• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4C
• /
• pp.229-238
• /
• 2006

Observed field behaviors are frequently different from the behaviors predicted in the design state due to several uncertainties involved in soil properties, numerical modeling, and error of measuring system even though a sophisticated numerical analysis technique is applied to solve the consolidation behavior of drainage-installed soft deposits. In this study, genetic algorithms are applied to back-analyze the soil properties using the observed behavior of soft clay deposit composed of multi layers that shows complex consolidation characteristics. Utilizing the program, one might be able to appropriately predict the subsequent consolidation behavior from the measured data in an early stage of consolidation of multi layered soft deposits. Example analyses for drainage-installed multi-layered soft deposits are performed to examine the applicability of proposed back-analysis method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.747-752
• /
• 2011

Microarray classification typically possesses two striking attributes: (1) classifier design and error estimation are based on remarkably small samples and (2) cross-validation error estimation is employed in the majority of the papers. A Microarray data of ovarian cancer consists of the expressions of thens of thousands of genes, and there is no systematic procedure to analyze this information instantaneously. In this paper, gene markers are selected by ranking genes according to statistics, popular classification rules - linear discriminant analysis, k-nearest-neighbor and decision trees - has been performed comparing classification accuracy of data selecting gene markers and not selecting gene markers. The Result that apply linear classification analysis at Microarray data set including marker gene that are selected using ANOVA method represent the highest classification accuracy of 97.78% and the lowest prediction error estimate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.8
• /
• pp.903-909
• /
• 2019

Periodontal disease is observed in many adult persons. However we has not clear know the molecular mechanism and how to treat the disease at the molecular levels. Here, we investigated the molecular differences between periodontal disease and normal controls using gene expression data. In particular, we checked whether the periodontal disease and normal tissues would be classified by machine learning algorithms using gene expression data. Moreover, we revealed the differentially expression genes and their function. As a result, we revealed that the periodontal disease and normal control samples were clearly clustered. In addition, by applying several classification algorithms, such as decision trees, random forests, support vector machines, the two samples were classified well with high accuracy, sensitivity and specificity, even though the dataset was imbalanced. Finally, we found that the genes which were related to inflammation and immune response, were usually have distinct patterns between the two classes.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.227-249
• /
• 2003

Prediction of corporate failure using past financial data is a well-documented topic. Early studies of bankruptcy prediction used statistical techniques such as multiple discriminant analysis, logit and probit. Recently, however, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as model construction process. Irrespective of the efficiency of a teaming procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network model. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables fur neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.

• Journal of Advanced Marine Engineering and Technology
• /
• v.37 no.8
• /
• pp.869-876
• /
• 2013

In order to estimate the fatigue life of mufflers at the early stage of researches and designs, the new prediction process was developed by the artificial neural network, which has the algorism of weldment properties. Bending fatigue test was carried out for defining the characteristics of muffler weldment fatigue life and damage. For considering and predicting mechanical and fatigue properties of the muffler, the maximum stress of weldment was adapted as the variable of artificial neural network training. Also, it was compared with the fatigue life predicting results using fatigue notch factors, for proving the newly developed process of the artificial neural network.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.6
• /
• pp.1481-1494
• /
• 1997

In hard real-time systems, a timing fault may yield catastrophic results. Dynamic scheduling provides the flexibility to compensate for unexpected events at runtime; however, scheduling overhead at runtime is relatively large, constraining both the accuracy of the timing and the complexity of the scheduling analysis. In contrast, static scheduling need not have any runtime overhead. Thus, it has the potential to guarantee the precise time at which each instruction implementing a control action will execute. This paper presents a new approach to the problem of analyzing high-level language code, augmented by arbitrary before and after timing constraints, to provide a valid static schedule. Our technique is based on instruction-level complier code scheduling and timing analysis, and can ensure the timing of control operations to within a single instruction clock cycle. Because the search space for a valid static schedule is very large, a novel adaptive genetic search algorithm was developed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.9
• /
• pp.1596-1601
• /
• 2006

To customer management finds and forecast customer's various pattern more easily and conveniently rising by important topic that control corporation's success and failure, mmy corporations are introducing CRM and eCRM fast. At past, customer management had been managed by statisticians or special statistics package but it is trend been alternating gradually by datamining technique to do to computerize statistics process based on sudden development of IT. Field that this datamining is used representatively is CRM, eCRM. This paper applied datamining using GA referencing customer data or discount store and sale data or 2004 years. forecasted 2005 years melancholy customer by datamining and proved datamining through comparison with actuality customer data is how effective to eCRM.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.11a
• /
• pp.272-275
• /
• 2004

플라즈마 식각공정은 소자제조를 위한 미세 패턴닝 제작에 이용되고 있다. 공정 메커니즘의 정성적 해석, 최적화, 그리고 제어를 위해서는 컴퓨터 예측모델의 개발이 요구된다. 역전파 신경망 (backpropagation neural network-BPNN) 모델을 개발하는 데에는 다수의 학습인자가 관여하고 있으며, 가장 그 최적화가 어려운 학습인자는 초기웨이트이다. 모델개발시, 초기웨이트는 random 값으로 설정이 되며, 이로 인해 초기웨이트의 최적화가 어렵다. 본 연구에서는 유전자 알고리즘 (genetic algorithm-GA)을 이용하여 BPNN의 초기웨이트를 최적화하였으며, 이를 식각공정 모델링에 적용하여 평가하였다. 실리카 식각공정 데이터는 $2^3$ 인자 실험계획법을 이용하여 수집하였으며, GA에 관여하는 두 확률인자의 영향을 42 인자 실험계획법을 이용하여 최적화 하였다. 종래의 모델에 비해, 최적화된 모델은 실리카 식각률, Al 식각률, Al 선택비, 그리고 프로파일 응답에 대해서 각 기 24%, 13%,, 16%, 그리고 17%의 향상률을 보였다. 이는 제안된 최적화 기법이 플라즈마 모델의 예측성능을 증진하는데 효과적으로 응용될 수 있음을 의미한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.24-24
• /
• 2015

최근 원격탐사기법을 이용한 많은 가뭄평가기법들이 개발되었으나 산림과 함께 산악지형이 우세한 우리나라의 경우 지형특성으로 인하여 가뭄평가시 불확실성이 증가하게 된다. 특히, 농업가뭄은 기후와 지표특성에 큰 영향을 받기 때문에 기후특성만을 고려한 가뭄지수는 실제 필요한 농업가뭄의 특성을 반영하는데 있어서 한계가 있다. 따라서 본 연구에서는 기후와 지표특성을 함께 고려할 수 있는 토양수분을 이용한 가뭄평가기법(Drought Assessment Scheme)을 개발하였다. 가뭄평가기법을 위하여 역추적기법(Inverse Modeling-IM) 기반의 자료동화기법(Data Assimilation, DA)을 이용하였다. 자료동화기법은 1-Dimensional (1-D) 기반의 토양의 물리적 특성을 고려하는 SWMI_ST 모형과 최적화 알고리즘(유전자 알고리즘, Genetic Algorithm-GA)을 연계하여 실측 및 위성기반의 토양수분자료로부터 토양의 수리학적 매개변수(${\alpha}$, n, ${\Theta}_{res}$, ${\Theta}_{sat}$, $K_{sat}$)를 추출한다. 본 연구에서는 LANDSAT(30 m X 30 m) 및 MODerate Resolution Imaging Spectroradiometer(MODIS, 500 m X 500 m) 이미지자료를 이용하여 시 공간적으로 분포되어 있는 토양수분을 산정하였으며, 이후 자료동화기법을 이용하여 LANDSAT/MODIS 토양수분자료로 부터 공간적으로 분포되어 있는 토양의 매개변수를 추출하였다. 추출된 매개변수, GIS 기반의 지표피복 및 기상자료를 이용하여 장기간의 토양수분을 산정 및 예측 할 수 있다. 고해상도의 이미지 자료를 사용하는 가뭄평가기법은 필지~시 군 단위까지 실제 우리나라 지형특성을 고려하여 효율적으로 가뭄을 모니터링 및 예측 할 수 있다.

• The Korean Society of Law and Medicine
• /
• v.23 no.1
• /
• pp.121-148
• /
• 2022

CRISPR-Cas9 is one of the gene-editing technologies that infinite potential. It may provide human beings with many benefits or cause unanticipated challenges. The governance as standards setting or regulation of gene-editing technologies can contribute to keeping a balance between scientific value and ethical commitments. Guaranteeing public participation provides an additional opportunity to think about ethical and moral considerations: For whose benefit the internationally discussed governance of gene-editing technologies is directed at? There is a doubt regarding whether the governance justifies scientific researchers' gene-editing research. Suppose that governance promotes the advancement of CRISPR-Cas9, it should also encourage greater research responsibility. If not, there may be tragedies brought about by the misconduct of researchers. Thus, the essential matter on the governance for the research of CRISPR-Cas9 is the researchers' responsibility.