http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Moon, Heeyeon,Jeong, Kihoon,Kwak, Moo Jin,Choi, Siyoung Q.,Im, Sung Gap American Chemical Society 2018 ACS APPLIED MATERIALS & INTERFACES Vol.10 No.38
<P>A new fabrication method for an ultrathin (500 nm thick) pressure-sensitive adhesive (PSA) was demonstrated by utilizing a series of in situ cross-linked viscoelastic copolymer films. Viscoelastic films composed of poly(2-hydroxyethyl acrylate-<I>co</I>-2-ethylhexyl acrylate) were synthesized successfully in a one-step manner by an initiated chemical vapor deposition (iCVD) process, where free-radical polymerization is triggered in the vapor phase either by heat or UV, or a combination of both. In particular, the photoinitiated chemical vapor deposition method generated a highly cross-linked polymer film, whereas cross-linking of the copolymer film was suppressed greatly in the conventional thermal iCVD method. A combination of thermal and photoinitiated chemical vapor deposition could regulate the cross-linking density of the copolymer films. We controlled the cross-linking density of the copolymer films to exhibit a viscoelastic property so that they would readily adhere to various kinds of substrates with only 500 nm thick copolymer PSA. The adhesion performance of the PSA was systematically optimized by tuning the copolymer composition as well as the cross-linking density, and consequently a high shear strength of more than 85.2 ± 5 N/cm<SUP>2</SUP> was achieved despite the 500 nm thickness. In addition, the PSA was completely transparent. We expect that the ultrathin PSAs developed in this work will be utilized widely for the realization of various soft electronic devices, which usually require strong adhesion, tunable viscoelastic properties, and optical transparency.</P> [FIG OMISSION]</BR>
( Kihoon Lee ),( Nammee Moon ) 한국정보처리학회 2021 Journal of information processing systems Vol.17 No.3
This paper proposes a digital signage system based on an intelligent recommendation model. The proposed system consists of a server and an edge. The server manages the data, learns the advertisement recommendation model, and uses the trained advertisement recommendation model to determine the advertisements to be promoted in real time. The advertisement recommendation model provides predictions for various products and probabilities. The purchase index between the product and weather data was extracted and reflected using correlation analysis to improve the accuracy of predicting the probability of purchasing a product. First, the user information and product information are input to a deep neural network as a vector through an embedding process. With this information, the product candidate group generation model reduces the product candidates that can be purchased by a certain user. The advertisement recommendation model uses a wide and deep recommendation model to derive the recommendation list by predicting the probability of purchase for the selected products. Finally, the most suitable advertisements are selected using the predicted probability of purchase for all the users within the advertisement range. The proposed system does not communicate with the server. Therefore, it determines the advertisements using a model trained at the edge. It can also be applied to digital signage that requires immediate response from several users.
상관관계 분석을 통한 소비예측 시 필요 요소 도출 및 LSTM을 이용한 소비예측 모델
이기훈 ( Kihoon Lee ),김진아 ( Jinah Kim ),문남미 ( Nammee Moon ) 한국정보처리학회 2019 한국정보처리학회 학술대회논문집 Vol.26 No.1
오프라인 소비자의 의사결정은 크게 라이프스타일, 동기, 개성, 학습 등 개인적인 영향요인과 문화, 기후, 가족 등 기타 상황적 요인을 포함하는 환경적 영향요인에 의해 결정된다. 이러한 요인들을 입력 값으로 하는 다양한 딥러닝 모델을 이용한 소비예측 연구들이 진행되고 있다. 딥러닝을 이용한 예측모델을 사용하기 위해서는 먼저 요인들이 의사를 결정하는데 있어 얼마나 상관관계가 있는지 파악하는 작업이 중요하다. 본 논문에서는 이를 위해 다양한 상관관계 분석모델을 이용해 소비 의사결정 요소 중 기후, 문화와 같은 상황적 요인과 소비와의 상관관계를 도출하고, 기후, 문화를 대변하는 미세먼지 데이터와, SNS 버즈량 데이터와 소비데이터를 학습하는 소비예측 LSTM모델을 제안하고자 한다.
몰입도와 생체신호 간 상관관계분석을 위한 스마트기기 사용자 군집방법설계
이기훈 ( Kihoon Lee ),김진아 ( Jinah Kim ),문남미 ( Nammee Moon ) 한국정보처리학회 2018 한국정보처리학회 학술대회논문집 Vol.25 No.1
본 논문은 몰입도와 생체신호 간의 상관관계를 분석하기 위한 데이터 수집 및 데이터 군집에 대한 연구이다. 스마트기기를 이용해 걸음 수, 심박 수, 수면깊이와 같은 생체 데이터수집과, 수집한 데이터를 토대로 사용자의 행동패턴을 분석한다. 사용자 생체 데이터를 k-means 클러스터링과 계층적 클러스터링을 혼합해 이용해 앞서 나열한 데이터와 사용자의 집중도와 연관관계분석이 최종 목표이다.
문혜정(Moon, Hyejung),이기훈(Lee, Kihoon) 전북대학교 산업경제연구소 2020 아태경상저널 Vol.12 No.3
본 연구는 2000∼2016년 기간중 우리나라 제조업의 에너지 효율 변화에 미친 요인들과 그 영향의 정도를 LMDI 분해법으로 추정한다. 특히 제조업을 에너지 고집약, 중집약, 저집약 등 3개 그룹으로 나누어 LMDI 다계층 모형을 활용하였다. 그 결과 분석기간 중 구조변화 효과와 에너지 집약도 효과는 제조업 에너지 집약도 개선에 기여한 것으로 나타났다. 그룹 별로는 에너지 저집약 그룹, 중집약 그룹의 에너지 효율이 크게 개선된 것으로 나타났다. 반면 에너지 고집약 그룹은 효율 개선 정도가 미미하였다. 따라서 향후 제조업부문의 에너지 효율화 정책은 에너지 집약산업에 초점을 두는 것이 바람직할 것으로 평가된다. 또 본 연구는 연구방법론상에 있어서 다계층 모형과 단일계층 모형간의 관계를 규명하고 그룹 내부 효과와 그룹간 효과를 구분하여 파악할 수 있음을 보였다. This study examines the energy efficiency change of Korean manufacturing industry from 2000 to 2016 by LMDI decomposition method. In particular, we focused on the change of energy intensity and compared and analyzed energy high-intensive, midium-intensive and low-intensive groups using LMDI multi-level model. As a result, the structural change effect and energy intensity effect contributed to improvement of energy intensity during the analysis period. While the energy efficiency of the low-energy and midium-energy groups was significantly improved, that of the energy high-intensive group was relatively minimal. Therefore, it is recommended that the energy efficiency policy of the manufacturing sector should be focused on the energy-intensive industries. This study shows that the LMDI multi-level model is useful for distinguishing between-group effect and within-group effect and for identifying the relationship between single level model and multi-level model.
User Modeling Using User Preference and User Life Pattern Based on Personal Bio Data and SNS Data
( Hyejin Song ),( Kihoon Lee ),( Nammee Moon ) 한국정보처리학회 2019 Journal of information processing systems Vol.15 No.3
The purpose of this study was to collect and analyze personal bio data and social network services (SNS) data, derive user preference and user life pattern, and propose intuitive and precise user modeling. This study not only tried to conduct eye tracking experiments using various smart devices to be the ground of the recommendation system considering the attribute of smart devices, but also derived classification preference by analyzing eye tracking data of collected bio data and SNS data. In addition, this study intended to combine and analyze preference of the common classification of the two types of data, derive final preference by each smart device, and based on user life pattern extracted from final preference and collected bio data (amount of activity, sleep), draw the similarity between users using Pearson correlation coefficient. Through derivation of preference considering the attribute of smart devices, it could be found that users would be influenced by smart devices. With user modeling using user behavior pattern, eye tracking, and user preference, this study tried to contribute to the research on the recommendation system that should precisely reflect user tendency.
Passive Bypass Using Anthron Tube in Adult Living Donor Liver Transplantation
SungGyu Lee,Shin Hwang,KiHoon Kim,ChulSoo Ahn,KwangMin Park,YoungJoo Lee,DeokBog Moon,ChongWoo Chu,HyunSeong Yang,SungHoon Cho,KiBong Oh,TaeYong Ha,KiWon Song,YunSik Yu,PyungChul Min 대한외과학회 2002 대한외과학회 학술대회 초록집 Vol.2002 No.10