http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Anodizing과 Burning 공정 혼합으로 표면처리 된 마그네슘합금(AZ31) 안경테 표면의 특성 연구
유재용,임진환,유재인,김진희,박창훈,김기홍,Yu, Jae-Yong,Lim, Jin-Hwan,Yu, Jae-In,Kim, Jin-Hie,Park, Chang-Hun,Kim, Ki-Hong 한국진공학회 2007 Applied Science and Convergence Technology Vol.16 No.3
마그네슘 합금을 Anodizing과 Burning anodizing만으로만 표면 처리했을 때는 표면에 기공이 많이 발생 되었지만, anodizing 처리 후, burning 공정을 추가 하였을 때는 기공이 현저히 줄어들었다. 즉 burning 공정이 추가 되므로 인해 anodizing 공정의 단점인 기공의 봉공처리가 가능함을 알았다. 또한 막 두께도 anodizing 만 처리 했을 때 보다 더 균일하게 성장함을 보았다. During the anodizing and burning anodizing process, appreciable amounts of pores were generated on the surface of magnesium (Mg) alloy which deteriorate the quality of the alloy. However, additional burning process subsequent to the anodizing process reduces the density of pores on the surface. We found that additional burning process can increase the quality of Mg alloy. In addition we found that burning process increases homogeneity of the film thickness as well.
III-V 화합물반도체에서의 He-Ne Laser를 활용한 광 특성 연구
유재용,최경수,최순돈,Yu, Jae-Yong,Choi, K.S.,Choi, Son Don 한국레이저가공학회 2013 한국레이저가공학회지 Vol.16 No.1
The optical properties of III-V compound semiconductor structure was investgated by photoreflectance (PR). The results show two signals at 1.42 and 1.73eV. These are attributed to the bandgap energy of GaAs, AlGaAs, respectively. Also, AlGaAs region showed weak signal. This signal is attributed to carbon or si defect.
Stakeholders’ Requirements for Artificial Intelligence for Healthcare in Korea
유재용,홍성준,이영찬,이경현,이일동,서연이,강미라,김경아,차원철,신수용 대한의료정보학회 2022 Healthcare Informatics Research Vol.28 No.2
Objectives: The outlook of artificial intelligence for healthcare (AI4H) is promising. However, no studies have yet discussedthe issues from the perspective of stakeholders in Korea. This research aimed to identify stakeholders’ requirements forAI4H to accelerate the business and research of AI4H. Methods: We identified research funding trends from the KoreanNational Science and Technology Knowledge Information Service (NTIS) from 2015 and 2019 using “healthcare AI” and relatedkeywords. Furthermore, we conducted an online survey with members of the Korean Society of Artificial Intelligence inMedicine to identify experts’ opinions regarding the development of AI4H. Finally, expert interviews were conducted with 13experts in three areas (hospitals, industry, and academia). Results: We found 160 related projects from the NTIS. The majordata type was radiology images (59.4%). Dermatology-related diseases received the most funding, followed by pulmonarydiseases. Based on the survey responses, radiology images (23.9%) were the most demanding data type. Over half of the solutionswere related to diagnosis (33.3%) or prognosis prediction (31%). In the expert interviews, all experts mentioned healthcaredata for AI solutions as a major issue. Experts in the industrial field mainly mentioned regulations, practical efficacyevaluation, and data accessibility. Conclusions: We identified technology, regulatory, and data issues for practical AI4H applicationsfrom the perspectives of stakeholders in hospitals, industry, and academia in Korea. We found issues and requirements,including regulations, data utilization, reimbursement, and human resource development, that should be addressed topromote further research in AI4H.
등방성-등방성 이종재료에 대한 균열 선단에서의 코스틱스 상에 관한 해석
유재용,문윤배 대구미래대학 2001 論文集 Vol.19 No.1
For the stress analysis in bi-materials, there have been used many theoretical and experimental methods. The experimental methods such as Morie, Photoelasticity, holography and caustics are primarily used by many researchers. In this paper, as the first step to develop the experimental method of caustics in bi-materials, the initial and caustic curve equations are established by introducing the existing stress component equations to the equation of the formation of Caustics and made the program for the generation of caustics in computer.
차량용 CAN Bus Network의 고장진단 기법 연구
유재용 한국기계기술학회 2019 한국기계기술학회지 Vol.21 No.1
The maintenance part of the CAN Bus Networks failure is very difficult due to the difficulty of the inspection and the variety of the cause of the failure. In this study, first, diagnosis process is classified into diagnosis process of non-communication in total and diagnostic process of partial communication failure. Second, based on the past fault code, we analyze the fault by analyzing the nearest fault by analyzing the faults through the array and diagram. And, if the past failure codes can not be analyzed, the CAN logger is used to collect data. After that, it is confirmed that the fault diagnosis can be performed effectively by analyzing and checking it. Through this, troubleshooting by the diagnostic process is suggested and the direction of troubleshooting that the field technicians can use for diagnosis and inspection of CAN Bus Networks is presented.
Machine Learning and Initial Nursing Assessment-Based Triage System for Emergency Department
유재용,정갑용,Ok Soon Jeong,장동경,차원철 대한의료정보학회 2020 Healthcare Informatics Research Vol.26 No.1
Objectives: The aim of this study was to develop machine learning (ML) and initial nursing assessment (INA)-based emergency department (ED) triage to predict adverse clinical outcome. Methods: The retrospective study included ED visits between January 2016 and December 2017 that resulted in either intensive care unit admission or emergency room death. We trained four classifiers using logistic regression and a deep learning model on INA and low dimensional (LD) INA, logistic regression on the Korea Triage and acuity scale (KTAS) and Sequential Related Organ Failure Assessment (SOFA). We varied the outcome ratio for external validation. Finally, variables of importance were identified using the random forest model’s information gain. The four most influential variables were used for LD modeling for efficiency. Results: A total of 86,304 patient visits were included, with an overall outcome rate of 3.5%. The area under the curve (AUC) values for the KTAS model were 76.8 (74.9–78.6) with logistic regression and 74.0 (72.1–75.9) for the SOFA model, while the AUC values of the INA model were 87.2 (85.9–88.6) and 87.6 (86.3–88.9) with logistic regression and deep learning, suggesting that the ML and INA-based triage system result more accurately predicted the outcomes. The AUC values for the LD model were 81.2 (79.4–82.9) and 80.7 (78.9–82.5) for logistic regression and deep learning, respectively. Conclusions: We developed an ML and INA-based triage system for EDs. The novel system was able to predict clinical outcomes more accurately than existing triage systems, KTAS and SOFA.