• 터널과지하공간
• /
• 제30권6호
• /
• pp.540-550
• /
• 2020

최근 AI 기술의 발전과 정립으로 자동화 분야에서 머신러닝 기법의 활용이 활발하게 이루어지고 있다. 머신러닝 기법의 활용에 있어 중요한 점은 데이터 특성에 따라 적합한 알고리즘이 존재한다는 점이며, 머신러닝 기법 적용을 위한 데이터세트의 분석이 필요하다. 본 연구에서는 다양한 머신러닝 기법을 기반으로 하천 하부의 토사지반을 통과하는 토압식 쉴드TBM 터널 구간의 지반정보와 굴진정보를 사용하여 토압식 쉴드TBM의 굴진율을 예측하였다. 선형회귀모델에서 모델의 통계적인 유의성과 다중공선성에서는 문제가 없었으나 결정계수가 0.76으로 나타났고 앙상블 모델과 서포트 벡터 머신에서는 0.88이상의 예측성능을 보여, 분석한 데이터세트에서 토압식 쉴드TBM 굴진성능예측에 적합한 모델은 서포트 벡터 머신임을 알 수 있었다. 현재 도출된 결과로 볼 때, 토압식 쉴드TBM의 기계데이터와 지반정보가 포함된 데이터를 활용한 굴진성능 예측 모델의 적합성은 높다고 판단된다. 추가적으로 지반조건의 다양성과 데이터양을 늘리는 연구가 필요한 것으로 판단된다.

• 한국정밀공학회지
• /
• 제21권8호
• /
• pp.112-119
• /
• 2004

This paper develops a computer model of a cabover type large truck for estimating the effects of the mounted method of frame on handling performance. The computer model considers two mounted methods of frame; flange mounted and web mounted. Frame is modeled by finite elements using MSC/NASTRAN in order to consider the flexibility of frame. The reliability of the developed computer model is verified by comparing the actual vehicle test results with the simulation results. The actual vehicle test is performed in a double lane change course, and lateral acceleration, yaw rate, and roll angle are measured. To estimate the effects of the mounted method of frame on handling performance, simulations are performed with the flange mounted and web mounted frame. Simulation results show that the web mounted frame＇s variations of roll angle, lateral acceleration, and yaw rate are larger than the flange mounted frame＇s variations, especially in the high test velocity and the second part of the double lane course. Also, simulation results show that the web mounted frame＇s tendencies of roll angle, lateral acceleration, and yaw rate advance the flange mounted frame＇s tendencies, especially in the high test velocity and the second part of the double lane course.

• 한국컴퓨터정보학회논문지
• /
• 제15권2호
• /
• pp.127-134
• /
• 2010

연속 어휘 인식 확률 분포의 공유 방법에서는 사용될 모델 파라미터들의 초기 추정치를 생성하기 위한 각 문맥들에 대한 음소 데이터가 반드시 필요하지만 이들 음소 데이터에 대한 모델을 구성할 수 없는 단점으로 가우시안 모델의 정확성을 확보하지 못한다는 단점이 있다. 이를 개선하기 위하여 확률 분포의 혼합 가우시안 모델을 최적화하고, 음소 단위로 데이터를 탐색을 지원하는 형상 형성 시스템을 제안한다. 본 논문의 형상 형성 시스템은 확장 facet 분류를 이용하여 사용자에게 음소 단위의 형상 형성 정보를 제공하므로 가우시안 모델의 정확성을 제공한다. 본 논문에서 제안한 시스템을 적용한 결과 시스템 성능에서 어휘 종속 인식률은 98.31%, 어휘 독립 인식률은 97.63%의 인식률을 나타내었다.

• East Asian mathematical journal
• /
• 제39권5호
• /
• pp.493-503
• /
• 2023

Tendency prediction of daily confirmed cases is an important issue for public health authorities. To protect the tendency, we estimate the transmission rate of stochastic SEIR model for COVID-19 in Korea using particle Markov chain Monte Carlo method. The results show that the increasing and decreasing tendency of estimated transmission rate appear one or two days in advance compared to daily incidence cases, and as time evolves the standard deviation of the estimates of transmission rate reduces. Since ten months have passed since the first incident case of COVID-19 in Korea, we expect to forecast the tendency of daily confirmed cases for the next one or two days more accurately using our method.

• 한국터널지하공간학회 논문집
• /
• 제19권6호
• /
• pp.857-870
• /
• 2017

사회기반시설의 지중화로 인하여 쉴드 TBM 적용이 점차 확대되고 있는 추세다. 합리적인 공기기간 및 공사비 산정을 위해 쉴드 TBM의 실굴진율을 정확하게 예측하는 것은 매우 중요한 사안이라 할 수 있다. 이러한 이유로 국내에서는 지반의 물성을 합리적으로 반영한 쉴드 TBM의 실굴진율 예측모델이 필요한 상황이다. 본 연구는 쉴드 TBM의 순굴진율 산정을 위해 현장 데이터베이스를 기반으로 현장관입지수의 통계적 예측절차를 모듈화 하였다. 출력인자로 현장관입지수를 선정하였고, 비정상치 제거 및 전처리 그리고 최상 부분집합선택이 고려된 능형회귀를 적용한 예측시스템을 모듈에 포함하였다. 또한 현장 굴진 데이터를 활용하여 예측모델의 적용성을 확인하였다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회B
• /
• pp.2518-2523
• /
• 2007

In this paper, thermo-flow characteristics of an outer-rotor type of a BLDC motor are numerically analyzed using three-dimensional turbulence modeling. In an advance design of BLDC motor, cooling blades and holes are preferred for the enhanced cooling performances. Rotating the blades and holes generates axial air flow passing through stator slots, which cools down stator by forced convection. For the present study, a new design of the BLDC motor has been developed and major design parameters such as the arrangement of cooling holes, the area of cooling holes, and cooling blades and the cooling blade angle, are analyzed for the enhanced convective heat transfer rate. It is found that the convective heat transfer rate of the new BLDC motor model is increased by about 8.1%, compared to that of the reference model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.385-405
• /
• 2019

High Efficiency Video Coding (HEVC) enables significantly improved compression performance relative to existing standards. However, the advance also requires high computational complexity. To accelerate the intra prediction mode decision, a minimum risk Bayesian classification framework is introduced. The classifier selects a small number of candidate modes to be evaluated by a rate-distortion optimization process using the sum of absolute Hadamard transformed difference (SATD). Moreover, the proposed method provides a loss factor that is a good trade-off model between computational complexity and coding efficiency. Experimental results show that the proposed method achieves a 31.54% average reduction in the encoding run time with a negligible coding loss of 0.93% BD-rate relative to HEVC test model 16.6 for the Intra_Main common test condition.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제6권2호
• /
• pp.380-391
• /
• 2014

In this study, the scale effect on the performance of the podded propeller of tractor type is investigated. Turbulent flow computations are carried out for Reynolds numbers increasing progressively from model scale to full scale using the CFD analysis. The result of the flow calculation for model scale Reynolds numbers agrees well with that of the experiment of a large cavitation tunnel. The existing numerical analysis indicates that the performance of the podded propeller blades is mainly influenced by the advance coefficient and relatively little by the Reynolds number. However, the drag of pod housing with propeller in operation is different from that of pod housing without propeller due to the acceleration and swirl of propeller slipstream which is altered by propeller loading as well as the pressure recovery and friction according to Reynolds number, which suggests that the pod housing drag under the condition of propeller in operation is the key factor of the scale effect on the performance between model and full scale podded propellers. The so called 'drag ratio', which is the ratio of pod housing drag to total thrust of podded propeller, increases as the advance coefficient increases due to accelerated flow in the slipstream of the podded propeller. However, the increasing rate of the drag ratio reduces continuously as the Reynolds number increases from model to full scale progressively. The contribution of hydrodynamic forces, which acts on the parts composed of the pod housing with propeller operating in various loading conditions, to the thrust and the torque of the total propeller unit are presented for a range of Reynolds numbers from model to full scales.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2019년도 춘계 학술논문 발표대회
• /
• pp.45-46
• /
• 2019

Accident rate in domestic construction industry has been increased rapidly in every year. In particular, the rate of death has been shown very high compared with other industries. It means that safety activities performed by government is not effective in reducing the rate of accident. To solve these problems, the risk factors should be predicted in advance, controlled, monitored and managed from start of project to end of project. However, most studies have been conducted by using frequency of occurrence of accident and only listed the importance of risk. Therefore, the objective of this study is to provide basic material to develop risk quantifying model for human accidents on construction site in South Korea. In the future, it is expected to be used as a reference of study on developing safety mangement checklist in construction industry and model for forecasting accident.

• 한국수산과학회지
• /
• 제36권2호
• /
• pp.178-186
• /
• 2003

Seasonal variation of phytoplankton was investigated with surface mixed layer ecosystem model in the East Sea. The model consisted of four compartments (phytoplankton, zooplankton, nutrient, detritus) forced by mixed layer depths, photosynthetically available radiation and nutrient concentrations. From model results we estimated entrainment rate $2.5-4.0\;m{\cdot}day^{-1}$ to reproduce the two annual blooms, and reproduced seasonal variation of phytoplankton at southern and northern regions by the difference of surface winter mixed layer depth (MLD) using the entrainment rate value $3.0\;m{\cdot}day^{-1}$. The spring blooms in the southern and northern regions closely related to deepening of a winter surface MLD. In the southern region where MLD was shallow and phytoplankton spring bloom occurs one month in advance to the northern region where MLD was deep. The amount of light increases within the MLD during the onset of stratification and water temperature increases faster in spring in the southern region than the northern region. Decrease of phytoplankton was mainly affected by zooplankton grazing in the southern region and by nutrient exhaustion in the northern region. The fall bloom in the two regions was caused by the nutrient availability and entrainment on the phytoplankton.