• Journal of Korean Biological Nursing Science
• /
• 제25권3호
• /
• pp.183-204
• /
• 2023

Purpose: The purpose of this study was to evaluate the applicability of ChatGPT in biological nursing science education. Methods: This study was conducted by entering questions about the field of biological nursing science into ChatGPT versions GPT-3.5 and GPT-4 and evaluating the answers. Three questions each related to microbiology and pharmacology were entered, and the generated content was analyzed to determine its applicability to the field of biological nursing science. The questions were of a level that could be presented to nursing students as written test questions. Results: The answers generated in English had 100.0% accuracy in both GPT-3.5 and GPT-4. For the sentences generated in Korean, the accuracy rate of GPT-3.5 was 62.7%, and that of GPT-4 was 100.0%. The total number of Korean sentences in GPT-3.5 was 51, while the total number of Korean sentences in GPT-4 was 68. Likewise, the total number of English sentences in GPT-3.5 was 70, while the total number of English sentences in GPT-4 was 75. This showed that even for the same Korean or English question, GPT-4 tended to be more detailed than GPT-3.5. Conclusion: This study confirmed the advantages of ChatGPT as a tool to improve understanding of various complex concepts in the field of biological nursing science. However, as the answers were based on data collected up to 2021, a guideline reflecting the most up-to-date information is needed. Further research is needed to develop a reliable and valid scale to evaluate ChatGPT's responses.

• 디지털산업정보학회논문지
• /
• 제19권1호
• /
• pp.139-151
• /
• 2023

This study aims to gain insights into ChatGPT, which has recently received significant attention. The study utilized a mixed method involving case studies and news big data analysis. ChatGPT can be described as an optimized language model for dialogue. The question arises whether ChatGPT will replace Google search services, posing a potential threat to Google. It could hurt Google's advertising business, which is the foundation of its profits. With AI-based chatbots like ChatGPT likely to disrupt the web search industry, Google is establishing a new AI strategy. The study used the BIG KINDS service and analyzed 2,136 articles over six months, from August 23, 2022, to February 22, 2023. Thirty of these articles were written in 2022, while 2,106 have been reported recently as of February 22, 2023. Also, the study examined the contents of ChatGPT by utilizing literature research, news big data analysis, and use cases. Despite limitations such as the potential for false information, analyzing news big data and use cases suggests that ChatGPT is worth using.

• Journal of Positioning, Navigation, and Timing
• /
• 제7권3호
• /
• pp.183-188
• /
• 2018

The Global Navigation Satellite System (GNSS) signal gets delayed as it goes through the troposphere before reaching the GNSS antenna. Various tropospheric models are being used to correct the tropospheric delay. In this study, we compared effectiveness of two popular troposphere correction models: Global Pressure and Temperature (GPT) and Satellite-Based Augmentation System (SBAS). One-year data from a particular site was chosen as the test case. Tropospheric delays were computed using the GPT and SBAS models and compared with the International GNSS Service tropospheric product. The bias of SBAS model computations was 3.4 cm, which is four times lower than that of the GPT model. The cause of higher biases observed in the GPT model is the fact that one cannot get wet delays from the model. If SBAS-based wet delays are added to the hydrostatic delays computed using the GPT model, then the accuracy is similar to that of the full SBAS model. From this study, one can conclude that it is better to use the SBAS model than to use the GPT model in the standard code-pseudorange data processing.

• 문화기술의 융합
• /
• 제9권4호
• /
• pp.659-666
• /
• 2023

생성형 인공지능 기술을 기반으로 한 도구 중 하나로 ChatGPT에 대한 활용 가능성이 모색되고 있다. 하지만 이를 교육적으로 활용할 때, 어떠한 요소를 고려해야 하는지를 학습자의 실제적인 인식을 기반으로 확인한 연구는 미흡하다. 본 연구는 교육 현장에서 ChatGPT를 활용할 때, 고려해야 하는 요소가 무엇인지를 질적 연구를 통해 도출하고자 하였다. 연구 결과, 교육에 있어서 ChatGPT를 효과적으로 활용하기 위해서는 생성된 정보에 대한 비판적 사고, 학습을 지원하는 한 가지 도구로서 인식하여 의존적인 활용 지양, 올바른 윤리적 활용에 대한 사전 교육 실시, 명확하고 적절한 질문 생성, 답변에 대한 재검토와 종합화 총 다섯 가지의 핵심 고려 요소를 확인하였다. 향후 이상의 요소를 종합적으로 구성한 교수설계 모형 개발이 이루어질 필요가 있다.

• 한국IT서비스학회지
• /
• 제23권2호
• /
• pp.99-116
• /
• 2024

Recently, interest in ChatGPT has been increasing. This study investigated the factors influencing the satisfaction of users using ChatGPT service, a chatbot system based on artificial intelligence technology. This paper empirically analyzed causality between the four major factors of service quality, system quality, information quality, and security as independent variables and user satisfaction of ChatGPT as dependent variable. In addition, the mediating effect of reliability between the independent variables and user's satisfaction was analyzed. As a result of this research, except for information quality, among the quality factors, security and reliability had a positive causality with use satisfaction. Reliability played a mediating role between quality factors, security, and user satisfaction. However, among quality factors, the mediating effect of reliability between service quality and user's satisfaction was not significant. In conclusion, in order to increase user satisfaction with new technology-based services, it is important to create trust among users. The research results sought to emphasize the importance of user trust in establishing development and operation strategies for artificial intelligence systems, including ChatGPT.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.363-364
• /
• 2023

현재 많은 사람이 GPT를 통해 다양한 활동 및 연구를 진행하고 있다. 사람들은 GPT를 통해 문장생성 시 문장에 대한 정확도를 중요하게 생각한다. 하지만 용도에 따라 GPT를 통해 생성하는 문장의 문체와 같은 표현방식이 다르다. 그래서 생성된 문장이 유의미한 문장이라는 것에 판단이 매우 주관적이기 때문에 수치적 평가가 어렵다. 본 논문에서는 자연어처리 모델이 생성한 문장의 유의미함을 판단하기 위해 각 모델을 학습하는 데이터 용량과 반복 학습의 횟수에 따른 결과물을 비교하였다. 본 연구에서는 Fine-Tuning을 통해 총 4개의 GPT 모델을 구축하였다. 각 모델로 생성 문장을 BLEU 평가지표를 통해 평가한 결과 본 연구에 BLEU 모델은 부적합하다는 결과를 도출하였다. 이를 해결하기 위해 본 연구에서는 생성된 모델을 평가하고자 설문지를 만들어 평가를 진행하였다. 그 결과 사람에게 긍정적인 평가를 받는 결과를 얻을 수 있었다.

• 한국IT서비스학회지
• /
• 제22권6호
• /
• pp.17-35
• /
• 2023

This study investigated how helpful the use of generative AI such as ChatGPT is in conducting engaged learning at each university. In this study, based on the experiences of users using generative AI technology, we analyzed the relationship between usability and ease in consideration of the characteristics of learners, and examined whether there is an intention to continue using generative AI technology in the future. In this study, in order to verify the factors affecting the intention to use ChatGPT technology in order to solve the problems given in the participating classes, we examined previous papers based on the Technology Acceptance Model (TAM) and the Information System Success Model (IS), extracted the factors affecting the intention of ChatGPT technology, and presented the research model and hypothesis. Empirical research on the continuous use of generative AI in participatory learning using ChatGPT was conducted to determine whether it is suitable for long-term and continuous use in the educational environment, and whether it is sustainable by examining the intention of learners to continue using it. First, user satisfaction was positively related to the intention to continue using generative AI technology. Second, if the user experience has a great influence on the intention to continue using ChatGPT technology, and users gain experiences such as usefulness, interest, and effective response in the process of using the technology, the evaluation of the technology is positively formed and the intention to continue using it is high. Third, the ease of use of the technology also showed that it was intended to be used continuously when an environment was provided in which users could easily and conveniently utilize generative AI technology.

• 한국BIM학회 논문집
• /
• 제14권2호
• /
• pp.25-34
• /
• 2024

This study proposes a new methodology to increase the flexibility and efficiency of the design data evaluation system by combining Building Information Modeling (BIM) technology in the architectural industry, OpenAI's interactive artificial intelligence, and ChatGPT. BIM technology plays an important role in digitally modeling and managing architectural information. Since architectural information is included, research and development are underway to review and evaluate BIM data according to conditions through program development. However, in the process of reviewing BIM design data, if the review criteria or evaluation criteria according to design change occur frequently, it is necessary to update the program anew. In order for designers or reviewers to apply the changed criteria, requesting a program developer will delay time. This problem was studied by using ChatGPT to modify and update the design data evaluation program code in real time. In this study, it is aimed to improve the changing standards and accuracy by enabling programming non-professionals to change the design regulations and calculation standards of the BIM evaluation program system using ChatGPT. In this study, in the BIM-based design certification automation evaluation program, a program in which the automation evaluation method is being studied based on the design certification evaluation manual was first used. In the design certification automation evaluation program, the programming non-majors checked the automation evaluation code by linking ChatGPT, and the changed calculation criteria were created and modified interactively. As a result of the evaluation, the change in the calculation standard was explained to ChatGPT and the applied result was confirmed.

• 한국인터넷방송통신학회논문지
• /
• 제24권3호
• /
• pp.87-94
• /
• 2024

LLM(Large Language Model)을 활용하여 사전에 게임 데이터 학습 없이 텍스트 기반 게임을 수행할 수 있는지 알아보았다. LLM을 구현한 시스템으로는 ChatGPT-3.5와 가장 최신 형태인 ChatGPT-4를 채택하였다. 이에 더해 ChatGPT-4에 본 논문에서 제안하는 영구 메모리 기능을 추가하여 세 개의 게임 플레이어 에이전트를 제작하였다. 텍스트 기반 게임으로 가장 유명한 Zork를 활용하여 복잡한 장소를 이동해가며 정보를 모으고 퍼즐을 풀 수 있는지 알아보았다. 그 결과 세 에이전트 중 영구 메모리 기능을 추가한 에이전트의 성능이 탐험을 가장 넓은 범위로 진행하였고 점수도 가장 뛰어났다. 그러나 세 에이전트 모두 퍼즐을 푸는데 한계를 보였으며 이는 다단계 추론이 필요한 문제에 LLM이 취약하다는 것을 보여주었다. 그럼에도 여전히 본 논문에서 제안하는 에이전트를 사용하면 전체 장소의 37.3%를 방문하고, 방문했던 장소의 아이템을 모두 모으는데 성공할 수 있었던 것으로 LLM의 가능성을 확인할 수 있었다.

• 사물인터넷융복합논문지
• /
• 제9권6호
• /
• pp.45-50
• /
• 2023

소프트웨어 개발에서 요구사항 도출 및 분석은 매우 중요한 단계이며, 다양한 이해관계자가 관여하기 때문에 많은 시간과 노력을 필요로 한다. ChatGPT는 다양한 문서를 학습한 대규모 언어 모델로서 코드 생성, 디버깅 등의 능력은 물론 소프트웨어 분석 설계 영역에서도 활용할 수 있는 능력을 갖고 있는 것으로 연구되고 있다. 본 논문에서는 ChatGPT의 이러한 능력을 활용하여 소프트웨어 요구사항 도출, 시스템 목표에 적합한 요구사항 분석, 유스케이스 형태로 문서화하는 요구공학 방법을 제안한다. 소프트웨어 요구공학에서 이해관계자, 분석가, ChatGPT는 협업 모델을 가져야 하며, 요구사항 도출, 분석, 명세화에서 ChatGPT의 결과를 초기 요구사항으로 하여 분석가와 이해관계자가 점검 및 내용을 추가하는 형태로 요구공학이 진행하는 것을 제안한다. ChatGPT의 성능이 향상될수록 요구사항의 도출 및 분석이 점차 정확도를 높일 수 있을 것이며, 소프트웨어 요구공학에서 시간 및 비용을 절감할 수 있을 것이다.