• Journal of the Korean Geotechnical Society
• /
• v.18 no.5
• /
• pp.123-132
• /
• 2002

The purpose of this study is to predict the shear behavior of the weathered mudstone soil using dynamic neural network which mimics the biological system of human brain. SNN and RNN, which are kinds of the dynamic neural network realizing continuously a pattern recognition as time goes by, are used to predict a nonlinear behavior of soil. After analysis, parameters which have an effect on learning and predicting of neural network, the teaming rate, momentum constant and the optimum neural network model are decided to be 0.5, 0.7, 8$\times$18$\times$2 in SU model and 0.3, 0.9, 8$\times$24$\times$2 in R model. The results of appling both networks showed that both networks predicted the shear behavior of soil in normally consolidated state well, but RNN model which is effective fir input data of irregular patterns predicted more efficiently than SNN model in case of the prediction in overconsolidated state.

• Korean Journal of Social Welfare
• /
• v.57 no.3
• /
• pp.415-435
• /
• 2005

The purpose of this study was to investigate conceptual constructions which determined financial preparedness for retirement. This study was guided by two theoretical frameworks, planned behavior theory and hierarchical personality model. Based on two theories, the conceptual framework which aimed to explain financial preparedness for retirement were formulated. Data from 'The health and welfare profile of the elderly aged 65 and or older in Chung-choo city' was analyzed. The subjects consisted of 87 economically active elderly population. Structure equation model was employed for statistical analyses. The results of structure equation model revealed that the casual relationship between the level of perceived financial-planning knowledge and the level of financial preparedness for retirement was statistically significant. Also, the hypothesized structural model for financial preparedness for retirement had the good model fit. Implications for social work practice from this study were discussed.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.35 no.12
• /
• pp.1325-1333
• /
• 2011

An analytical, numerical, and experimental comparison of the hydraulic and thermal performance of new vascular channels with semicircular cross sections was conducted. The following conditions were employed in the study: Reynolds number, 30-2000; cooling channels with a volume fraction of the cooling channels, 0.04; and pressure drop, $30-10^5$ Pa. Three flow configurations were considered: first, second, and third constructal structures with diameters optimized for hydraulic operations. To validate the proposed vascular designs by an analytical approach, 3-D numerical analysis was performed. The numerical model was also validated by the experimental data, and the comparison results were in excellent agreement in all cases. The validation study against the experimental data showed that compared to traditional channels, the optimized structure of the cooling plates could significantly enhance heat transfer and decrease pumping power.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• Korean Chemical Engineering Research
• /
• v.53 no.6
• /
• pp.824-830
• /
• 2015

The influence of phosphorous precursors, $NH_4H_2PO_4$, $(NH_4)_2HPO_4$, $H_3PO_4$, $(C_2H_5)_3PO_4$, and $P_2O_5$, on the catalytic performance of the $BiFe_{0.65}MoP_{0.1}$ catalysts in the oxidative dehydrogenation of 1-butene to 1,3-butadiene was studied. The catalysts were characterized by XRD, $N_2$-sorption, ICP, SEM and TPRO analyses. It was not observed big difference on the physical properties of catalysts in accordance with used different phosphorous precursors, however, the catalytic performance was largely depended on the nature of the phosphorous precursors. Of various precursors, the $BiFe_{0.65}MoP_{0.1}$ oxide catalyst, which was prepared from a phosphoric acid precursor, showed the best catalytic performance. Conversion and yield to butadiene of the catalyst showed 79.5% and 67.7%, respectively, after 14 h on stream. The cation of phosphorous precursors was speculated to affect the lattice structure of the catalysts during catalyst preparation and this difference was influenced on the re-oxidation ability of the catalysts. Based on the results of TPRO, it was proposed that the catalytic performance could be correlated with re-oxidation ability of the catalysts.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2001.10a
• /
• pp.165-196
• /
• 2001

DNA chip 또는 microarray는 다수의 유전자 또는 유전자 조각을 (보통 수천내지 수만 개)칩상에 고정시켜 놓고 DNA hybridization 반응을 이용하여 유전자들의 발현 양상을 분석할 수 있는 기술이다. 이러한 high-throughput기술은 예전에는 생각하지 못했던 여러가지 분자생물학의 문제에 대한 해답을 제시해 줄 수 있을 뿐 만 아니라, 분자수준에서의 질병 진단, 신약 개발, 환경 오염 문제의 해결 등 그 응용 가능성이 무한하다. 이 기술의 실용적인 적용을 위해서는 DNA chip을 제작하기 위한 하드웨어/웻웨어 기술 외에도 이러한 데이터로부터 최대한 유용하고 새로운 지식을 창출하기 위한 bioinformatics 기술이 핵심이라고 할 수 있다. 유전자 발현 패턴을 데이터마이닝하는 문제는 크게 clustering, classification, dependency analysis로 구분할 수 있으며 이러한 기술은 통계학과인공지능 기계학습에 기반을 두고 있다. 주로 사용된 기법으로는 principal component analysis, hierarchical clustering, k-means, self-organizing maps, decision trees, multilayer perceptron neural networks, association rules 등이다. 본 세미나에서는 이러한 기본적인 기계학습 기술 외에 최근에 연구되고 있는 새로운 학습 기술로서 probabilistic graphical model (PGM)을 소개하고 이를 DNA chip 데이터 분석에 응용하는 연구를 살펴본다. PGM은 인공신경망, 그래프 이론, 확률 이론이 결합되어 형성된 기계학습 모델로서 인간 두뇌의 기억과 학습 기작에 기반을 두고 있으며 다른 기계학습 모델과의 큰 차이점 중의 하나는 generative model이라는 것이다. 즉 일단 모델이 만들어지면 이것으로부터 새로운 데이터를 생성할 수 있는 능력이 있어서, 만들어진 모델을 검증하고 이로부터 새로운 사실을 추론해 낼 수 있어 biological data mining 문제에서와 같이 새로운 지식을 발견하는 exploratory analysis에 적합하다. 또한probabilistic graphical model은 기존의 신경망 모델과는 달리 deterministic한의사결정이 아니라 확률에 기반한 soft inference를 하고 학습된 모델로부터 관련된 요인들간의 인과관계(causal relationship) 또는 상호의존관계(dependency)를 분석하기에 적합한 장점이 있다. 군체적인 PGM 모델의 예로서, Bayesian network, nonnegative matrix factorization (NMF), generative topographic mapping (GTM)의 구조와 학습 및 추론알고리즘을소개하고 이를 DNA칩 데이터 분석 평가 대회인 CAMDA-2000과 CAMDA-2001에서 사용된cancer diagnosis 문제와 gene-drug dependency analysis 문제에 적용한 결과를 살펴본다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.4
• /
• pp.941-951
• /
• 2015

In the recent years, Korean construction companies have been awarded 680 billion USD in the oversea projects which lead to a successful quantitative growth. However, due to the lack of capability in the core technology and project management compared to the leading companies, in addition to low-price bidding, massive deficit projects have caused problems to the companies. In order to overcome the limitations of the lack of capabilities, the term constructability has been researched recently by developed countries to apply in the practical use. The concept of constructability must be applied for Korean companies to compete in the EPC construction projects. The term constructability is defined as the factor that affect the overall construction process of a project which is defined by the ease of construction and to secure the project quality. Therefore, this study aims to develop a constructability assessment model using the structural equation to assess the factors that affect the constructability in the design and construction stage. The purpose of using the structural equation is to analyze the direct and indirect correlation between each factor that affects the international construction projects. Total of 8 latent variables and 34 measured variables are derived through literature review, corporate reports, experts' interview and surveys. The result of the model suggests the constructability factors that are to be managed the most efficiently to reduce cost, time and improve the quality as well as a countermeasure strategy to successfully execute the target international construction projects.

• Journal of Korea Port Economic Association
• /
• v.33 no.1
• /
• pp.75-87
• /
• 2017

The purpose of this study is to utilize the system dynamics to carry out a medium and long-term forecasting analysis of the bunker price. In order to secure accurate bunker price forecast, a quantitative analysis was established based on the casual loop diagram between various variables that affects bunker price. Based on various configuration variables such as crude oil price which affects crude oil consumption & production, GDP and exchange rate which influences economic changes and freight rate which is decided by supply and demand in shipping and logistic market were used in accordance with System Dynamics to forecast bunker price and then objectivity was verified through MAPEs. Based on the result of this study, bunker price is expected to rise until 2029 compared to 2016 but it will not be near the surge sighted in 2012. This study holds value in two ways. First, it supports shipping companies to efficiently manage its fleet, offering comprehensive bunker price risk management by presenting structural relationship between various variables affecting bunker price. Second, rational result derived from bunker price forecast by utilizing dynamic casual loop between various variables.

• Journal of the Korean Institute of Gas
• /
• v.9 no.2 s.27
• /
• pp.34-37
• /
• 2005

The membrane for LNG storage tank behaves linearly in macroscopic view, but behaves elasto-plastically in some local areas, and has the structure undergoing both tension and bending. That is, the membrane is not able to be evaluated with the fatigue characteristics of the material, and it is so difficult to evaluate the membrane with a real big model because of the difficulty of imposing complex loads. Therefore, a prediction formula fur the fatigue life of the membrane is proposed to use for the design of LNG storage tank.