http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박준혁,이성욱,Park, Junhyeok,Lee, Songwook 한국정보처리학회 2018 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.7 No.7
세계 인구의 고령화가 진행되는 오늘날 노인들을 위한 의료 서비스의 수요는 점차 증가할 것으로 보인다. 특히, 응급실을 방문하는 노인 환자는 일반 환자보다 다양한 질병을 갖고 있거나, 특이한 증상을 호소하는 등 복잡한 의학적, 사회적 및 신체적 문제를 가지고 있는 경우가 많다. 우리는 65세 이상의 응급실을 방문한 노인 환자의 사망률 예측을 위해 연령, 성별, 혈압, 체온, 혈액검사, 주증상명 등의 의료 데이터를 사용하였다. Feed Forward 신경망과 지지벡터기계를 각각 학습하여 사망률을 예측하고 그 성능을 비교하였다. 1개의 은닉층을 사용한 Feed Forward 신경망의 실험결과가 가장 좋았으며, 이 때 F1 점수는 52.0%, AUC는 88.6%이다. 좀 더 좋은 의료 자질을 추출하여 제안 시스템의 성능을 향상시킨다면 응급실에 방문한 노인 환자들을 위한 효과적이고 신속한 의료 자원 배분을 통해 더 좋은 의료 서비스를 제공할 수 있을 것이다. As the global population becomes aging, the demand for health services for the elderly is expected to increase. In particular, The elderly visiting the emergency department sometimes have complex medical, social, and physical problems, such as having a variety of illnesses or complaints of unusual symptoms. The proposed system is designed to predict the mortality of the elderly patients who are over 65 years old and have admitted the emergency department. For mortality prediction, we compare the support vector machines and Feed Forward Neural Network (FFNN) trained with medical data such as age, sex, blood pressure, body temperature, etc. The results of the FFNN with a hidden layer are best in the mortality prediction, and F1 score and the AUC is 52.0%, 88.6% respectively. If we improve the performance of the proposed system by extracting better medical features, we will be able to provide better medical services through an effective and quick allocation of medical resources for the elderly patients visiting the emergency department.
적층 제조된 H13 공구강의 미세조직과 기계적 특성간의 상관관계
안우진,박준혁,이정섭,최중호,정임두,유지훈,김상식,성효경,An, Woojin,Park, Junhyeok,Lee, Jungsub,Choe, Jungho,Jung, Im Doo,Yu, Ji-Hun,Kim, Sangshik,Sung, Hyokyung 한국재료학회 2018 한국재료학회지 Vol.28 No.11
H13 tool steels are widely used as metallic mold materials due to their high hardness and thermal stability. Recently, many studies are undertaken to satisfy the demands for manufacturing the complex shape of the mold using a 3D printing technique. It is reported that the mechanical properties of 3D printed materials are lower than those of commercial forged alloys owing to micropores. In this study, we investigate the effect of microstructures and defects on mechanical properties in the 3D printed H13 tool steels. H13 tool steel is fabricated using a selective laser melting(SLM) process with a scan speed of 200 mm/s and a layer thickness of $25{\mu}m$. Microstructures are observed and porosities are measured by optical and scanning electron microscopy in the X-, Y-, and Z-directions with various the build heights. Tiny keyhole type pores are observed with a porosity of 0.4 %, which shows the lowest porosity in the center region. The measured Vickers hardness is around 550 HV and the yield and tensile strength are 1400 and 1700 MPa, respectively. The tensile properties are predicted using two empirical equations through the measured values of the Vickers hardness. The prediction of tensile strength has high accuracy with the experimental data of the 3D printed H13 tool steel. The effects of porosities and unmelted powders on mechanical properties are also elucidated by the metallic fractography analysis to understand tensile and fracture behavior.
병진운동 자극에서의 HMD 시간지연에 의한 멀미의 역치 고찰
이은강(Eun Kang Lee),최협(Hyeob Choi),김명섭(MyeongSub Kim),박준혁(Junhyeok Park),이용우(Yongwoo Yi),박수경(Sukyung Park) 대한기계학회 2016 대한기계학회 춘추학술대회 Vol.2016 No.12
Virtual reality (VR) related products are newly rising on electronics and entertainment market. Head Mounted Display (HMD) is one of the popular instrument to implement VR environment. However, HMD system has latency which is time delay between user’s motion and display. One of the reason for Motion Sickness (MS) or Simulator Sickness (SS) is known as sensory conflict and when there are more latency in HMD system, resultant sensory conflict will be greater. Therefore HMD manufacturers pursue less latency as possible, but at some point, it costs too much and if perceptional thresholds for latency exist, then amount of latency which is cost-efficient may exist too. Therefore in this study, we measured degree of MS as latency increases, under medial-lateral (ML) direction stimulus to find perceptional threshold of MS and SSQ (Simulator Sickness Questionnaire) was used to measure subjects’ MS/SS. Experiment 1 was done with 8 healthy male subject. Firstly we measured HMD system’s latency and added extra time delay to change latency condition from minimum to around 200 ms. Then sinusoidal motion stimulus with 0.25 Hz frequency and 1.23 m/s^2 peak acceleration was applied. Experiment 2 was done with 5 healthy male subjects and motion stimulus was changed to 0.32 Hz frequency and 2.0 m/s^2 acceleration, with ML movement in VR space is doubled and latency range increased to 400 ms. First experiment’s result did now show any meaningful changes in MS, but second experiment’s result had threshold-like increase in MS near 200~400 ms latency range. However, some subject had very low MS and did not show any changes in MS during experiment. This result may imply that for those are sensitive to MS, under ML directional motion stimulus, perceptional threshold exists around 200~400 ms latency. Also, for those are not sensitive to MS, latency had less or no effect on MS.