• 한국방사선학회논문지
• /
• 제17권6호
• /
• pp.873-879
• /
• 2023

본 연구는 인공지능(AI)을 사용하여 흉부 엑스레이 이미지에서 이물질을 탐지하는 방법을 탐구하였다. 의료영상학, 특히 흉부 엑스레이는 폐렴이나 폐암과 같은 질병을 진단하는 데 매우 중요한 역할을 한다. 영상의학 검사가 증가함에 따라 AI는 효율적이고 빠른 진단을 위한 중요한 도구가 되었다. 하지만 이미지에는 단추나 브래지어 와이어와 같은 일상적인 장신구를 포함한 이물질이 포함될 수 있어 정확한 판독을 방해할 수 있다. 본 연구에서는 이러한 이물질을 정확하게 식별하는 AI 알고리즘을 개발하였고, 미국 국립보건원 흉부 엑스레이 데이터셋을 가공하여 YOLOv8 모델을 기반으로 처리하였다. 그 결과 정확도, 정밀도, 리콜, F1-score가 모두 0.91에 가까울 정도로 높은 탐지 성능을 보였다. 이번 연구는 AI의 뛰어난 성능에도 불구하고 이미지 내 이물질로 인해 판독 결과가 왜곡될 수 있는 문제점을 해결함으로써 영상의학 분야에서 AI의 혁신적인 역할과 함께, 임상 구현에 필수적인 정확성에 기반하여 신뢰성을 강조하였다.

• 정보관리학회지
• /
• 제38권3호
• /
• pp.101-140
• /
• 2021

인공지능 기술이 결제 서비스 분야에도 적극 도입됨에 따라 말로 하는 결제 서비스 '음성결제(Voice Payments)'가 언택트 결제 서비스의 트렌드로 주목받고 있다. 음성결제 서비스는 인간의 가장 자연스러운 소통 수단인 '목소리'를 통해 결제를 더 빠르고 직관적으로 실행할 수 있는 서비스이다. 본 연구에서는 인공지능 에이전트와의 신뢰 형성을 위한 요인으로 '구체성', '친밀감', '자율성'을 선정하였으며, 각 특성들이 음성결제 상황의 음성 인터페이스에 적용되었을 때 이용자의 신뢰가 형성되는지 알아보고자 하였다. 실험 결과 음성결제 인터페이스의 구체성과 자율성은 높을수록, 친밀감은 낮을수록 신뢰가 높아졌다. 또한 구체성과 자율성의 이원상호작용효과가 유의하였다. 수집된 주관식 답변들을 분석 및 종합하여 이용자들이 음성결제 서비스를 접할 때 느끼는 불안 요인들을 파악하고, 음성결제에 대한 신뢰를 높일 수 있는 음성 인터페이스 디자인 방안들을 제안하였다.

• The Korean Journal of Physiology and Pharmacology
• /
• 제28권5호
• /
• pp.393-401
• /
• 2024

Large language models (LLMs) are rapidly transforming medical writing and publishing. This review article focuses on experimental evidence to provide a comprehensive overview of the current applications, challenges, and future implications of LLMs in various stages of academic research and publishing process. Global surveys reveal a high prevalence of LLM usage in scientific writing, with both potential benefits and challenges associated with its adoption. LLMs have been successfully applied in literature search, research design, writing assistance, quality assessment, citation generation, and data analysis. LLMs have also been used in peer review and publication processes, including manuscript screening, generating review comments, and identifying potential biases. To ensure the integrity and quality of scholarly work in the era of LLM-assisted research, responsible artificial intelligence (AI) use is crucial. Researchers should prioritize verifying the accuracy and reliability of AI-generated content, maintain transparency in the use of LLMs, and develop collaborative human-AI workflows. Reviewers should focus on higher-order reviewing skills and be aware of the potential use of LLMs in manuscripts. Editorial offices should develop clear policies and guidelines on AI use and foster open dialogue within the academic community. Future directions include addressing the limitations and biases of current LLMs, exploring innovative applications, and continuously updating policies and practices in response to technological advancements. Collaborative efforts among stakeholders are necessary to harness the transformative potential of LLMs while maintaining the integrity of medical writing and publishing.

• 대한의용생체공학회:의공학회지
• /
• 제43권4호
• /
• pp.259-270
• /
• 2022

Artificial intelligence (AI) has been studied in various fields of medical imaging. Currently, top-notch deep learning (DL) techniques have led to high diagnostic accuracy and fast computation. However, they are rarely used in real clinical practices because of a lack of reliability concerning their results. Most DL models can achieve high performance by extracting features from large volumes of data. However, increasing model complexity and nonlinearity turn such models into black boxes that are seldom accessible, interpretable, and transparent. As a result, scientific interest in the field of explainable artificial intelligence (XAI) is gradually emerging. This study aims to review diverse XAI approaches currently exploited in medical imaging. We identify the concepts of the methods, introduce studies applying them to imaging modalities such as computational tomography (CT), magnetic resonance imaging (MRI), and endoscopy, and lastly discuss limitations and challenges faced by XAI for future studies.

• 로봇학회논문지
• /
• 제19권1호
• /
• pp.23-30
• /
• 2024

This paper studies a GPS error filtering method that takes into account the continuity of the ongoing path to enhance the safety of autonomous agricultural mobile robots. Real-Time Kinematic Global Positioning System (RTK-GPS) is increasingly utilized for robot position evaluation in outdoor environments due to its significantly higher reliability compared to conventional GPS systems. However, in orchard environments, the robot's current position obtained from RTK-GPS information can become unstable due to unknown disturbances like orchard canopies. This problem can potentially lead to navigation errors and path deviations during the robot's movement. These issues can be resolved by filtering out GPS information that deviates from the continuity of the waypoints traversed, based on the robot's assessment of its current path. The contributions of this paper is as follows. 1) The method based on the previous waypoints of the traveled path to determine the current position and trajectory. 2) GPS filtering method based on deviations from the determined path. 3) Finally, verification of the navigation errors between the method applying the error filter and the method not applying the error filter.

• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.510-518
• /
• 2022

This paper confirmed the technical reliability of mobile-based sarcopenia prediction and monitoring system. In implementing the developed system, we designed using only sensors built into a smartphone without a separate external device. The prediction system predicts the possibility of sarcopenia without visiting a hospital by performing the SARC-F survey, the 5-time chair stand test, and the rapid tapping test. The Monitoring system tracks and analyzes the average walking speed in daily life to quickly detect the risk of sarcopenia. Through this, it is possible to rapid detection of undiagnosed risk of undiagnosed sarcopenia and initiate appropriate medical treatment. Through prediction and monitoring system, the user may predict and manage sarcopenia, and the developed system can have a positive effect on reducing medical demand and reducing medical costs. In addition, collected data is useful for the patient-doctor communication. Furthermore, the collected data can be used for learning data of artificial intelligence, contributing to medical artificial intelligence and e-health industry.

• 한국인공지능학회지
• /
• 제11권4호
• /
• pp.29-34
• /
• 2023

The flow from developing a machine learning model to deploying it in a production environment suffers challenges. Efficient and reliable deployment is critical for realizing the true value of machine learning models. Bridging this gap between development and publication has become a pivotal concern in the machine learning community. FastAPI, a modern and fast web framework for building APIs with Python, has gained substantial popularity for its speed, ease of use, and asynchronous capabilities. This paper focused on leveraging FastAPI for deploying machine learning models, addressing the potentials associated with integration, scalability, and performance in a production setting. In this work, we explored the seamless integration of machine learning models into FastAPI applications, enabling real-time predictions and showing a possibility of scaling up for a more diverse range of use cases. We discussed the intricacies of integrating popular machine learning frameworks with FastAPI, ensuring smooth interactions between data processing, model inference, and API responses. This study focused on elucidating the integration of machine learning models into production environments using FastAPI, exploring its capabilities, features, and best practices. We delved into the potential of FastAPI in providing a robust and efficient solution for deploying machine learning systems, handling real-time predictions, managing input/output data, and ensuring optimal performance and reliability.

• 한국구조물진단유지관리공학회 논문집
• /
• 제6권4호
• /
• pp.189-199
• /
• 2002

This study is intended to propose a systematic procedure for the development of the conditional assessment based on the safety of structures and the cost effective performance criteria for designing and upgrading of bridge structures. As a result, a set of cost function models for a life cycle cost analysis of bridge structures is proposed and thus the expected total life cycle costs (ETLCC) including initial (design, testing and construction) costs and direct/indirect damage costs considering repair and replacement costs, human losses and property damage costs, road user costs, and indirect regional economic losses costs. Also, the optimum safety indices are presented based on the expected total cost minimization function using only three parameters of the failure cost to the initial cost (${\tau}$), the extent of increased initial cost by improvement of safety (${\nu}$) and the order of an initial cost function (n). Through the enough numerical invetigations, we can positively conclude that the proposed optimum design procedure for bridge structures based on the ETLCC will lead to more rational, economical and safer design.

• 한국인공지능학회지
• /
• 제11권3호
• /
• pp.7-15
• /
• 2023

Purpose: The purpose of this study is to investigate how consumers perceive electric vehicles and factors that affect attitude, satisfaction, and intention to use electric vehicles and to explore policy issues regarding climate change and global environment. By classifying actual and potential users, this study developed the following research questions: i) factors including economic feasibility, sociality, environmental sustainability, inefficiency, inconvenience, convenience, and uncertainty affect attitude to electric vehicles; ii) attitude to electric vehicles affects actual consumers' satisfaction; and iii) attitude to electric vehicles affects potential users' intention to use. Research design, data and methodology: This study conducted an online survey and applied factor and regression analyses and ANOVA to test hypotheses. Results: The results of this study found that economic feasibility and convenience factors significantly affect attitude in both cases of actual and potential users. How actual users perceive efficiency of electric vehicles negatively and uncertain issues such as battery technology affect attitude to electric vehicles. Conclusions: This study provides policy implications that foster promotional policies for the adoption of electric vehicles for environment and regulate negative aspects. This study also provides managerial implications for manufacturers to develop better technology competences to enhance reliability on electric vehicles.