• (The)Study of the Eastern Classic
• /
• no.54
• /
• pp.155-182
• /
• 2014

This study aimed to find the possibility of interactions between the Doctrine of the Mean and evolutionary biology. Between the two disciplines, there exists a huge gap such as "traditional era vs. modern times" and "humanities vs. natural science." However, this paper assumed that an analysis of their similarities and differences would allow us to find the possibility for them to interact and communicate with each other. For this purpose, the author proposed a three-step approach to studies of the following topics: human nature in step 1, validity of reasons to live in step 2 and biologically affinitive relations in step 3. The present study in step 1 pays attention to the similarities and differences between genes and in-ui-ye-ji (a set of four Confucian values: benevolence, righteousness, propriety and wisdom). This step discusses the issues of ri (principle) and ki (generative force) in Zhu Xi's theory vs. genes and vehicles in evolutionary biology, innate goodness vs. altruism of genes and in-ui-ye-ji vs. epigenetic rules. In step 2, attention is paid to the similarities and differences between natural selection and shi zhong (時中). They are discussed in terms of the upset of the law of nature vs. mutation, changes vs. evolutions and shi zhong vs. natural selection/adaptation. Step 3 focuses on the similarities and differences between species diversity and li-yi-fen-shu (one li and its many aspects). The discussion in this step addresses the issues of part or whole vs. li-yi-fen-shu, biological affinity vs. single energy and ecosystem vs. "the earth moves orderly, and everything thereon flourishes." If these studies are conducted as planned, a new direction can be set for Zhu Xi's neo-Confucianism. Further, the interaction between humanities and natural science will pave the way for us to overcome asymmetry between different disciplines.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04d
• /
• pp.124-126
• /
• 2003

그리드 컴퓨팅은 광범위 분산 컴퓨팅 시스템(wide area distributed computing system)으로, 고성능의 유휴 컴퓨팅 자원을 서로 공유하여 효율적으로 작업을 수행하는 것을 목적으로 한다. 그리드 컴퓨팅에서 사용자가 요구하는 자원의 검색, 선택, 할당하는 문제는 시스템 성능에 큰 영향을 미친다. 그리드 컴퓨팅을 지원하는 대표적인 미들웨어인 글로버스(Globus Toolkit)에서는 위와 같은 과정들이 사용자에 의해 수동적으로 이루어지며, 검색된 후보 자원의 최적 선택 방법은 제공하지 않고 있다. 본 논문에서는 글로버스에서 사용자의 요구에 의해 검색된 후보 자원들 중 최적화된 자원 선택과 할당 요청을 담당하는 최적 자원 선택 브로커를 설계하였다. 이 브로커는 유전자 알고리즘을 이용하여 최적 자원을 선택하므로 사용자의 임의적 자원 선택으로 인한 시스템의 성능 저하를 막아준다. 자원 검색, 선택, 할당 요청이 하나의 브로커에서 이루어짐으로써 작업 수행 시 발생하는 사용자의 불필요한 관여를 막아 작업 수행에 대한 편의성을 제공한다.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.109-123
• /
• 2004

Corporate financial distress and bankruptcy prediction is one of the major application areas of artificial neural networks (ANNs) in finance and management. ANNs have showed high prediction performance in this area, but sometimes are confronted with inconsistent and unpredictable performance for noisy data. In addition, it may not be possible to train ANN or the training task cannot be effectively carried out without data reduction when the amount of data is so large because training the large data set needs much processing time and additional costs of collecting data. Instance selection is one of popular methods for dimensionality reduction and is directly related to data reduction. Although some researchers have addressed the need for instance selection in instance-based learning algorithms, there is little research on instance selection for ANN. This study proposes a genetic algorithm (GA) approach to instance selection in ANN for bankruptcy prediction. In this study, we use ANN supported by the GA to optimize the connection weights between layers and select relevant instances. It is expected that the globally evolved weights mitigate the well-known limitations of gradient descent algorithm of backpropagation algorithm. In addition, genetically selected instances will shorten the learning time and enhance prediction performance. This study will compare the proposed model with other major data mining techniques. Experimental results show that the GA approach is a promising method for instance selection in ANN.

• Journal of KIISE:Software and Applications
• /
• v.35 no.8
• /
• pp.463-478
• /
• 2008

Due to the high dimensional problem, typically machine learning algorithms have relied on feature selection techniques in order to perform effective classification in microarray gene expression datasets. However, the large number of features compared to the number of samples makes the task of feature selection computationally inprohibitive and prone to errors. One of traditional feature selection approach was feature filtering; measuring one gene per one step. Then feature filtering was an univariate approach that cannot validate multivariate correlations. In this paper, we proposed a function for measuring both class separability and correlations. With this approach, we solved the problem related to feature filtering approach.

• Environmental Analysis Health and Toxicology
• /
• v.20 no.4 s.51
• /
• pp.327-332
• /
• 2005

장기간 노출 시 발암 등 인체 유해성을 갖는 환경유래 내분비장애물질(endocrine disrupting chemicals, EDCs)에 대한 선택적이고 민감한 노출지표를 개발하기 위하여 본 연구에서는 DNA microarray를 이용하였다. 피험자는 아직 특별한 질환을 갖지 않는 18세 이상 연령, 성을 맞춘 EDCs고농도 노출군(N = 16)과 저농도군(N = 16)으로 구성되었다. 노출정도 구분은 10년 이상 거주지가 K산업폐기물 소각장과 2.5 km 반경 내, 외 인지에 따라 고노출군,저노출군으로 구분하였다. 피험자의 말초혈에서 total RNA를 분리, 각 군당 B인씩 pool로 cDNA를 합성하여 oligonucleotide DNA 칩에 적용하였다. 유전자발현의 차이를 GenePixPro 4.0 software를 이용하여 분석하였다. 총 3장의 칩을 이용하여 공통적으로 저노출군보다 고노출군에서 2배 이상 발현의 증가를 보인 유전자는 plasminogen activator(PLAT)등 12종이 관찰되었고, l/2이하로 발현의 감소를 보인 유전자는 kallikrein 3 (KLK3)등 29종이었다. 이 들 유전자는 PLAT등 면역계 반응에 관여하는 유전자 및 apoptosis, transport, G protein, chromatin, 암화, 발생 (development), 대사 등에 관여하는 유전자들이었다. 그러므로 KLK3등 본 연구에서 발굴한 유전자는 향후 확대된 인구에서 본 연구 결과의 확인을 통하여 EDCs특이적 노출지표로써, 나아가 암 등 EDCs관련 질병의 기전 및 병인학을 구명하는데 이용가치가 높다고 사료된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.383-386
• /
• 2019

4 차산업혁명의 발달은 전 세계가 건강한 삶에 관련된 스마트시티 및 맞춤형 치료에 큰 관심을 갖게 하였고, 특히 기계학습 기술은 암을 극복하기 위한 유전체 기반의 정밀 의학 연구에 널리 활용되고 있어 암환자의 예후 예측 및 예후에 따른 맞춤형 치료 전략 수립 등을 가능케하였다. 하지만 암 예후 예측 연구에 주로 사용되는 유전자 발현량 데이터는 약 17,000 개의 유전자를 갖는 반면에 샘플의 수가 200 여개 밖에 없는 문제를 안고 있어, 예후 예측을 위한 신경망 모델의 일반화를 어렵게 한다. 이러한 문제를 해결하기 위해 본 연구에서는 고차원의 유전자 발현량 데이터를 신경망 모델이 효과적으로 학습할 수 있도록 2D 이미지로 표현하는 기법을 제안한다. 길이 17,000 인 1 차원 유전자 벡터를 64×64 크기의 2 차원 이미지로 사상하여 입력크기를 압축하였다. 2 차원 평면 상의 유전자 좌표를 구하기 위해 유전자 네트워크 데이터와 Node2Vec 이 활용되었고, 이미지 기반의 암 예후 예측을 수행하기 위해 합성곱 신경망 모델을 사용하였다. 제안하는 기법을 정확하게 평가하기 위해 이중 교차 검증 및 무작위 탐색 기법으로 모델 선택 및 평가 작업을 수행하였고, 그 결과로 베이스라인 모델인 고차원의 유전자 벡터를 입력 받는 다층 퍼셉트론 모델보다 더 높은 예측 정확도를 보여주는 것을 확인하였다.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.4
• /
• pp.639-647
• /
• 2009

From development of computer science, genetic algorithm has been applied to many fields for search like non-linear problem based on various variables and optimization process. Among others, in the data mining field, there are methods to select the best input variables for model accuracy and various predict models which were merged by using the genetic algorithm. In the meantime, to improve and preserve quality of the Hanwoo (Korean cattle) which is represented the agricultural industry in our country, we need to find out outstanding economical traits of Hanwoo in having specific genotype of single nucleotide polymorphism (SNP) which is inherited to next generation. According to, This research proposed the selecting method to find genotype of SNPs marker which affects economical traits of the Hanwoo by using the genetic algorithm. And we selected the best genotypes of the principal SNPs marker by applying to real data on Hanwoo genetic.

• Korean Journal of Animal Reproduction
• /
• v.25 no.2
• /
• pp.171-180
• /
• 2001

Compared to other gene transfer system, the advantages of retrovirus-mediated gene transfer are technical ease, efficient expression and genetic stability. Despite the high potency of the retrovirus vector system in gene transfer, one of the drawbacks is a difficulty in concentration of virus stock. To overcome this problem, we tested a new retrovirus vector system producing the progeny retrovirus particles encapsidated with VSV-G (vesicular stomatitis virus G glycoprotein). The infectivity of this virus was not sacrificed by ultracentrifugal concentration and the host cell range extended from all mammalian to fish embryos. Virus titer after 1,000 x concentration was more than 10$^{8}$ CFU/ $m\ell$ on most of the target cell lines. We applied this pantropic viruses in transgenic chicken production by injecting the concentrated (100$\times$) stock into subgerminal cavity of stage X chicken embryos. The survival rate of chicken embryos after injection was about 20% and gene integration rate in surviving embryos was scored almost 100%. Analyses of RT-PCR and fluorescence microscopy, however, showed no evidence of the transgene expression.

• Journal of Korean Society of Steel Construction
• /
• v.18 no.2
• /
• pp.147-160
• /
• 2006

GA-based fuzzy optimum design algorithm incorporated with the refined plastic hinge analysis method is presented in this study. In the refined plastic hinge analysis method, geometric nonlinearity is considered by using the stability functions of the beam-column members. Material nonlinearity is also considered by using the gradual stiffness degradation model, which considers the effects of residual stresses, moment redistribution through the occurence of plastic hinges, and the geometric imperfections of the members. In the genetic algorithm, the tournament selection method and the total weight of the steel frames. The requirements of load-carrying capacity, serviceability, ductility, and constructabil ity are used as the constraint conditions. In fuzzy optimization, for crisp objective function and fuzzy constraint s, the tolerance that is accepted is 5% of the constraints. Furthermore, a level-cut method is presented from 0 to 1 at a 0 .2 interval, with the use of the nonmembership function, to solve fuzzy-optimization problems. The values of conventional GA optimization and fuzzy GA optimization are compared in several examples of steel structures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.10
• /
• pp.1924-1929
• /
• 2007

Nowadays, a lot of related data obtained from these research could be given a new present meaning to accomplish the original purpose of the whole research as a human project. The method of tumor classification based on microarray could contribute to being accurate tumor classification by finding differently expressing gene pattern statistically according to a tumor type. Therefore, the process to select a closely related informative gene with a particular tumor classification to classify tumor using present microarray technology with effect is essential. In this thesis, we used cDNA microarrays of 3840 genes obtained from neuronal differentiation experiment of cortical stem cells on white mouse with cancer, constructed accurate tumor classification model by extracting informative gene list through normalization separately and then did performance estimation by analyzing and comparing each of the experiment results. Result classifying Multi-Perceptron classifier for selected genes using Pearson correlation coefficient represented the accuracy of 95.6%.