http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Machine Learning-based Prediction of Relative Regional Air Volume Change from Healthy Human Lung CTs
Eunchan Kim,YongHyun Lee,Jiwoong Choi,Byungjoon Yoo,Kum Ju Chae,Chang-Hyun Lee 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.2
Machine learning is widely used in various academic fields, and recently it has been actively applied in the medical research. In the medical field, machine learning is used in a variety of ways, such as speeding up diagnosis, discovering new biomarkers, or discovering latent traits of a disease. In the respiratory field, a relative regional air volume change (RRAVC) map based on quantitative inspiratory and expiratory computed tomography (CT) imaging can be used as a useful functional imaging biomarker for characterizing regional ventilation. In this study, we seek to predict RRAVC using various regular machine learning models such as extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multi-layer perceptron (MLP). We experimentally show that MLP performs best, followed by XGBoost. We also propose several relative coordinate systems to minimize intersubjective variability. We confirm a significant experimental performance improvement when we apply a subject's relative proportion coordinates over conventional absolute coordinates.
Eunhye Seo,Yesung Lee,Eunchan Mun,Dae Hoon Kim,Youshik Jeong,Jaehong Lee,Jinsook Jeong,Woncheol Lee 대한직업환경의학회 2022 대한직업환경의학회지 Vol.34 No.-
Background: Long working hours are known to account for approximately one-third of the total expected work-related diseases, and much interest and research on long working hours have recently been conducted. Additionally, as the prevalence of prediabetes and the high-risk group for diabetes are increasing worldwide, interest in prediabetes is also rising. However, few studies have addressed the development of type 2 diabetes and long working hours in prediabetes. Therefore, the aim of this longitudinal study was to evaluate the relationship between long working hours and the development of diabetes in prediabetes. Methods: We included 14,258 prediabetes participants with hemoglobinA1c (HbA1c) level of 5.7 to 6.4 in the Kangbuk Samsung Cohort Study. According to a self-reported questionnaire, we evaluated weekly working hours, which were categorized into 35–40, 41–52, and > 52 hours. Development of diabetes was defined as an HbA1c level ≥ 6.5%. Hazard ratios (HRs) and 95% confidence intervals (CIs) for the development of diabetes were estimated using Cox proportional hazards analyses with weekly working 35–40 hours as the reference. Results: During a median follow-up of 3.0 years, 776 participants developed diabetes (incidence density, 1.66 per 100 person-years). Multivariable-adjusted HRs of development of diabetes for weekly working > 52 hours compared with working 35–40 hours were 2.00 (95% CI: 1.50–2.67). In subgroup analyses by age (< 40 years old, ≥ 40 years old), sex (men, women), and household income (< 6 million KRW, ≥ 6 million KRW), consistent and significant positive associations were observed in all groups. Conclusions: In our large-scale longitudinal study, long working hours increases the risk of developing diabetes in prediabetes patients.
차량용 램프 내열 예측 프로그램 개발을 위한 열전달 실험
이재진(Jae-jin Lee),지은찬(Eunchan Ji),우지호(Jiho Woo),최동녁(Dongnyeok Choi),김영완(Youngwan Kim),최승(Seung Choi),박유라(Yura Park),이진구(Jingoo Lee),이권영(Kwon-Yeong Lee) 한국자동차공학회 2020 한국자동차공학회 부문종합 학술대회 Vol.2020 No.7
The heat from bulbs of automotive lamp is transferred to internal materials in the form of conduction, convection and radiation. The transferred heat causes deformation of lamp materials when it exceeds the heat-resistance limits. To reduce the effort from trial and error by failing the heat-resistance test after designing and producing lamps, using a simulation program is necessary at the design stage. A new in-house heat-resistance prediction program with less errors is going to be developed, which covers conduction, convection and radiation based on experiments. The experimental facility is designed, according to variables, such as bulb powers, heat-resistant distance, boundary conditions, etc. Key parameters were set to select and perform experimental cases. The surface average temperatures were calculated, and the temperature distribution patterns of each surface were found. As a result of the experiment, the temperature distribution of all data values was different at temperature, but the shape was very similar. This shows similar heat transfer patterns throughout the data. In the case of forced convection, the temperature distribution was lower depending on the atmosphere temperature, bulb distance, and box size compared to the natural convection. By securing reliable data, algorithm development and verification program based on the experiment is possible.
Mobile Beacon-Based 3D-Localization with Multidimensional Scaling in Large Sensor Networks
Eunchan Kim,Sangho Lee,Chungsan Kim,Kiseon Kim IEEE 2010 IEEE communications letters Vol.14 No.7
<P>Localization is essential in wireless sensor networks to handle the reporting of events from sensor nodes. For 3-D applications, we propose a mobile beacon-based localization using classical multidimensional scaling (MBL-MDS) by taking full advantage of MDS with connectivity and measurements. To further improve location performance, MBL-MDS adopts a selection rule to choose useful reference points, and a decision rule to prevent a failure case due to reference points placed on the same plane. Simulation results show improved performance of MBL-MDS in terms of location accuracy and computation complexity.</P>
구조물 정보 제공을 위한 위치기반의 증강현실(AR)에 대한 연구: 캠퍼스 중심으로
나은찬 ( Eunchan Na ),이영재 ( Youngjae Lee ),김현규 ( Hyeongyu Kim ),최성률 ( Seongryul Choi ),김영종 ( Youngjong Kim ) 한국정보처리학회 2019 한국정보처리학회 학술대회논문집 Vol.26 No.1
4차 산업 혁명의 핵심기술로 손꼽히는 AR을 이용하여 캠퍼스 이용에 유용한 정보를 제공한다. 사물 인식, 위치기반의 AR구현 방식을 사용하며 AR네비게이션 방식으로 입체화된 길안내 정보를 제공한다. AR을 통해 제공되는 정보는 이미지 혹은 텍스트가 될 수 있고 3D모델, 미디어 그리고 이들의 모든 조합의 형태를 취할 수 있다.