• 한국정보통신학회논문지
• /
• 제5권5호
• /
• pp.977-984
• /
• 2001

본 논문에서는 유전자-퍼지 제어 알고리즘에 대하여 논의하고 그 성능을 평가하였다. 이 알고리즘은 퍼지 논리와 유전자알고리즘의 융합된 형태이며, 제어 대상으로는 도립진자 시스템을 모델링 하였다. 퍼지 제어기는 두 개의 입력과 한 개의 출력 변수를 설계하기 위해 적용되며, GA(Genetic Algorithm)는 퍼지 규칙과 소속 함수를 선택, 교차, 돌연변이의 진화 연산을 통해 최적화한다. 컴퓨터 시뮬레이션에 퍼지 제어의 경우 초기 함수 f(0.3, 0.3)일 때 최대 언더슈트가 $-5.0 \times 10^{-2}[rad]$, 최대 오버슈트가 $3.92\times10^{-2}[rad]$으로 측정되었으나, 유전자 퍼지 알고리즘의 경우 최대 오버슈트와 언더슈트가 각각 0.0[rad]으로 측정되었다. 또한 정상상태 도달시간이 퍼지제어의 경우 2.12[sec], 유전자-퍼지 알고리즘은 1.32[sec]로 비교적 안정적으로 나타났다. 컴퓨터 시뮬레이션으로 이 알고리즘을 도립진자 시스템에 적용시키고, 그 성능의 우수성과 효율성을 증명하였다.

• Journal of Ginseng Research
• /
• 제34권1호
• /
• pp.41-46
• /
• 2010

Expensive herbs such as ginseng are always a possible target for fraudulent labeling. New mountain ginseng strains have occasionally been found deep within mountain areas and commercially traded at exorbitant prices. However, until now, no scientific basis has existed to distinguish such ginseng from commonly cultivated ginseng species other than by virtue of being found within deep mountain areas. Polymerase chain reaction (PCR) analysis of the internal transcribed spacer has been shown to be an appropriate method for the identification of the most popular species (Panax ginseng) in the Panax ginseng genus. A single nucleotide polymorphism (SNP) has been identified between three newly found mountain ginseng (KGD4, KGD5, and KW1) and already established Panax species. Specific PCR primers were designed from this SNP site within the sequence data and used to detect the mountain ginseng strains via multiplex PCR. The established multiplex-PCR method for the simultaneous detection of newly found mountain ginseng strains, Korean ginseng, and foreign ginseng in a single reaction was determined to be effective. This study is the first report of scientific discrimination of "mountain ginsengs" and describes an effective method of identification for fraud prevention and for uncovering the possible presence of other, cheaper ginseng species on the market.

• 농업과학연구
• /
• 제32권1호
• /
• pp.53-61
• /
• 2005

한국의 소 사육 농가에서 유전병을 monitoring 하는 체계가 현재 존재하지 않기 때문에 정확히 한우에서 어떤 유전병이 존재하는지 알 수가 없는 실정이다. 최근에 일본에서는 흑모화우에 존재하는 유전병을 제거하기 위해 많은 노력을 들이고 있다. 본 연구는 일본의 흑모화우에 존재하는 유전병인 Band 3와 CHS의 존재 유무를 혈연관계가 없는 한우 22개체를 이용하여 PCR-RFLP 방법으로 확인하였다. 비록 한우에서 Band 3와 CHS 유전병을 가진 개체는 나오지 않았으나 본 연구에서 확립된 방법을 한우 보증 종모우와 후보 종모우에서 확인하여 유전병을 가진 유전자가 다음 세대로 전달되는 것을 막을 필요성이 있다.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2001년도 Bulletin of The 5th Asian Design Conference International Symposium on Design Science
• /
• pp.1.2-1
• /
• 2001

• Asian-Australasian Journal of Animal Sciences
• /
• 제27권11호
• /
• pp.1548-1553
• /
• 2014

Four Korean native cattle (KNC) breeds-Hanwoo, Chikso, Heugu, and Jeju black-are entered in the Domestic Animal Diversity Information System of the United Nations Food and Agriculture Organization (FAO). The objective of this study was to assess the genetic diversity, phylogenetic relationships and population structure of these KNC breeds (n = 120) and exotic breeds (Holstein and Charolais, n = 56). Thirty microsatellite loci recommended by the International Society for Animal Genetics/FAO were genotyped. These genotypes were used to determine the allele frequencies, allelic richness, heterozygosity and polymorphism information content per locus and breed. Genetic diversity was lower in Heugu and Jeju black breeds. Phylogenetic analysis, Factorial Correspondence Analysis and genetic clustering grouped each breed in its own cluster, which supported the genetic uniqueness of the KNC breeds. These results will be useful for conservation and management of KNC breeds as animal genetic resources.

• Journal of Genetic Medicine
• /
• 제5권2호
• /
• pp.89-93
• /
• 2008

"Personalized medicine," the goal of which is to provide better clinical care by applying patient's own genomic information to their health care is a global challenge for the $21^{st}$ century "genomic era." This is especially true in Korea, where provisions for clinical genetic services are inadequate for the existing demand, let alone future demands. Genomics-based knowledge and tools make it possible to approach each patient as a unique biological individual, which has led to a paradigm-shift in medical practice, giving it more of a predictive focus as compared with current treatment oriented approach. With recent advancements in genomics, many genetic tests, such as susceptibility genetic tests, have been developed for both rare single gene diseases and more common multifactorial diseases. Indeed, genetic tests for presymtomatic individuals and genetic tests for drug response have become widely available, and personalized medicine will face the challenge of assisting patients who use such tests to make appropriate and wise use of genetic risk assessment. A major challenge of genomic medicine lies in understanding and communicating disease risk in order to facilitate and support patients and their families in making informed decisions. Establishment of a health care system with provisions for genetic counseling as an integral part of health care service, in addition to genomic literacy of health care providers, is vital to meet this growing challenge. Realization of the promise of personalized medicine in the era of genomics for improvement of health care is dependent on further development of next generation sequencing technology and affordable sequencing test costs. Also necessary will be policy development concerning the ethical, legal and social issues of genomic medicine and an educated and ready medical community with clinical practice guidelines for genetic counseling and genetic testing.

• 한국컴퓨터정보학회논문지
• /
• 제10권6호
• /
• pp.85-92
• /
• 2005

본 논문에서는 변형된 돌연변이 연산자를 적용한 대화형 유전자 알고리즘을 사용해서 웹-기반 학습 콘텐츠를 개발하였다. 대화형 유전자 알고리즘은 주로 상호 교환(reciprocal exchange) 돌연변이를 사용한다. 그러나 본 논문에서는 학습자의 학습 효과를 높이기 위해 돌연변이 연산자를 변형하였다. 그리고, 대화형 유전자 알고리즘을 이용한 웹 기반 학습 콘텐츠는 동적인 학습 내용과 실시간 테스트 시스템을 제공한다. 특히 학습자가 자신의 특성과 흥미에 따라 대화형 유전자 알고리즘을 수행하면서 효율적인 학습 환경과 콘텐츠 배열 순서를 선택할 수 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.612-618
• /
• 1998

The success of a fuzzy logic control system solving any given problem critically depends on the architecture of th network. Various attempts have been made in optimizing its structure its structure using genetic algorithm automated designs. In a regular genetic algorithm , a difficulty exists which lies in the encoding of the problem by highly fit gene combinations of a fixed-length. This paper presents a new approach to structurally optimized designs of a fuzzy model. We use a messy genetic algorithm, whose main characteristics is the variable length of chromosomes. A messy genetic algorithms used to obtain structurally optimized fuzzy models. Structural optimization is regarded important before neural network based learning is switched into. We have applied the method to the exampled of a cart-pole balancing.

• 한국정밀공학회지
• /
• 제29권4호
• /
• pp.469-478
• /
• 2012

This study aims to discover the optimal pipe layout for a ship, which generally needs a lot of time, efforts and experiences. Genetic algorithm was utilized to search for the optimum. Here the optimum stands for the minimum pipe length between two given points. Genetic algorithm is applied to planar pipe layout problems to confirm plausible and efficiency. Sub-programs are written to find optimal layout for the problems. Obstacles are laid in between the starting point and the terminal point. Pipe is supposed to bypass those obstacles. Optimal layout between the specified two points can be found using the genetic algorithm. Each route was searched for three case models in two-dimensional plane. In consequence of this, it discovered the optimum route with the minimized distance in three case models. Through this study, it is possible to apply optimization of ship pipe route to an actual ship using genetic algorithm.

• 대한임베디드공학회논문지
• /
• 제15권5호
• /
• pp.261-268
• /
• 2020

Genetic algorithms find the optimal solution by mimicking the evolution of natural organisms. In this study, the genetic algorithm was used to enable Pac-Man's reinforcement learning, and a simulator to observe the evolutionary process was implemented. The purpose of this paper is to reinforce the learning of the Pacman AI of the simulator, and utilize genetic algorithm and artificial neural network as the method. In particular, by building a low-power artificial neural network and applying it to a genetic algorithm, it was intended to increase the possibility of implementation in a low-power embedded system.