• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권2호
• /
• pp.52-61
• /
• 2006

For the detection of moving objects, background subtraction methods are widely used. An adaptive Gaussian mixture model combined with probabilistic learning is one of the most popular methods for the real-time update of the complex and dynamic background. However, probabilistic learning approach does not work well in high traffic regions. In this paper, we Propose a reliable learning method of complex and dynamic backgrounds in high traffic regions.

• 대한음성언어의학회:학술대회논문집
• /
• 대한음성언어의학회 2003년도 제19회 학술대회
• /
• pp.149-149
• /
• 2003

후두질환 감별용 음성 분석방법인 multi-dimensional voice program (MDVP)으로 분석이 불가능할 정도로 주기성이 크게 훼손된 후두암 말기의 음성 에 대하여 효과적인 감별을 하기 위하여, 몇 가지 켑스트럼(cepstrum) 파라미터를 비롯하여, 주기성 및 그 동요 정도, 영교차율(zero-crossing rate, ZCR), 스텍트럼 중심 (spectral centroid, SC) 등 다양한 특징 파라미터를 이용한 감별 실험을 수행하였다. 후두암 감별 실험을 위해 부산대학교 병원 이비인후과에서 수집한 정상 남자 음성 데이터 50개, 양성 후두질환 남자 음성 데이터 50개 및 남성 후두암 환자 음성 데이터 105개를 사용하였다. 음성 데이터는 단모음 /아/ 발성만을 사용하였고, 정상인과 양성후두질환 환자, 그리고 MDVP 분석이 가능한 후두암 환자 음성 데이터 중 2/3는 학습에, 나머지 113은 감별실험에 사용하였다. 후두암 감별을 위한 분류기로는 Gaussian Mixture Model(GMM) 분류기를 사용하였으며, 이때 모델의 복잡도를 표현하는 mixture 수는 1에서 10까지 가변시키면서 가장 좋은 성능을 나타내는 값으로 결정하였다. 또한 모든 실험에서 켑스트럼 분석의 차수는 동일하게 12차로 고정시켰다. (중략)

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2018년도 춘계 학술논문 발표대회
• /
• pp.130-131
• /
• 2018

The compressive strength of concrete is determined by various influencing factors. However, the conventional method for estimating the compressive strength of concrete has been suggested by considering only 1 to 3 specific influential factors as variables. In this study, nine influential factors (W/B ratio, Water, Cement, Aggregate(Coarse, Fine), Fly ash, Blast furnace slag, Curing temperature, and humidity) of papers opened for 10 years were collected at 4 conferences in order to know the various correlations among data and the tendency of data. The selected mixture and compressive strength data were learned using the Deep Learning Algorithm to derive an estimated function model. The purpose of this study is to investigate the effect of the number of hidden layers on the prediction performance in the process of estimating the compressive strength for an arbitrary combination.

• 한국식품영양과학회지
• /
• 제23권1호
• /
• pp.90-97
• /
• 1994

Effect of addition of oil , sucrose, dextrin and oil-sucrose (1 : 1 w/w) mixture on SPI tofu was investigated. The characteristics measured were yield , water holding capacity , textural and organoleptic properties. THe SPI tofufwas prepared by coagulation of soyprotein isolate (SP) suspensino by CaCl$_2$ , CaSo$_4$ an dGDL , followed by compression . Addition of oil to SPI increased the tofu yield and water holding capacity, particulary for those tofu coagulated by CaCl$_2$. Eventhough dextrin addition decreased the yield, it showed the most improving effect on water holding capacity. The tofu prepared by CaSO$_4$coagulant resulted highest in yield and water holding capacity. Hardness was found to be decreased as the oil, sucrose and dextrin added more and adhesiveness, cohesiveness and guminess were also affected. The sensory evaluation showed the SPI tofu prepared by CaSO$_4$ and 10% addition of oil and sucrose mixture to be realtively high in hardness , elasticity and uniformity of the texture.

• 혜화의학회지
• /
• 제13권2호
• /
• pp.123-129
• /
• 2004

We observed the efficacy of natural herbs and mixture in treating atopic dermatitis using anti-human IgE treated Human HMC-I cell model. We selected three herbs, Cynonchum witfordii, Diospyros kaki, Ilite which were used to treat skin disease in Traditional Korea Medicine. Using Human HMC-I cell treated with anti-human IgE, we investigate in vitro whether each herb effects on IL-4, IL-13, TNF-a expression and TNF-a, Histamine secretion value. The results show the possibility that the mixture of three herbs may be better in improving atopic dermatitis condition.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1997년도 봄 학술발표회 논문집
• /
• pp.254-260
• /
• 1997

Chloride-induced corrosion of reinforcement is one of the main factors which cause the deterioration of concrete structures. Durability and service lives of the concrete sturctures should be predicted in order to minimize the risk of corrosion of reinforcement. The objective of this study is to suggest the basis of analytical methods of predicting the corrosion threhold time of concrete structures. Based on the chemistry and physics of chloride ion transport and corrosion process, chloride intrusion with various exposure conditions, variability of diffusivity and transport of pore water in concrete are taken into consideration in applying finite element formulation to the predicion of corrosion threhold time. The effects of main factors on the prediction of chloride intrusion and corrosion threhold time are examined. In addition, after chloride diffusivities of several mixture proportions with different parameters are measured by chloride diffusion test, the exemplary anayses of corrosion threhold time of those mixture proportions are carried out.

• 한국연소학회:학술대회논문집
• /
• 한국연소학회 2015년도 제51회 KOSCO SYMPOSIUM 초록집
• /
• pp.265-266
• /
• 2015

The multi-environment PDF model coupled with flamelet generated manifolds(FGM) has been developed for a large eddy simulation of turbulent partially premixed lifted flame. This approach has a capability to realistically account for the transport and evolution of probability density function for mixture fraction and progress variable with the manageable computational burden. Using the tabulated chemistry, it is possible to track radical distributions which is important to predict autoignition process with the vitiated coflow environment. Numerical results indicate that the present yields the good agreement with experimental data in terms of mixture fraction, temperature, and species mass fractions.

• 한국화재소방학회:학술대회논문집
• /
• 한국화재소방학회 2009년도 춘계학술논문발표회 논문집
• /
• pp.423-430
• /
• 2009

본 논문에서는 ISO-9705 공간의 2/5 스케일 축소모형에 대한 화재 실험에서 측정된 고온 상층부의 연소가스 농도를 혼합분율 개념을 도입하여 분석함으로써 환기부족 상태의 실내화재에서 발생되는 연소생성물의 특성을 파악하고자 한다. 화재실 내부 고온 상층부의 두 지점에서 측정된 잔존 탄화수소, 일산화탄소, 이산화탄소, 산소, 수트(soot) 등의 성분비를 혼합분율의 함수로 내어 분석하였다. 또한 탄화수소 연료의 이상적인 반응에 근거한 상태 관계식과 비교함으로써 환기부족 화재에서 혼합분율 모델의 적용성을 분석하였다. 혼합분율 분석을 이용함으로써 측정된 수많은 데이터들을 화재 크기나 측정 위치에 상관없이 하나의 파라미터에 대해서 정리하여 전체적으로 분석할 수 있었다. 또한 혼합분율 분석에서 수트를 고려하는 것이 분석의 정확성을 크게 향상시킴을 확인할 수 있었다.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2004년도 제23회 추계학술대회 논문집
• /
• pp.282-287
• /
• 2004

Unielement combustion tests were conducted using coaxial bi-swirl injectors. Major experimental parameters were a recess length and a fuel-side swirl chamber. Combustion efficiency mainly depends on a mixing mechanism for the present coaxial swirl injectors. Low-frequency pressure excitations around 200Hz were observed for all injectors. However, dynamic behaviors considerably differ for an external and an internal mixing case controlled by a recess length. The internal mixing induces mixture to be biased at a specific frequency in a mass flow rate, which results in a relatively high amplitude of pressure fluctuations but results for the external mixing case show that fuel and oxidizer mixture flow carries more complicated, multiple wave characteristics due to broad mixing region as well as disintegration and merging phenomena of propellant films.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.88-93
• /
• 2020

Based on the capture-emission energy (CEE) maps of CMOS devices, a physics-informed machine learning model for the bias temperature instability (BTI)-induced threshold voltage shifts and low frequency noise is presented. In order to incorporate physics theories into the machine learning model, the integration of artificial neural network (IANN) is employed for the computation of the threshold voltage shifts and low frequency noise. The model combines the computational efficiency of IANN with the optimal estimation of Gaussian mixture model (GMM) with soft clustering. It enables full lifetime prediction of BTI under various stress and recovery conditions and provides accurate prediction of the dynamic behavior of the original measured data.