• Korean Journal of Radiology
• /
• 제24권11호
• /
• pp.1061-1080
• /
• 2023

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1273-1300
• /
• 2024

In the complex virtual environment of cyberspace, comprised of digital and communication networks, ensuring the security of information is being recognized as an ongoing challenge. The importance of 'Cyber Situation Awareness (CSA)' is being emphasized in response to this. CSA is understood as a vital capability to identify, understand, and respond to various cyber threats and is positioned at the heart of cyber security strategies from a defensive perspective. Critical industries such as finance, healthcare, manufacturing, telecommunications, transportation, and energy can be subjected to not just economic and societal losses from cyber threats but, in severe cases, national losses. Consequently, the importance of CSA is being accentuated and research activities are being vigorously undertaken. A systematic five-step approach to CSA is introduced against this backdrop, and a deep analysis of recent research trends, techniques, challenges, and future directions since 2019 is provided. The approach encompasses current situation and identification awareness, the impact of attacks and vulnerability assessment, the evolution of situations and tracking of actor behaviors, root cause and forensic analysis, and future scenarios and threat predictions. Through this survey, readers will be deepened in their understanding of the fundamental importance and practical applications of CSA, and their insights into research and applications in this field will be enhanced. This survey is expected to serve as a useful guide and reference for researchers and experts particularly interested in CSA research and applications.

• Geomechanics and Engineering
• /
• 제36권3호
• /
• pp.205-215
• /
• 2024

Manually mapping fractures in construction stone mines is challenging, time-consuming, and hazardous. In this method, there is no physical access to all points. In contrast, digital image processing offers a safe, cost-effective, and fast alternative, with the capability to map all joints. In this study, two methods of detecting the trace of discontinuities using image processing in construction stone mines are presented. To achieve this, we employ two modified Hough transform algorithms and the degree of neighborhood technique. Initially, we introduced a method for selecting the best edge detector and smoothing algorithms. Subsequently, the Canny detector and median smoother were identified as the most efficient tools. To trace discontinuities using the mentioned methods, common preprocessing steps were initially applied to the image. Following this, each of the two algorithms followed a distinct approach. The Hough transform algorithm was first applied to the image, and the traces were represented through line drawings. Subsequently, the Hough transform results were refined using fuzzy clustering and reduced clustering algorithms, along with a novel algorithm known as the farthest points' algorithm. Additionally, we developed another algorithm, the degree of neighborhood, tailored for detecting discontinuity traces in construction stones. After completing the common preprocessing steps, the thinning operation was performed on the target image, and the degree of neighborhood for lineament pixels was determined. Subsequently, short lines were removed, and the discontinuities were determined based on the degree of neighborhood. In the final step, we connected lines that were previously separated using the method to be described. The comparison of results demonstrates that image processing is a suitable tool for identifying rock mass discontinuity traces. Finally, a comparison of two images from different construction stone mines presented at the end of this study reveals that in images with fewer traces of discontinuities and a softer texture, both algorithms effectively detect the discontinuity traces.

• Archives of Plastic Surgery
• /
• 제50권6호
• /
• pp.621-626
• /
• 2023

In the first half of the third century B.C., Herophilus and Erasistratus performed the first systematic dissection of the human body. For subsequent centuries, these cadaveric dissections were key to the advancement of anatomical knowledge and surgical techniques. To this day, despite various instructional methods, cadaver dissection remained the best way for surgical training. To improve the quality of education and research through cadaveric dissection, our institution has developed a unique method of perforator-preserving cadaver injection, allowing us to achieve high-fidelity perforator visualization for dissection studies, at low cost and high efficacy. Ten full body cadavers were sectioned through the base of neck, bilateral shoulder, and hip joints. The key was to dissect multiple perfusing arteries and draining veins for each section, to increase "capture" of vascular territories. The vessels were carefully flushed, insufflated, and then filled with latex dye. Our injection dye comprised of liquid latex, formalin, and acrylic paint in the ratio of 1:2:1. Different endpoints were used to assess adequacy of injection, such as reconstitution of eyeball volume, skin turgor, visible dye in subcutaneous veins, and seepage of dye through stab incisions in digital pulps. Dissections demonstrated the effectiveness of the dye, outlining even the small osseous perforators of the medial femoral condyle flap and subconjunctival plexuses. Our technique emphasized atraumatic preparation, recreation of luminal space through insufflation, and finally careful injection of latex dye with adequate curing. This has allowed high-fidelity perforator visualization for dissection studies.

• 유통과학연구
• /
• 제22권4호
• /
• pp.11-22
• /
• 2024

Purpose: This research delves into the various factors that influence the performance of restaurant businesses on social commerce platforms in Bangkok, Thailand. The study considers both internal and external factors, including but not limited to business characteristics and location. Moreover, this research also analyzes the effects of employing multiple social commerce platforms on business efficiency and explores the underlying reasons for such effects. Research design, data, and methodology: Restaurants can be classified into different price ranges: low, medium, and high. To further investigate, we employed natural language processing AI to analyze online reviews and evaluate algorithm performance using machine learning techniques. We aimed to develop a model to gauge customer satisfaction with restaurants across different price categories effectively. Results: According to the research findings, several factors significantly impact restaurant groups in the low and mid-price ranges. Among these factors are population density and the number of seats at the restaurant. On the other hand, in the mid-and high-price ranges, the price levels of the food and drinks offered by the restaurant play a crucial role in determining customer satisfaction. Furthermore, the correlation between different social commerce platforms can significantly affect the business performance of high-price range restaurant groups. Finally, the level of online review sentiment has been found to influence customer decision-making across all restaurant types significantly. Conclusions: The study emphasizes that restaurants' characteristics based on their price level differ significantly, and social commerce platforms have the potential to affect one another. It is worth noting that the sentiment expressed in online reviews has a more significant impact on customer decision-making than any other factor, regardless of the type of restaurant in question.

• 복식문화연구
• /
• 제32권3호
• /
• pp.334-344
• /
• 2024

This study aimed to develop a new convergence course applying project-based learning (PBL) and collaborative teaching methods and identify its educational effects. The course development proceeded as follows: First, three instructors collaborated to define course goals, plan objectives, content, and methods, and create a syllabus for a PBL-based fashion studio course. Roles were divided to maximize expertise: one instructor focused on fashion design, another on three-dimensional cutting, and the third on flat cutting, and digital techniques. Second, the classes were conducted and feedback on student progress was shared, enhancing class quality and engagement. Third, teaching effectiveness was assessed through learner evaluation questionnaires, reflection journals, and performance assessments. Lastly, based on the results from these evaluations, positive aspects of the course were reviewed, and ways to modify it and enhance course quality for continuous improvement were explored. The results showed high satisfaction with the learning effects on major competencies, indicating that students not only effectively learned major skills but also improved their communication and teamwork. The students perceived the teaching methods positively allowing them to be more active in class. Instructors noted that the course produced higher-quality design and production outcomes compared to previous courses. Overall, the course applying PBL and collaborative teaching methods was found to improve educational quality and effectiveness, making it a valuable approach for learner-centered education.

• Journal of Cerebrovascular and Endovascular Neurosurgery
• /
• 제26권2호
• /
• pp.223-226
• /
• 2024

Percutaneous techniques for femoral arterial access are increasingly being performed due to advances in endovascular cerebral procedures, as they provide a less morbid and minimally invasive approach than open procedures. Common complications associated with this peripheral puncture include hematoma, bleeding, pseudoaneurysm, arteriovenous fistula, retroperitoneal bleeding, inadvertent venous puncture, dissection, etc. The retrograde femoral access is currently the most frequently used arterial access as it is technically straightforward, allows for the use of larger size sheaths and catheters, allows repeated attempts, etc. Although being technically less challenging, grave complications can occur due to hardware failure. Here, we present a case of unruptured posterior inferior cerebellar artery (PICA) aneurysm, who underwent uneventful diagnostic cerebral digital substraction angiography (DSA) via right femoral artery route on first attempt, but on second attempt for therapeutic intervention, landed up with stuck guide wire and faced decannulation difficulty due to unravelling of guide wire and multiple knot formation, which was finally removed after multiple attempts at pulling and improvised manoeuvres. Such cannulation and decannulation difficulties have been reported multiple times for central venous access, but extremely rarely for femoral routes, making this case a rarity and worth reporting.

• 지능정보연구
• /
• 제17권1호
• /
• pp.139-152
• /
• 2011

1990년대 중반에 협업 필터링의 출현으로 인하여 추천시스템에 관련된 연구가 늘어나게 되었다. 협업 필터링의 출현 이후 내용 기반 필터링, 협업 필터링과 내용 기반 필터링이 혼합된 하이브리드 필터링 등 새로운 기법들이 출현함으로써 2000년대에는 추천시스템의 연구가 눈에 띄게 증가하였다. 하지만 현재까지 추천시스템에 관련된 문헌들에 대한 리뷰와 분류가 체계적으로 되어있지 않다. 이와 같은 문제에 대한 해결방안으로써, 본 연구에서는 2001년부터 2010년도까지의 추천시스템에 관련된 문헌들 중 MIS Journal Ranking의 125개의 저널에서 추천시스템(Recommender system, Recommendation system), 협업 필터링(Collaborative Filtering), 내용 기반 필터링(Content based Filtering), 개인화 시스템(Personalized system) 등의 5가지 키워드로 제한하여 조사하였다. 총 37개의 저널에서 논문을 검색하였으며, 검색되어진 논문을 분석한 결과 추천시스템과 관련이 없는 논문을 제외한 총 187개의 논문을 선정하여 분석하였다. 이 연구에서는 그러나 컨퍼런스 논문, 석사, 박사학위 논문, 영어로 작성되지 않은 논문, 완성되지 않은 논문 등은 제외하였다. 본 연구에서는 187개의 논문을 분석하여 2001년부터 2010년까지의 각각의 년도 별 추천시스템의 연구에 대한 동향 분석, Journal별 추천시스템의 게재 분류, 추천시스템 어플리케이션의 사용 분야(책, 문서, 이미지, 영화, 음악, 쇼핑, TV 프로그램, 기타)별 분류 및 분석, 추천시스템에 사용된 데이터마이닝 기술(연관 규칙, 군집화, 의사 결정나무, 최근접 이웃 기법, 링크 분석 기법, 신경망, 회귀분석, 휴리스틱 기법)별 분류 및 분석을 수행하였다. 따라서 본 연구에서 제안한 각각의 분류 및 분석 결과들을 통하여 현재까지 추천시스템의 연구에 대한 연구 동향을 파악 할 수 있었으며, 분석결과를 통해 추천시스템에 관심이 있는 연구자와 전문가에게 미래의 추천시스템의 연구에 대한 가이드라인을 제시 할 수 있을 것이라고 기대한다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제32권3호
• /
• pp.313-323
• /
• 2009

확산강조영상 (diffusion weighted image, DWI)은 급성 뇌경색, 뇌종양, 뇌백질 질환, 뇌 막질의 확산 정도 등 여러 뇌질환의 진단을 획기적으로 향상시켰으며 그 활용도가 증가하고 있다. 본 연구는 $10{\sim}60$대 환자들의 뇌를 대상으로 두 기법간의 신호강도, 현성확산계수의 평균치를 측정하였다. 그 결과, 확산강조영상에서의 신호강도 평균값은 편도체부 (amygdala)가 가장 높고, 뇌척수액(cerebrospinal fluid)에서 가장 낮았다. 현성확산계수의 평균값은 뇌척수액이 높고, 교뇌 (pons)가 낮게 측정되었다. 확산강조 신호강도와 현성확산계수의 평균값은 $T_2^*$-DW-EPI 기법이 FLAIR-DW-EPI 기법보다 높고, b-value의 변화에 따른 평균값은 두 기법의 b-value에 모두 반비례하였다. 또한 뇌경색환자의 뇌의 시간 경과에 따른 분석결과, 초급성뇌경색 환자의 일반적인 MR 영상에서는 병변부분이 명확하지 않았으나 확산강조영상에서는 고신호강도로 나타났다. 출혈성 뇌경색, 급성 뇌경색 등 여러질환별로 분석한 결과 그 두 기법의 특성에 따라 신호강도의 값이 차이가 클수록 현성확산계수는 낮게 나타났다. 결론적으로 뇌 질환이 자주 발생되는 부위와 뇌 질환의 확산강조 신호강도 및 현성확산계수 값은 b-value의 변환과 영상기법에 따라 각각 다르게 나타났다. 이러한 정량적인 결과를 바탕으로 보다 안정적인 기법과 적절한 b-value 값을 이용하여 검사를 한다면 여러 뇌의 질환 및 병변 등을 발견, 판독하는 것뿐만 아니라 정상부위나 질환에 따른 기법별 신호의 인지를 통한 정확한 질병 진단과 치료에 중요한 의미가 있다고 사료된다.

• 한국조경학회지
• /
• 제49권2호
• /
• pp.51-60
• /
• 2021

현대사회는 인간, 사물, 네트워크가 관계를 형성하는 디지털기술의 발전으로 정보화, 지능화되고 있다. 이와 같은 시대적 변화에 따라 식물 재배 시 온도, 습도, 일광량, 수분공급 등 식물관리를 용이하게 할 수 있는 정원 관련 시스템이 등장하기 시작하였다. 이에 본 연구에서는 최근 이슈가 되고 있는 스마트가든의 개념 및 인식경향에 대하여 파악하고자 하였다. 본 연구의 목적을 달성하기 위하여 선행연구와 텍스트마이닝을 활용하였으며, 결과는 다음과 같다. 첫째, 스마트가든의 특성은 기술의 발전 및 사람들의 라이프스타일의 변화로 실내·외 공간에서 IoT기술과 정원이 융합한 새로운 정원형태 혹은 여가의 유형 중 하나이다. 기술의 발전과 환경의 중요성이 높아지면서 인간과 자연이 융합되는 생활공간의 요구로 스마트가든이 현실화되고 보편화되고 있다. 스마트가든의 등장으로 정원 관련 산업의 변화, 사람들의 라이프스타일 변화 등 정원의 활성화에 기여할 수 있을 것이다. 둘째, 현재 스마트가든과 관련된 연구 및 이용자의 경험에서 공통적으로 스마트가든의 기술적인 측면에 관심이 가장 높다. 사람들은 스마트가든이 일상생활 속에서 안전하고 쾌적하며 편리한 생활을 할 수 있는 기능 및 기술적인 측면을 중요시하며, 개인의 취향 및 디지털 기기의 이용능력에 따라 주체적인 이용이 나타나고 있다. 셋째, 스마트가든의 이용행태를 살펴보면 주로 가정 및 실내공간에서 이용하고 있으며, 먹을 수 있는 식물을 재배하고 있는 추세이다. 환경의 중요성이 높아지고 기후변화, 식량위기 등에 대한 우려로 먹거리와 관련된 식물 재배를 선호하고 있지만, 화훼류 등을 키울 수 있는 다양한 기술 및 매뉴얼로 이용자의 욕구를 만족시켜주어 정원기능의 확대에 이바지할 수 있을 것이다. 또한, 스마트가든의 형태를 새롭고 세련된 형태라고 느끼고 있어 스마트가든의 디자인이 이용자의 가치를 만족시키는 중요한 요소임을 알 수 있다. 현재 스마트가든은 기술적인 차원에서 발전하고 있다. 그러나 스마트가든의 주요 구성 요인은 인간과 자연 그리고 기술일 것이다. 단순하게 화분과 스마트기기를 연결하여 식물을 편하게 기르는데 집중하는 것이 아니라, 스마트시티, 스마트홈 등 다양한 도시서비스와 연계성을 강화하고, 스마트가든이 과학기술에 의해서만 자연이 재현되는 것이 아니라, 조경가와 상호작용하여 정원의 기능 및 이용자의 니즈를 포함한 디자인이어야 할 필요가 있다. 또한, 실내뿐만이 아니라, 도시공원 및 공공시설에서 시민에게 제공하여 연령 및 디지털 기기·정보의 격차로 인하여 '스마트'한 서비스를 향유하지 못하는 계층을 대상으로 하여 세대 간 커뮤니케이션, 정원의 기능을 공유할 수 있는 새로운 조경공간으로 잠재성을 갖고 있다.