culture, and how to regulate these relationships was examined. To analyze these relationships, individual-level data collected from 657 people at domestic companies were used for analysis. According to the analysis results, in a hierarchical culture, procedural justice and information justice had a positive influence on teamwork behavior through the mediating process of job satisfaction, and in an innovative culture, interpersonal justice and information justice had a positive influence on teamwork behavior through job satisfaction. It was confirmed to have a (+) effect. These research results provide implications for people management by indicating that, although organizational justice is important to members and organizations, it may be perceived differently and have different meanings depending on the organizational context. Through the use of the information presented in this study, we will provide value that can effectively and efficiently implement a company's human resource management system.

• Journal of the Society of Disaster Information
• /
• v.20 no.3
• /
• pp.601-608
• /
• 2024

Purpose: The purpose of this study is to predict the criminal patterns and risks of conflicts caused by inequality such as weakening regional ties and social exclusion caused by climate change and present basic policy data to solve them. Method: This study was mainly conducted through analysis of contents and cases through the use of media information such as the Internet and newspapers, and some literature research. Result: The crime patterns and characteristics of climate gentrification are as follows. First, rising sea levels caused by climate change will temporarily increase crimes related to real estate speculation. Second, social exclusion due to public service and environmental inequality will intensify, leading to terrorist crimes such as riots and hate crimes. Third, due to the weakening of regional ties, young people in poverty in the region will participate in organized violence crimes such as drugs and gangs or become crime victims. Conclusion: Therefore, it is necessary to prepare policy countermeasures through cooperation with institutions. In particular, it is necessary to explore ESG policy measures in police activities in consideration of environmental factors in the future.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.3
• /
• pp.131-143
• /
• 2024

This article examines the cases of archive development by research institutions for overseas Korean studies from the perspective of documenting the locality and explores development plans. The study investigates the impact of the solidarity between overseas Korean studies institutions and Korea-related communities in the region on the expansion of archives and the practice of locality documentation, using the case of the Korean War Archive Collection at the University of Hawai'i at Mānoa Library. For this, it reexamines the implications of locality and locality documentation. In addition, it discusses the methods of Korean studies locality documentation emerging abroad, such as the locality where the two geographical areas of Korea and Hawaii are fused. Since 2023, the University of Hawai'i at Mānoa Library has been forming a network with the Korean War Veterans Association Hawaii Chapter 1 (KWVA) to collect and archive materials related to the Korean War. This is a case where the relationship between the archivists and the donor community has been developed to practice documenting the locality regarding Korean studies abroad. It proposes locality documentation as a way to expand archives in overseas Korean studies institutions that inevitably rely on the collection of records and discusses the importance of solidarity with Korea-related local communities. Finally, it shares the role of the record management subject and the implications found through the case.

• Journal of Practical Engineering Education
• /
• v.16 no.4
• /
• pp.553-566
• /
• 2024

The core of this study is to review South Korea's individual-driven training scheme, identify factors hindering elderly participation, and derive implications to support their retention and participation of the elderly in the labor market. This study focuses on population aging, examining the National Lifelong Learning Card system and the current employment insurance scheme, both initiatives of the Ministry of Employment and Labor, to assess the status and issues surrounding elderly participation in vocational training. Based on this analysis, the study seeks to derive policy measures and academic significance to promote elderly participation in vocational training. Based on this analysis, the study aims to derive policy measures and academic significance to promote the participation of older adults in vocational training. The findings emphasized the importance of employment retention for elderly and highlighted the need for vocational training tailored to the specific characteristics of each individual, along with the necessity for professional life-career consulting. Based on these findings, the study proposed recommendations to promote self-directed training among elderly, including enhancing the diversity of vocational training to meet individuals' varied needs, implementing lifelong vocational training programs from a life-cycle perspective, creating age-friendly workplaces at the national level, encouraging individual-driven training participation for the self-realization of elderly, and strengthening the linkage between employment counseling and vocational training for elderly.