• Journal of Korean Neurosurgical Society
• /
• 제67권1호
• /
• pp.94-102
• /
• 2024

Objective : The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML). Methods : Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR). Results : We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables. Conclusion : The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

• 한국주거학회논문집
• /
• 제24권2호
• /
• pp.97-104
• /
• 2013

This study involves 2 newly built apartment houses which are A with 23 floors as 150 mm slab width and B with 16 floors as 180 mm slab width. The impact was added by tapping and bang machine at the middle floor level of these 2 apartments and the test was arranged in terms of the characteristic of vibration and sound level which transferred to upper or down floors. As a result, impact floor shows the highest value in terms of both sound and vibration level and followed was at down floor of the Impact floor. Also, blocking function for the lightweight and heavyweight floor impact sound level was tested for each room of the apartment A and B including living room, main room, room 1 and 2. As a result, sound blocking function of B apartment was better than that of A and the function was getting worse when the room size is getting smaller.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2006년도 추계학술대회논문집
• /
• pp.622-625
• /
• 2006

This study is a fundamental investigation for standardization of the heavy-weight floor impact measuring method by the impact ball. The distribution chrematistics of floor impact sound level and reverberation time in a receiving room of the testing building for floor impact sound were measured with variations of number and arrangement of the sound-absorbing materials. Total 8 cases were investigated. The distribution of the floor impact sound level($L_{i,\;Fmax}$) was measured at 30 points with same intervals. The absorption coefficient of the room is 0.10 in case of installation of 6 absorbing materials and 0.02 in case of non-installation. The distribution shape of the impact sound pressure level was similar to the result of the bang machine driving at the measured frequency range. However, the overall reduction of the impact sound level investigated in the 125 to 500 Hz shows that the sound absorption characteristics of the receiving room actually affects the result of the heavy-weight impact measurement.

• 해양환경안전학회지
• /
• 제27권2호
• /
• pp.363-368
• /
• 2021

선박 기관실은 기술의 발전으로 인해 자동화 시스템이 향상되었지만, 해상에서는 바람, 파도, 진동, 기기 노후화 등의 다양한 변수가 많아 자동화 시스템에서 계측되지 않는 풀림, 절단, 누유, 누수 등이 발생하므로 기관사는 주기적으로 순찰을 한다. 순찰 시에는 1명의 기관사만 순찰하는 경우도 있으며, 이는 고온고압 및 회전기기가 운전 중인 기관실에서 많은 위험요소를 가지고 있다. 기관사가 순찰 시에는 오감을 활용하며, 특히 시각에 의존한다. 본 논문에서는 로봇이 기관실을 순찰하며 기기의 특이사항을 검출하고 알려주는 기관실 순찰 로봇을 구현하기 위한 선행연구로서 선박 기관실 기기의 이미지를 합성곱 신경망을 이용하여 분류하였다. 선박 기관실의 이미지 데이터 셋을 구성한 후 사전 훈련된 합성곱 신경망 모델로 학습하였다. 학습한 모델의 분류 성능은 높은 재현율을 보였으며, 클래스 활성화 맵으로 이미지를 시각화 하였다. 데이터의 양이 제한적이어서 일반화할 수는 없지만, 각 선박의 데이터를 전이학습으로 학습시키면 적은 시간과 비용으로 각 선박의 특성에 맞는 모델을 구축할 수 있을 것으로 사료된다.

• 한국실내디자인학회논문집
• /
• 제13호
• /
• pp.37-44
• /
• 1997

The aim of this study is to find out the changes that have happened to korea DA-BANG(tea-room). This survey was carried out from 1876 to 1997 and the subject of this study is korea DA-BANGS in Seoul. Following conclusions were obtained from this study. 1) DA-BANG came into being from Koryo ages and more DA-BANGS from 1920's. 2) DA-BANG has changed in the following order : GAEWHA DA-BAHG(that were used to meet, communicate and negotiate foreigners when out country was opening ports), MUNWHA DA-BANG(that were used cultural space for example, exhibitio, display etc.), SEANGWHAL DA-BANG(the place that used a part of living space ; meeting friends to make appointment, etc.), SANGUB DA-BANG(commercial tea-room ; the place that makes money.) 3) Considering early MUNWHA DA-BANG, we can regard the beginning of korea interior architecture as 1920's. 4) The decline of DA-BANG is due to the increase of vending machine, expensive tea, costly rent, employee's dear wages and customer's needs that pursues westernization and convenient life as well as the moodof more comfortable tea-room(for example, fresh air, agreeable mood etc.).

• 반도체디스플레이기술학회지
• /
• 제2권2호
• /
• pp.25-30
• /
• 2003

In the case of a vibration sensitive equipment, it require a vibration free environment to provide its proper function. Especially, lithography and inspection device, which have sub-nanometer class high accuracy and resolution, have come to necessity for producing more improved Giga Class semi conductor wafers. This high technology equipments require very strict environmental vibration criteria in proportion to the accuracy of the manufacturing. In this paper, the dynamic analysis and modal test were performed to evaluate the dynamic properties of the constructing clean room structure. Based on these results, a structural dynamic modification(SDM) were required to satisfiy the vibration allowable limit for pression machine. Therefore, in order to improve the dynamic stiffness of clean room structure, the VSD system which can control the force applied on structure, were adopted and its utility were proved from dynamic test results of the improved structure after a modification work.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2009년도 추계학술대회 논문집
• /
• pp.698-699
• /
• 2009

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2004년도 하계학술발표 논문집
• /
• pp.113-113
• /
• 2004

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2004년도 하계학술발표 논문집
• /
• pp.114-114
• /
• 2004

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2004년도 하계학술발표 논문집
• /
• pp.117-117
• /
• 2004