• 한국전자통신학회논문지
• /
• 제15권1호
• /
• pp.85-92
• /
• 2020

심층학습은 많은 양의 데이터셋을 학습에 활용하여 객체 분류, 검출, 분할 등의 영상 분석에 탁월한 성능을 나타내고 있다. 본 논문에서는 데이터셋의 종류가 다양한 얼굴 표정인식 데이터셋들을 활용하여 학습 데이터셋의 특성이 심층학습 성능에 영향을 줄 수 있음을 확인하고, 각 학습 데이터셋에 적합한 심층학습 모델의 구성 요소를 설정하는 방법을 제안한다. 제안하는 방법은 심층학습 모델의 성능에 영향을 주는 구성 요소인 활성함수, 그리고 최적화 알고리즘을 유전 알고리즘을 이용하여 선정한다. CK+, MMI, KDEF 데이터셋에 대해서 널리 활용되고 있는 심층학습 모델의 각 구성 요소별 다양한 알고리즘을 적용하여 성능을 비교 분석하고, 유전 알고리즘을 적용하여 최적의 구성 요소를 선정할 수 있음을 시뮬레이션을 통하여 확인한다.

• 한국방사성폐기물학회:학술대회논문집
• /
• 한국방사성폐기물학회 2004년도 학술논문집
• /
• pp.105-114
• /
• 2004

This study investigated the thermal behavior of the nuclear graphite waste generated from the decommissioning of the Korean nuclear research reactor, The first part study investigated the decomposition rate of the nuclear graphite waste up to $1000^{\circ}C$ under various oxygen partial pressures using a thermo-gravimetric analyzer (TGA). Tested graphite waste sample not easily destroyed in the oxygen-deficient condition. However, the gas-solid oxidation reaction was found to be very effective in the presence of oxygen. No significant amount of the product of incomplete combustion was formed even in the limited oxygen concentration of 4% $O_2$. The influence of temperature and oxygen partial pressure was evaluated by the theoretical model analysis of the thermo-gravimetric data. The activation energy and the reaction order of graphite oxidation were evaluated as 128 kJ/mole and 1.1, respectively. The second part of this study investigated the behavior of radioactive elements under graphite oxidation atmosphere using thermodynamic equilibrium model. $^{22}Na$, $^{134}Cs$ and $^{137}Cs$ were found be the semi-volatile elements. Since volatile uranium species can be formulated at high temperatures above $1050^{\circ}C$, the temperature of incinerator furnace should be minimized. Other corrosion/activation products, fission products and uranium were found to be the non-volatile species.

• BMB Reports
• /
• 제38권4호
• /
• pp.373-380
• /
• 2005

For measles viruses, fusion on the cell membrane is an important initial step in the entry into the infected cells. The recent research indicated that hemagglutinin firstly leads the conformational changes in the fusion protein then co-mediates the membrane fusion. In the work, we use the co-immunoprecipitation and pull-down techniques to identify the interactions among fusion protein, hemagglutinin and signaling lymphocyte activation molecule (SLAM), which reveal that the three proteins can form a functional complex to mediate the SLAM-dependent fusion. Moreover, under the confocal microscope, fusion protein and hemagglutinin protein can show the cocapping mediated by the SLAM. So fusion protein not only is involved in the fusion but also might directly interact with the SLAM to be a new fusion-trimer model, which might account for the infection mechanism of measles virus.

• Carbon letters
• /
• 제8권3호
• /
• pp.199-206
• /
• 2007

The activated carbon produced from rubber wood sawdust by chemical activation using phosphoric acid have been utilized as an adsorbent for the removal of Cu(II) from aqueous solution in the concentration range 5-40 mg/l. Adsorption experiments were carried out in a batch process and various experimental parameters such as effect of contact time, initial copper ion concentration, carbon dosage, and pH on percentage removal have been studied. Adsorption results obtained for activated carbon from rubber wood sawdust were compared with the results of commercial activated carbon (CAC). The adsorption on activated carbon samples increased with contact time and attained maximum value at 3 h for CAC and 4 h for PAC. The adsorption results show that the copper uptake increased with increasing pH, the optimum efficiency being attained at pH 6. The precipitation of copper hydroxide occurred when pH of the adsorbate solution was greater than 6. The equilibrium data were fitted using Langmuir and Freundlich adsorption isotherm equation. The kinetics of sorption of the copper ion has been analyzed by two kinetic models, namely, the pseudo first order and pseudo second order kinetic model. The adsorption constants and rate constants for the models have been determined. The process follows pseudo second order kinetics and the results indicated that the Langmuir model gave a better fit to the experimental data than the Freundlich model. It was concluded that activated carbon produced using phosphoric acid has higher adsorption capacity when compared to CAC.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.2
• /
• pp.101-106
• /
• 2006

The geoidal undulations are needed for determining the orthometric heights from the Global Positioning System GPS-derived ellipsoidal heights. There are several methods for geoidal undulation determination. The paper presents a method employing a simple architecture Two Layer Multiquadric-Biharmonic Artificial Neural Network (TLMB-ANN) to approximate an area of 4200 square kilometres quasigeoid surface with GPS-levelling data. Hardy’s Multiquadric-Biharmonic functions is used as the hidden layer neurons’ activation function and Levenberg-Marquardt algorithm is used to train the artificial neural network. In numerical examples five surfaces were compared: the gravimetric geometry hybrid quasigeoid, Support Vector Machine (SVM) model, Hybrid Fuzzy Neural Network (HFNN) model, Traditional Three Layer Artificial Neural Network (ANN) with tanh activation function and TLMB-ANN surface approximation. The effectiveness of TLMB-ANN surface approximation depends on the number of control points. If the number of well-distributed control points is sufficiently large, the results are similar with those obtained by gravity and geometry hybrid method. Importantly, TLMB-ANN surface approximation model possesses good extrapolation performance with high precision.

• Preventive Nutrition and Food Science
• /
• 제1권1호
• /
• pp.41-45
• /
• 1996

This study was conducted to develop the fermentation kinetic model for the prediction of acidity and pH changes in Kimchi as a function of fermentation temperatures. The fitness of the model was evaluated using traditional two-step method and an alternative non-linear regression method. The changes in acidity and pH during fermentation followed the pattern of the first order reaction of a two-step method. As the fermentation temperature increased from 4$^{\circ}C$ to 28, the reaction rates of acidity and pH were increased 8.4 and 7.6 times, respectively. The activation energies of acidity and pH were 16.125 and 16.003kcal/mole. The average activation energies of acidity and pH using a non-linear method were 16.006 by the first order and 15.813 kcal/mole by the zero order, respectively. The non-linear procedure had better fitting 개 experimental data of the acidity and pH than two-step method. The shelf-lives based on the time to reach the 1.0% of acidity were 33.1day at 4$^{\circ}C$ and 2.8 day 28$^{\circ}C$.

• 한국정보시스템학회지:정보시스템연구
• /
• 제28권1호
• /
• pp.115-132
• /
• 2019

Purpose The purpose of this study is to explain the agrophotovolatic system built by the Korea South-East Power Company and to propose methods to activate the agrophotovolatic system for the development of the renewable energy industry. Design/methodology/approach We conducted a three-step simulation in order to design a photovoltaic module, and we built the agrophotovolatic system based on the results of the simulation. Then, we analyzed the monthly generation of power and the rice harvests produced on farmland using the photovoltaic module. Based on the results of the analysis, we proposed institutional improvements to increase the use of the agrophotovolatic system, and we proposed new business models to increase the participation of farmers and business persons. Findings When we compared the agrophotovolastic system with the general photovoltaic system, we found that the agrophotovoltaic system had higher utilization rates and power generation. An analysis of rice produced on farmland using the photovoltaic module showed that more than 80% of the rice produced on general farmland was harvested. We suggested activation plans that involved the revision of the farmland law and the introduction of renewable energy certificate (REC). We also proposed a land lease model and a farmer participation model as two new business models, and we conducted economic evaluations and sensitivity analyses for both models.

• ETRI Journal
• /
• 제46권3호
• /
• pp.538-549
• /
• 2024

A conventional codec aims to increase the compression efficiency for transmission and storage while maintaining video quality. However, as the number of platforms using machine vision rapidly increases, a codec that increases the compression efficiency and maintains the accuracy of machine vision tasks must be devised. Hence, the Moving Picture Experts Group created a standardization process for video coding for machines (VCM) to reduce bitrates while maintaining the accuracy of machine vision tasks. In particular, in-loop filters have been developed for improving the subjective quality and machine vision task accuracy. However, the high computational complexity of in-loop filters limits the development of a high-performance VCM architecture. We analyze the effect of an in-loop filter on the VCM performance and propose a suboptimal VCM method based on the selective activation of in-loop filters. The proposed method reduces the computation time for video coding by approximately 5% when using the enhanced compression model and 2% when employing a Versatile Video Coding test model while maintaining the machine vision accuracy and compression efficiency of the VCM architecture.

• 한국콘텐츠학회논문지
• /
• 제21권3호
• /
• pp.616-625
• /
• 2021

심층신경망은 임의의 함수를 근사화하는 방법으로 선형모델로 근사화한 후에 비선형 활성함수를 이용하여 추가적 근사화를 반복하는 근사화 방법이다. 이 과정에서 근사화의 성능 평가 방법은 손실함수를 이용한다. 기존 심층학습방법에서는 선형근사화 과정에서 손실함수를 고려한 근사화를 실행하고 있지만 활성함수를 사용하는 비선형 근사화 단계에서는 손실함수의 감소와 관계가 없는 비선형변환을 사용하고 있다. 본 연구에서는 기존의 활성함수에 활성함수의 크기를 변화시킬 수 있는 크기 파라메터와 활성함수의 위치를 변화시킬 수 있는 위치 파라미터를 도입한 파라메트릭 활성함수를 제안한다. 파라메트릭 활성함수를 도입함으로써 활성함수를 이용한 비선형 근사화의 성능을 개선시킬 수 있다. 각 은닉층에서 크기와 위치 파라미터들은 역전파 과정에서 파라미터들에 대한 손실함수의 1차 미분계수를 이용한 학습과정을 통해 손실함수 값을 최소화시키는 파라미터를 결정함으로써 심층신경망의 성능을 향상시킬 수 있다. MNIST 분류 문제와 XOR 문제를 통하여 파라메트릭 활성함수가 기존의 활성함수에 비해 우월한 성능을 가짐을 확인하였다.

• 공업화학
• /
• 제27권1호
• /
• pp.56-61
• /
• 2016

본 연구에서는 천연 광물질 촉매를 사용하여 $CO_2$ 석탄가스화의 반응특성을 조사하였다. Meng Tai지역의 갈탄에 4종류의 천연 광물질(Dolomite, Silica sand, Olivine, Kaolin)을 각각 5 wt%로 물리적으로 혼합한 후 Thermogravimetric Analyzer (TGA)를 이용하여 800, 850, $900^{\circ}C$에서 $CO_2$ 가스화 반응을 수행하였다. 실험 결과를 Volumetric Reaction Model (VRM), Shrinking Core Model (SCM), Modified Volumetric Reaction model (MVRM)을 이용하여 분석하였다. MVRM이 가장 적합하였다. 반응 온도가 올라감에 따라 반응속도상수가 커졌다. 천연 광물질 촉매를 사용할 경우가 촉매를 혼합하지 않은 경우에 비해 반응속도상수는 커지고 활성화 에너지 값이 낮아졌다. Silica sand를 혼합한 시료의 활성화 에너지 값은 114.90 kJ/mol로 가장 낮은 활성화 에너지 값을 보였다. Kaolin을 혼합한 시료의 경우 $850^{\circ}C$와 $900^{\circ}C$에서 각각 가장 높은 반응속도상수를 보여주다가 $800^{\circ}C$에서 낮은 반응속도상수를 나타냈다. 따라서 Kaolin을 혼합한 경우, 반응 온도가 높아질수록 $CO_2$ 가스화에 좋은 효과가 있을 것이다.