http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
서비스 이용자의 지각된 위험이 AI추천시스템 이용의도에 미치는 영향
서상윤 ( Seo¸ Sangyun ) 경희대학교 경영연구원 2021 의료경영학연구 Vol.15 No.4
This study examines the intention to use, and the willingness to pay for an AI treatment recommendation system according to the disease severity and risk attitude of medical service users. To test the effects of disease severity and risk attitude on the medical service users’ intention to use AI treatment recommendation system, we compared the users’ intention and willingness to pay for the treatment on the assumption that they had mild disease such as a cold or severe disease such as a cancer. We also measured their risk-taking attitudes and categorized them into high-and low-risk-taking groups. Based on the results, respondents had a higher intention to use and willingness to pay for the AI treatment recommendation system for severe diseases than for mild ones. Furthermore, respondents with high risk-taking attitudes were more willing to use the AI treatment recommendation system than those with low risk-taking attitudes. The risk-taking attitude moderated the effect of disease severity on the intention to use and willingness to pay, as in the case of severe disease , the respondents had a strong intention to use it regardless of their risk-taking attitude, while in the case of mild diseases, the intention differed between the low and the high risk-taking groups.
Resonant X-ray Scattering Study of Anisotropic Charge Distribution of Gd Ions in GdB4
Sangyun Hwang,Byeong-Gwan Cho,Tae-Young Koo,Sungdae Ji,Beongki Cho,Ki Bong Lee 한국물리학회 2020 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.76 No.6
Temperature dependence of anisotropic tensor susceptibility (ATS) scattering intensities of GdB4 were measured near L-edges of Gd to investigate how spin ordering affects ATS. ATS scattering intensities for L2- and L3-edges show different temperature dependence below TN. At L3-edge the intensities reflect spin order parameter while intensities at L2-edge do not show noticeable change. The difference is explained in terms of spin-orbit coupling and isotropic distribution of spin-polarized 5d states of Gd ions. Above TN ATS scattering intensities demonstrate that thermal motions enhance charge distribution anisotorpy of Gd 5d states in paramagnetic phase.
Validation of an Acoustic Finite Element Model of an Automobile Passenger Compartment
Sangyun Lee(이상윤),Joohyung Lee(이주형),Kwangseo Park(박광서),Youngho Kim(김영호) 한국자동차공학회 2010 한국자동차공학회 부문종합 학술대회 Vol.2010 No.5
An acoustic finite-element model of an automobile passenger compartment that represents the more complicated vehicle interior acoustic characteristics is developed and experimentally assessed using loudspeaker excitation. The acoustic finite-element model represents the passenger compartment cavity, trunk compartment cavity, front and rear seats, parcel shelf, door volumes, and IP (Instrument Panel) volume. The model accounts for the coupling between the compartment cavity and trunk cavity through the rear seat and parcel shelf, and the coupling between the compartment cavity and the door and IP panel volumes. Modal analysis tests of a vehicle were conducted using loudspeaker excitation to identify the compartment cavity modes and sound pressure response at a large number of interior locations. Comparisons of the predicted versus measured mode frequencies, mode shapes, and sound pressure response at the occupant ear locations are made to assess the accuracy of the model to 400 Hz.
Extended Siamese Convolutional Neural Networks for Discriminative Feature Learning
Sangyun Lee,홍성준 한국지능시스템학회 2022 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.22 No.4
Siamese convolutional neural networks (SCNNs) has been considered as among the bestdeep learning architectures for visual object verification. However, these models involvethe drawback that each branch extracts features independently without considering the otherbranch, which sometimes lead to unsatisfactory performance. In this study, we propose a newarchitecture called an extended SCNN (ESCNN) that addresses this limitation by learningboth independent and relative features for a pair of images. ESCNNs also have a featureaugmentation architecture that exploits the multi-level features of the underlying SCNN. Theresults of feature visualization showed that the proposed ESCNN can encode relative anddiscriminative information for the two input images at multi-level scales. Finally, we appliedan ESCNN model to a person verification problem, and the experimental results indicate thatthe ESCNN achived an accuracy of 97.7%, which outperformed an SCNN model with 91.4%accuracy. The results of ablation studies also showed that a small version of the ESCNNperformed 5.6% better than an SCNN model.
Sangyun Kim,Heui Jae Pahk 한국광학회 2018 Current Optics and Photonics Vol.2 No.2
In semiconductor manufacturing, critical dimensions indicate the features of patterns formed by the semiconductor process. The purpose of measuring critical dimensions is to confirm whether patterns are made as intended. The deposition process for an organic light emitting diode (OLED) forms a luminous organic layer on the thin-film transistor electrode. The position of this organic layer greatly affects the luminescent performance of an OLED. Thus, a system for measuring the position of the organic layer from outside of the vacuum chamber in real-time is desired for monitoring the deposition process. Typically, imaging from large stand-off distances results in low spatial resolution because of diffraction blur, and it is difficult to attain an adequate industrial-level measurement. The proposed method offers a new superresolution single-image using a conversion formula between two different optical systems obtained by a deep learning technique. This formula converts an image measured at long distance and with low-resolution optics into one image as if it were measured with high-resolution optics. The performance of this method is evaluated with various samples in terms of spatial resolution and measurement performance.