• 한국지능시스템학회논문지
• /
• 제17권6호
• /
• pp.731-737
• /
• 2007

본 논문에서는 계층적인 퍼지추론 기법을 기반으로 한 영양상태 분석 시스템을 제안한다. 제안된 방법에서 계층적인 퍼지 추론 기법은 각 개인의 비만정도와 과거의 영양상태 그리고 식습관 패턴으로부터 영양상태의 변화과정을 분석하기 위해서 사용되었다. 또한 계층 퍼지추론 시스템에서 각 계층의 추론결과들의 신뢰성을 향상시키기 위해서 이전 계층으로부터 얻은 비퍼지화된 추론결과들의 통계적인 정보를 사용하여 다음 계층의 퍼지 소속구간들의 선택방법에 대해서도 논의하였다. 제안된 시스템의 효과성을 보이기 위해서, 65세 이상의 노인 113명의 신체계측 정보와 생화학적 검사로부터 획득한 정보 그리고 영양 밀도 지수(INQ)로부터 영양상태를 평가하였다.

• 한국환경생태학회지
• /
• 제8권1호
• /
• pp.58-67
• /
• 1994

Object of this study is to suggest the plan for natural vegetation restoration and management by ecological approach. The concept of biotope planting technique was introduced in order to restore the natural vegetation in the northern part of Mt. Nam in Seoul, and Quercus mongolica forests was surveyed so as to obtain the basic data. This study focused on the vegetational context between northern part of Mt. Nam and develop-reserved site. The results are following ; 1. It is suitable to plant 25~30 trees in $100\m^2$ with trees of DBH 10cm and below at intervals of about 2m in canopy layer. In the case of subtree layer of DBH 2cm, about 30 trees were planted at an Intervals of 1.5~2m around in $100\m^2$. 2. In the last step of nature vegetation restoration, it is desiable that canopy density is $5/100\m^2$ and 녀btree one is 10~20/$100\m^2$. 3. Management plans was proposed to use the native species of Mt. Nam around and to investigate the ecological situation once a year such as species introduce, dead-tree, soil, fauna etc.

• Journal of Electrical Engineering and Technology
• /
• 제12권3호
• /
• pp.1292-1298
• /
• 2017

In this paper, we represent a nonlinear identification of electronic brake pedal behavior in the brake-by-wire (BBW) system based on hybrid group method of data handling (GMDH) and genetic algorithm (GA). A GMDH is a kind of multi-layer network with a structure that is determined through training and which can express nonlinear dynamics as a mathematical model. The GA is used in the GMDH, enabling each neuron to search for its optimal set of connections with the preceding layer. The results obtained with this hybrid approach were compared with different nonlinear system identification methods. The experimental results showed that the hybrid approach performs better than the other methods in terms of root mean square error (RMSE) and correlation coefficients. The hybrid GMDH/GA approach was effective for modeling and predicting the brake pedal system under random braking conditions.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.136-141
• /
• 2022

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (𝛽) and alpha (𝛼), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.

• 한국지반공학회논문집
• /
• 제23권3호
• /
• pp.15-24
• /
• 2007

본 논문은 도로기초 입상재료의 응력의존적인 특성을 고려한 응력의존적 재료 상수의 적용을 통하여 층 변형예측을 수행하는 간편한 방식을 소개한다. 이 방법은 Unbound지반재료에 대하여 회복변형과 영구변형을 구분하여 고려하며 두 변형의 상호작용을 적용하지 않는 방식이다. 그 결과 회복변형 탄성계수와 포와송비를 포함한 해석모형은 상호작용이 고려되지 않아도 현장에서의 도로기초 변형을 예측할 수 있음을 잘 보여주고 있다. 또한 응력의존 탄성계수와 응력의존 포와송 비 모형에서 가장 영향을 많이 미치는 계수를 찾기 위하여 민감도분석을 실시하였다. 이러한 분석결과를 토대로 응력의존에 의하여 변형 예측시 나타나는 경향을 살펴보았다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2006년도 하계학술대회 논문집 Vol.7
• /
• pp.261-262
• /
• 2006

High temperature superconducting coated conductor has multi-layer structure of protecting layer/superconducting layer/buffer layer/metallic substrate. The buffer layer consists of multi layer, and the architecture most widely used in RABiTS approach is $CeO_2$(cap layer)/YSZ(diffusion barrier layer)/$CeO_2$(seed layer). Multi-buffer layer deposition required many times and process. Therefore single buffer layer deposition study reduce 2G HTS manufacture efforts. Evaporation technique for single buffer deposition method is used for the $CeO_2$ layer. $CeO_2$ single buffer film could be achieved in the chamber. Detailed deposition conditions (temperature and partial gas pressure of deposition) were investigated for the rapid growth of high quality $CeO_2$ single buffer film.

• 한국재료학회:학술대회논문집
• /
• 한국재료학회 2006년도 추계학술발표대회 및 제11회 신소재 심포지엄
• /
• pp.3.2-3.2
• /
• 2006

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1301-1306
• /
• 2018

Artificial intelligence is one of the key technologies of the Fourth Industrial Revolution. This paper introduces the diverse kinds of approaches to subjects that tackle diverse kinds of research fields such as model-based MS approach, deep neural network model, image edge detection approach, cross-layer optimization model, LSSVM approach, screen design approach, CPU-GPU hybrid approach and so on. The research on Superintelligence and superconnection for IoT and big data is also described such as 'superintelligence-based systems and infrastructures', 'superconnection-based IoT and big data systems', 'analysis of IoT-based data and big data', 'infrastructure design for IoT and big data', 'artificial intelligence applications', and 'superconnection-based IoT devices'.

• Structural Engineering and Mechanics
• /
• 제58권3호
• /
• pp.555-576
• /
• 2016

In this paper an efficient approach is introduced for design and analysis of double-layer grids including both geometrical and material nonlinearities, while the results are compared with those considering material nonlinearity. Optimum design procedure based on Enhanced Colliding Bodies Optimization method (ECBO) is applied to optimal design of two commonly used configurations of double-layer grids. Two ranges of spans as small and big sizes with certain bays of equal length in two directions are considered for each type of square grids. ECBO algorithm obtains minimum weight grid through appropriate selection of tube sections available in AISC Load and Resistance Factor Design (LRFD). Strength constraints of AISC-LRFD specifications and displacement constraints are imposed on these grids.

• 한국입자에어로졸학회지
• /
• 제10권3호
• /
• pp.99-108
• /
• 2014

Liquid filtration by membrane filters is essential for the preparation of ultrapure water in semiconductor manufacturing processes. The separation of submicrometer particles suspended in ultrapure water with a laminated fibrous membrane filter was studied numerically and experimentally in the present work. We found that an electrical double layer around a single fiber expanded to a large extent at a low ion concentration, as in ultrapure water, and deformed toward the upstream of the fiber with increasing filtration velocity. Since an increase in the electrical double-layer thickness leads to a decrease in the electrical potential gradient, particles with the same polarity as the fiber approach the fiber more easily and are captured at a high filtration velocity. Experimental results also confirmed that the collection efficiency of polystyrene latex(PSL) particles through a PTFE filter became higher as the filtration velocity increased.