• Journal of the Korea Society for Simulation
• /
• v.26 no.3
• /
• pp.105-113
• /
• 2017

This study considers an optimal investment planning for improving survivability from an air threat in the layered air defense system. To establish an optimization model, we first represent the layered air defense system as a network model, and then, present two optimization models minimizing the failure probability of counteracting an air threat subject to budget limitation, in which one deals with whether to invest and the other enables continuous investment on the subset of nodes. Nonlinear objective functions are linearized using log function, and we suggest dynamic programming algorithm and linear programing for solving the proposed models. After designing a layered air defense system based on a virtual scenario, we solve the two optimization problems and analyze the corresponding optimal solutions. This provides necessity and an approach for an effective investment planning of the layered air defense system.

• Journal of the Korean GEO-environmental Society
• /
• v.10 no.7
• /
• pp.159-165
• /
• 2009

The Strain Wedge Model is useful method for horizontal bearing capacity calculation considering interaction of pile and ground deformation. However, application case of the Strain Wedge Model is rare and the strain wedge model of plenty of verification is needed on multi layered ground in Korea. In this present study, to conduct laboratory model test and numerical analysis for verification of Strain Wedge Model, adapt model that could describe the interaction of pile and ground deformation on multi layered ground. In model test, it was performed to estimate the behavior characteristics on pile under lateral load and to analyze the relationship between load and deformation. In addition, it was fulfilled to measure the skin friction on pile using strain gauge and to decide the ground passive resistance wedge using skin friction. Numerical analysis was performed to verify laboratory model test results.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.426-427
• /
• 2023

최근 현대인의 식습관 및 고령화로 인해 당뇨병 환자의 수가 연간 증가하고 있다. 따라서 현재는 아직 당뇨병이 발생하지 않았더라도 미래에 발생할 가능성 예측의 중요성이 커지고 있다. 기존의 당뇨병 발생 여부 진단 연구는 회귀 분석과 같은 단일 모델을 사용하여 수행된다. 그러나 당뇨병에 영향을 미치는 변수들은 복잡하게 얽혀있어 단일 모델만으로는 패턴을 충분히 학습하기 어렵다. 본 논문에서는 데이터에 적합하게 자동으로 다층 스태킹 앙상블 모델을 구성하는 알고리즘을 이용한 다층 스태킹 앙상블 모델을 제안한다. 제안하는 방법은 성능이 높은 모델들을 기준으로 층을 쌓으며 모델을 구성하며 실험 결과 다른 자동 기계학습 라이브러리와 비교해 F1 score 기준으로 최대 12.89%p의 성능 향상을 보였다.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.7 no.2
• /
• pp.341-348
• /
• 1997

X-ray diffraction patterns of Pt/Co modulated films prepared by RF comagnetron sputtering method was investigated. Modulated films ([$Pt10.7\AA/Co2.8{\AA}{\times}{12}$]) were deposited on glass substrate with various sputtering conditions : sputtering with variations of gas pressures, sputtering with Xe instead Ar gas, and etching of the buffer layers. In order to obtain the structural information of Pt/Co modulated films, the structural model was constructed and calculated data of the model were compared with experimental ones. Comparison results showed that there were good agreements in satellite peak position and its intensity between them. This suggests that the realistic Pt/Co modulated film can be reproduced by our structure model.

• Composites Research
• /
• v.22 no.3
• /
• pp.66-73
• /
• 2009

Total thickness, areal density and mass moment of inertia of materials are important material factors for structural characteristics. In this work, a material-structural optimization was performed up to the maximum ballistic limit of multi-layered composite structures under high impact velocity followed by the investigation of the influence of these factors on an impact absorption performance. A unified model combined with Florence's and Awerbuch-Bonder's models was used in optimizing the multi-layered composite structure consisting of CMC, rubber, aluminum and Al-foam. Total thickness, areal density and mass moment of inertia were used for the optimization constraint. As shown in the results, the ballistic limit determined from a newly developed unified model was closely similar to the finite clement analysis. Additionally, the ballistic limit and impact absorption energy obtained by the optimized structure were improved approximately 16.8% and 26.7%, respectively comparing with a not optimized multi-layered structure.

• Journal of the Korean Vacuum Society
• /
• v.12 no.3
• /
• pp.182-192
• /
• 2003

A new Monte Carlo (MC) simulator for electron beam lithography process in the multi-layer resists and compound semiconductor substrates has been developed in order to fabricate and develop the high-speed PHEMT devices for millimeter-wave frequencies. For the accurate and efficient calculation of the transferred and deposited energy distribution to the multi-component and multi-layer targets by electron beams, we newly modeled for the multi-layer resists and heterogeneous multi-layer substrates. By this model, the T-shaped gate fabrication process by electron beam lithography in the PHEMT device has been simulated and analyzed. The simulation results are shown along with the SEM observations in the T-gate formation process, which verifies the new model in this paper.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.540-549
• /
• 2003

In collaborative recommendation two models are generally used: the user model and the article model. A user model learns correlation between users preferences and recommends an article based on other users preferences for the article. Similarly, an article model learns correlation between preferences for articles and recommends an article based on the target user's preference for other articles. In this paper, we investigates various combination methods of the user model and the article model for better recommendation performance. They include simple sequential and parallel methods, perceptron, multi-layer perceptron, fuzzy rules, and BKS. We adopt the multi-layer perceptron for training each of the user and article models. The multi-layer perceptron has several advantages over other methods such as the nearest neighbor method and the association rule method. It can learn weights between correlated items and it can handle easily both of symbolic and numeric data. The combined models outperform any of the basic models and our experiments show that the multi-layer perceptron is the most efficient combination method among them.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.1116-1119
• /
• 2021

2018 년 Google 사의 사전 학습된 언어 인공지능 BERT 를 기점으로, 자연어 처리 학계는 주요 구조를 유지한 채 경쟁적으로 모델을 대형화하는 방향으로 발전했다. 그 결과, 오늘날 자연어 인공지능은 거대 사기업과 그에 준하는 컴퓨팅 자원을 소유한 연구 단체만의 전유물이 되었다. 본 논문에서는 다층 퍼셉트론을 병렬적으로 배열해 자연어 인공지능을 제작하는 기법의 모델을 제안하고, 이를 적용한'조건부 게이트 다층 퍼셉트론 모델(SG-MLP)'을 구현하고 그 결과를 비교 관찰하였다. SG-MLP 는 BERT 의 20%에 해당하는 사전 학습량만으로 다수의 지표에서 그것과 준하는 성능을 보였고, 동일한 과제에 대해 더 적은 연산 비용을 소요한다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3C
• /
• pp.115-125
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by insitu test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network (NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. It was already found that NN model can come over the site dependency and prediction accuracy is greatly improved when compared with present theoretical and empirical models. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network (CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. Prediction results of CNN model are compared with those of conventional empirical and theoretical models and multi-layered neural network model, which has the optimized structure. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.

• Proceedings of the Korean Vacuum Society Conference
• /
• 1999.07a
• /
• pp.156-156
• /
• 1999

자성박막에 존재하는 자기구역의 형상 및 동력학은, 자성박막의 학문적 연구와 응용기술 개발의 핵심을 제공하는 매우 중요한 분야의 하나로서, 최근 크게 관심이 고조되고 있다. 본 연구에서는 차세대 광자기 재질로 각광받고 있는 Co/Pd 다층박막에서의 자기구역 형상 및 자기구역 동력학을 연구하였다. 전자빔 진공증착 시스템을 사용하여, Co 층의 두께와 Pd층의 두께, 그리고 전체 층수가 변화하는 일련의 Co/Pd 다층박막 시료를 제작하였다. 제작된 모든 시료가 명목두께에 대하여 4%의 정밀도로 제작되었음을 확인하였고, 제작된 시료의 자기 및 광자기 성질은 자기이력곡선 등을 측정하였다. 또한 고성능 광자기 Kerr 현미경 시스템을 이용하여 자성박막에 존재하는 자기구역의 형상 및 자기구역 동력학을 관찰하였다. 이 장비는 1,000배의 배율에서 0.3$\mu\textrm{m}$의 공간분해능을 가지며 실시간 자기구역 영상을 CCD 카메라를 통해 컴퓨터에 저장함으로써, 자지구역 거동현상을 관찰할 수 있다. 자성다층박막에 존재하는 자기구역의 형상을 이론적으로 예측하기 위하여, 다층박막 구조에서의 정자기 에너지를 일반적으로 계산할 수 있는 이론을 유도하였다. 이 이론을 통해 다층박막의 자성층의 두께가 두꺼워짐에 따라, 자기구역의 형상이 단일 자기구역 형상에서 줄무늬 자기구역 형상으로 천이함을 예측할 수 있었고, 이러한 지구구역 천이현상을 Co-Pd 다층박막의 자화역전현상을 연구하였고, 새로운 자구동력학 정량분석기술을 개발하여 Co/Pd 다층박막에 적용함으로써 자화역전의 자구벽 이동속도와 핵형성 확률을 각각 정량적으로 구하였다. 이러한 관찰 및 분석기술을 통하여, Co/Pd 다층박막의 층구조에 따라 대조적인 자화역전현상이 존재함을 관찰하였다. 이러한 대조적인 자화역전현상을 결정짓는 요인을 연구하기 위해서 나노자성학이온을 이용한 자화역전현상을 결정짓는 요인을 연구하기 위해서 나노자성학이온을 이용한 자화역전모델을 개발하였으며, 이를 통하여 자성박막의 거시적 자기성질에 의해 이러한 대조적인 자화역전모델을 개발하였으며, 이를 통하여 자성박막의 거시적 자기성지에 의해 이러한 대조적인 자화역전현상이 결정될 수 있음을 설명하였다. 또한, 미시적 자기이력곡선 측정을 통하여 자성박막구조에 따른 국소적인 구조불균일성을 관찰하였고, 이러한 구조불균일성 또한 대조적인 자화역전현상을 결정하는 큰 요인임을 논의하였다.