• 한국작물학회지
• /
• 제44권2호
• /
• pp.112-116
• /
• 1999

Genetic diversity of 31 rice varieties including 25 japonica and 6 indica varieties was evaluated using a combination of 19 microsatellite or simple sequence repeats (SSRs) and 28 random decamer oligonucle-otide primers. All 19 microsatellite primer sets representing 19 loci in the rice genome showed polymorphisms among the 31 varieties and revealed 91 alleles with an average of 4.80 bands per primer. Also all 28 random decamer primers used were informative and generated 114 non-redundant bands with a mean of 4.07 bands. Microsatellite markers detected higher number of alleles than random primers .although the mean difference was not statistically significant. A cluster analysis based on Nei＇s genetic distances calculated from the 205 bands resolved the 31 varieties into two major groups that correspond to indica and japonica subspecies, which is consistent with the genealogical information. As few as six random decamer primers or a combination of one microsatellite and four random decamer primers were sufficient to uniquely differentiate all 31 varieties. These combinations would be potentially useful in rice variety protection and identification considering that 25 out of 31 varieties used in this study are japonica rices with high grain quality and have close make up.

• 한국콘텐츠학회논문지
• /
• 제8권5호
• /
• pp.38-43
• /
• 2008

감성공학이 생활의 일부가 되어가면서 정보의 양도 급속도로 늘어나고 있으며, 이로 인해 데이터 속에서 정보를 찾아내는 기술이 부각되고 있다. 협력적 필터링은 비슷한 선호도를 가진 일부 사용자의 정보를 바탕으로 하기 때문에 나머지 정보를 무시하는 경향이 있다. 본 논문에서는 유전자 알고리즘을 이용한 감성공학적 의상 코디 지원 방법을 제안한다. 제안된 방법에서는 유전자 알고리즘에 의한 적합 함수로 평가 값을 계산하고 a-cut을 이용하여 군집한다. 성능평가를 위해 설문조사 데이터 집합에서 기존의 방법과 비교 평가하였다. 실험 결과 제안한 방법이 기존의 다른 방법들보다 정확도면에서 우수함을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권2호
• /
• pp.542-558
• /
• 2016

Vehicular Ad Hoc Networks (VANETs) are self-configuring networks where the nodes are vehicles equipped with wireless communication technologies. In such networks, limitation of signal coverage and fast topology changes impose difficulties to the proper functioning of the routing protocols. Traditional Mobile Ad Hoc Networks (MANET) routing protocols lose their performance, when communicating between vehicles, compromising information exchange. Obviously, most applications critically rely on routing protocols. Thus, in this work, we propose a methodology for investigating the performance of well-established protocols for MANETs in the VANET arena and, at the same time, we introduce a routing protocol, called Genetic Network Protocol (G-NET). It is based in part on Dynamic Source Routing Protocol (DSR) and on the use of Genetic Algorithms (GAs) for maintenance and route optimization. As G-NET update routes periodically, this work investigates its performance compared to DSR and Ad Hoc on demand Distance Vector (AODV). For more realistic simulation of vehicle movement in urban environments, an analysis was performed by using the VanetMobiSim mobility generator and the Network Simulator (NS-3). Experiments were conducted with different number of vehicles and the results show that, despite the increased routing overhead with respect to DSR, G-NET is better than AODV and provides comparable data delivery rate to the other protocols in the analyzed scenarios.

• 터널과지하공간
• /
• 제15권2호
• /
• pp.129-136
• /
• 2005

터널이나 지하구조물의 건설시 필요한 지보의 설계는 보통 시추에 의한 지반조사결과에 기초하고 있다. 지반조사 자료가 부족한 지역에서의 암반 물성을 보다 객관적이고 추계학적(stochastic)으로 예측하기 위해 유전알고리즘(genetic algorithm)과 조건부 모사 기법(conditional simulation)을 사용하였다. 지구통계학적 모델링의 방법으로 조건부 모사를 실시한 후에 공간상관관계의 최적화과정을 통해 암반 물성을 구하였다. 유전알고리즘을 이용할 경우 크리깅에 의한 분산의 감소 현상을 극복하고 확률적으로 값을 제시할 수 있었다. 또한 30번의 확률적 등가치(equi-probable) 모사를 통해 유전알고리즘으로 구한 값의 불확실성을 정량적인 확률분포 값으로 제시하였고, 교차검증(cross validation) 방법으로 유전알고리즘의 신뢰도를 검증하였다.

• International Journal of Industrial Entomology and Biomaterials
• /
• 제9권2호
• /
• pp.207-215
• /
• 2004

The present study was carried out to evaluate the ISSR and RAPD markers for their efficiency as genetic marker systems to establish the relationships between 18 mulberry genotypes. A total of 36 from 56 (64%) RAPD primers and 12 from 48 (25%) ISSR primers produced reproducible amplification patterns. A high proportion of polymorphic bands ranging from 44 to 91% was observed respectively with RAPD and ISSR markers. The average Resolving Power (Rp) of ISSR primers was higher than RAPD primers. The ISSR primers, UBC 825, 868 and 873, and RAPD primers, UBC 712, 720 and 729, possessed the highest Rp values and could in each instance distinguish all the 18 genotypes. Similarity matrix values were estimated based on Jaccards coefficient, considering 109 polymorphic ISSR and 212 polymorphic RAPD bands and two dendrograms were constructed. The dendrograms obtained with ISSR and RAPD markers distinguished the eight exotic genotypes from the ten indigenous (Indian) genotypes. A significant correlation value (r=0.959; p=0.001) for the cophenetic matrix between the RAPD and ISSR matrices was observed. The results indicated that the ISSR and RAPD markers could assist in the differentiation of genotypes and permit the determination of genetic distances that might be exploited by mulberry breeders in improvement programs.

• 한국정밀공학회지
• /
• 제16권11호
• /
• pp.106-115
• /
• 1999

Design parameters and goals play important roles in design. Design goals are the required functions of the design elements and explicitly expressed by design parameters. Design parameters also indicate the relations among design elements, by which constraint networks can be constructed and some useful information can be induced. In this study, the mechanical design process is assumed to be the assignment of design goals and their realization through the evolutionary refinement of the design parameters. Thus an integrated design system is proposed to support the process of assigning the design goals and refining the values of the design parameters. In the design system, a genetic engine that utilizes a genetic algorithm is installed to simulate an iterative design process, which leads to an evolutionary design. The genetic engine treats design parameters as genes and design goals as evaluation function. Re-design and design modification are facilitated by the design parameters. The re-design can be activated in the design system by using the information stored in the design parameters when design parameters or goals are changed.

• 한국작물학회지
• /
• 제63권4호
• /
• pp.314-321
• /
• 2018

Durum (Triticum turgidum L. ssp. durum) is a major crop species cultivated for human consumption worldwide. In Tunisia, salt stress is one of the main problems that limit crop production. 'Mahmoudi' was selected as the most salt-sensitive out of 11 Tunisian durum cultivars. Using the salt-tolerant cultivar 'Om Rabia', resistant and susceptible cultivars were evaluated to compare genetic responses under salt stress. At the fully expanded third leaf stage, salt stress was applied by submerging the pots in 500 mM NaCl for 5 min every day for saline water irrigation in the greenhouse. The treatment was applied for 1 week and salt stress tolerance was determined by changes of growth parameters to the control condition. The salt tolerance trait index and salt tolerance index were calculated and used as selection criteria. The expression levels of TdHKT1;4, TdHKT1;5, and TdSOS1 were examined using qPCR. For further evaluation of physiological responses, salt stress (150 mM NaCl) was additionally applied for 48 h at the fully expanded third-leaf stage. Increased expression of the genes responsible for salt tolerance and proline content in tolerant durum can be used to broaden genetic diversity and provide genetic resources for the durum breeding program.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.167-174
• /
• 2022

In metaheuristic algorithms such as Genetic Algorithm (GA), initial population has a significant impact as it affects the time such algorithm takes to obtain an optimal solution to the given problem. In addition, it may influence the quality of the solution obtained. In the machine learning field, feature selection is an important process to attaining a good performance model; Genetic algorithm has been utilized for this purpose by scientists. However, the characteristics of Genetic algorithm, namely random initial population generation from a vector of feature elements, may influence solution and execution time. In this paper, the use of a statistical algorithm has been introduced (Chi2) for feature relevant checks where p-values of conditional independence were considered. Features with low p-values were discarded and subject relevant subset of features to Genetic Algorithm. This is to gain a level of certainty of the fitness of features randomly selected. An ensembled-based learning model for Hepatitis has been developed for Hepatitis C stage classification. 1385 samples were used using Egyptian-dataset obtained from UCI repository. The comparative evaluation confirms decreased in execution time and an increase in model performance accuracy from 56% to 63%.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2005년도 BIOINFO 2005
• /
• pp.395-398
• /
• 2005

Genetic association case-control studies using DNA pools are efficient ways of detecting association between a marker allele and disease status. DNA pooling is an efficient screening method for locating susceptibility genes associated with the disease. However, DNA pooling is efficient only when allele frequency estimation is done precisely and accurately. Through the evaluation of empirical type I errors and empirical powers by simulation, we will evaluate the methods that correct for preferential amplification of nucleotides when estimating the allele frequency of single-nucleotide polymorphisms.

• 한국정보과학회논문지:시스템및이론
• /
• 제37권2호
• /
• pp.66-75
• /
• 2010

본 논문에서는 GPU(graphics processing unit)를 이용하여 오목의 인공지능 알고리즘 연산을 고속으로 수행하기 위한 효율적인 알고리즘 설계와 구현 방법을 제안한다. 본 논문에서 제안하는 게임 인공지능은 최소-최대 게임 트리(min-max game tree)와 유전 알고리즘(genetic algorithm)의 협업적 구조로 설계된다. 게임 트리와 유전 알고리즘의 평가함수(evaluation function) 부분은 많은 계산 량을 소모하지만 해 공간(solution space)의 수많은 후보 벡터에 대해 독립적으로 수행되기 때문에 본 논문에서는 이를 GPU 상에서의 대량 병렬처리를 통해 수행한다. NVIDIA CUDA(compute unified device architecture)환경에서의 실제 구현을 통해 CPU에서의 처리에 비해 게임 트리는 400배 이상의 수행 속도의 향상을, 유전 알고리즘은 300배 이상의 수행 속도의 향상을 각각 보였다. 본 논문에서는 스레드(thread)의 넘침(overflow)을 피하고 보다 효과적인 해 공간 탐색을 위해, 게임 트리를 이용하여 근방의 몇 단계까지 전역 탐색(full search)을 수행한 후 이후 단계는 유전 알고리즘을 이용하여 선별 탐색을 수행하는 협업적 인공지능을 제안한다. 다양한 실험 결과를 통해 제안하는 알고리즘은 게임의 인공지능을 향상시키고 게임의 규칙으로부터 주어진 시간 내에 문제를 해결할 수 있음을 보인다.