• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1997년도 추계학술대회발표논문집; 홍익대학교, 서울; 1 Nov. 1997
• /
• pp.105-108
• /
• 1997

Previous studies in stock market predictions using artificial intelligence techniques such as artificial neural networks and case-based reasoning, have focused mainly on spot market prediction. Korea launched trading in index futures market (KOSPI 200) on May 3, 1996, then more people became attracted to this market. Thus, this research intends to predict the daily up/down fluctuant direction of the price for KOSPI 200 index futures to meet this recent surge of interest. The forecasting methodologies employed in this research are the integration of genetic algorithm and artificial neural network (GAANN) and the integration of genetic algorithm and case-based reasoning (GACBR). Genetic algorithm was mainly used to select relevant input variables. This study adopts the categorical data preprocessing based on expert's knowledge as well as traditional data preprocessing. The experimental results of each forecasting method with each data preprocessing method are compared and statistically tested. Artificial neural network and case-based reasoning methods with best performance are integrated. Out-of-the Model Integration and In-Model Integration are presented as the integration methodology. The research outcomes are as follows; First, genetic algorithms are useful and effective method to select input variables for Al techniques. Second, the results of the experiment with categorical data preprocessing significantly outperform that with traditional data preprocessing in forecasting up/down fluctuant direction of index futures price. Third, the integration of genetic algorithm and case-based reasoning (GACBR) outperforms the integration of genetic algorithm and artificial neural network (GAANN). Forth, the integration of genetic algorithm, case-based reasoning and artificial neural network (GAANN-GACBR, GACBRNN and GANNCBR) provide worse results than GACBR.

• Asian-Australasian Journal of Animal Sciences
• /
• 제17권5호
• /
• pp.603-607
• /
• 2004

Randomly Amplified Polymorphic DNA-Polymerase Chain Reaction (RAPD-PCR) analysis was carried out with a battery of 11 random decamer primers to study band frequency (BF), genetic identity index (I) and mean average percentage difference (MAPD) between Bhadawari and Murrah breeds of buffalo. The primers OPA04 and BG15 resolved a band of 460 bp, which was present only in animals of Bhadawari breed. Whereas, the primers OPA14, BG27 and BG28 produced Murrah specific fragments of sizes 730 bp and 1,230 bp, respectively. The estimate of genetic identity index was highest (0.845) with the primer OPA01 and the lowest (0.479) with the primer BG27. The genetic identity index pooled over the primers was 0.596${\pm}$0.037 between these two breeds. The highest MAPD estimate (53.9) between the two breeds was obtained with the primer BG27 and the lowest (14.3) with the primer OPA01. It might be concluded that the genetic identity index between these two breeds calculated on the basis of BF showed moderate level of genetic identity with the primers employed. MAPD calculated on the basis of uncommon bands also demonstrated lower to medium level of genetic difference between Bhadawari and Murrah breeds of buffalo.

• 한국가금학회지
• /
• 제25권3호
• /
• pp.103-111
• /
• 1998

This study was carried out to estirnate the heritabilities and genetic correlations on egg shape index and internal egg qualities ; shell thickness, alburnin heights and Haugh units for breeding plan and selection in Korean native chicken. Data analyzed were the records of 46,908 eggs from 43() layers from April, 1994 to September, 1995. The egg shape index at the first egg, 300 days and 500 days of ages were 74.771, 74.468 and 73.702; the shell thickness were 0.345, 0.344 and 0. 334mm; the alburnen heights were 6.579, 6.130 and 5.318mm; the Haugh units were 86.859, 81.014 and 73.565 respectively. The heritability estimates of egg shape index and internal egg qualities based on the variance of sire, dam and combined components at 300 days of age were 0.136, 0.954 and 0.545 for egg shape index; 0.201, 0.622 and 0.421 for shell thickness; 0.410, 0.961 and 0.633 for albumen height ; 0.353, 0.962 and': 0.608 for Haugh units. The genetic correlation coefficient between shell thickness and albumen height was -0.044~0.824; 0.016~0.949 between Haugh units and shell thickness 0.313~0.941 between albumen height and Haugh units, respectively.

• 생명과학회지
• /
• 제14권1호
• /
• pp.115-120
• /
• 2004

민자주방망이버섯은 우수한 식용버섯으로 세계적으로 분포하고 있는 종이다. 민자주방망이버섯과 5가지 송이과버섯 종들의 유전적인 변이와 분류학적 관계를 RAPD에 의해 분석 하였다. RAPD에 15가지 random primer를 사용하였다. 버섯들의 유전적 거리는 UPCMA를 사용하여 측정하였고 계통유전학적 유연관계는 neighnor-joining (NJ) 방법을 사용하여 분석하였다. PCR에 의하여 증폭된 RAPD 절편들은 100bp에서 1600 bp이었다. Nei-Li의 유전적 거리는 228개의 DNA밴드를 사용하여 계산하였고 이를 바탕으로 계통유전학적 계통수를 만들었다. 민자주방망이버섯, 자주방망이버섯 아재비, 가랑잎애기버섯, 밀버섯, 만가닥버섯, 졸각버섯의 유전적 변이 는 각각 0∼21.3%, 21.2∼28.0%, 15.4∼23.0%, 14.0∼21.8%, 16,5∼34.6%, 12.4∼27.4%이였다. CI (Consistency index), RI (Retention index), HI (Homoplasy inedx)의 값은 각각 0.5217, 0.5769, 0.5156이었다. 또한 NJ tree로 두 그룹을 만들 수 있었다. 유전적 거리는 민자주방망이버섯과 자주방망이버섯아재비보다 민자주방망이버섯과 밀버섯이 더 가까웠다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 춘계정기학술대회 e-Business를 위한 지능형 정보기술 / 한국지능정보시스템학회
• /
• pp.347-356
• /
• 2000

This paper compares four models of artificial neural networks (ANN) supported by genetic algorithms the prediction of stock price index. Previous research proposed many hybrid models of ANN and genetic algorithms(GA) in order to train the network, to select the feature subsets, and to optimize the network topologies. Most these studies, however, only used GA to improve a part of architectural factors of ANN. In this paper, GA simultaneously optimized multiple factors of ANN. Experimental results show that GA approach to simultaneous optimization for ANN (SOGANN3) outperforms the other approaches.

• 한국환경과학회지
• /
• 제14권3호
• /
• pp.265-269
• /
• 2005

This study was carried out to provide the basic data for an identifying system for Iris species distributed in Korean market from complete analysing of genetic relationship between three native Iris species and one cultivar bred from the native Iris plant. RAPD analysis of genetic relationship among 4 Irises was possible. According to the RAPD analysis, they were divided into two groups. Among 4 Irises used in this study, Iris laevigata 'Veriegata', Iris laevigata and Iris setosa were classified into the same group since they had many similarities even though the habitat of Iris laevigata in Korean peninsular is restricted mainly in the south and Iris setosa is naturally inhabited in the northern part of Kangwondo. The value for the dissimilarity index of Iris laevigata and Iris laevigata 'Veriegata' was 6.757. The value for the dissimilarity index of Iris laevigata and Iris dichotoma was 95.000, so that they were genetically the farthest among them since the genetic relationship between two species are separated far if the value of the dissimilarity index is close to 100.

• 한국정밀공학회지
• /
• 제21권7호
• /
• pp.115-123
• /
• 2004

This paper deals with the gait optimization of via points on biped robot. ZMP(Zero Moment point) is the most important index in a biped robot's dynamic walking stability. To stable walking of a biped robot, leg's trajectory and a desired ZMP trajectory is required, balancing motion is solved by FDM(Finite Difference Method). In this paper, optimal index is defined to dynamically stable walking of a biped robot, and genetic algorithm is applied to optimize gait trajectory and balancing motion of a biped robot. By genetic algorithm, the index of walking parameter is efficiently optimized, and dynamic walking stability is verified by ZMP verification equation. Genetic algorithm is only applied to balancing motion, and is totally applied to whole trajectory. All of the suggested motions of biped robot are investigated by simulations and verified through the real implementation.

• Journal of the Optical Society of Korea
• /
• 제14권3호
• /
• pp.277-281
• /
• 2010

We propose a design and optimization method for a dielectric-loaded surface plasmon polariton waveguide using a genetic algorithm. This structure consists of a polymer ridge on top of two layers of substrate and gold film. The thickness, width and refractive index of the ridge are designed to optimize the figures of merit including mode confinement and propagation length. The modal analysis combined with the effective index method shows that the designed waveguide exhibits a fundamental propagation mode with high mode confinement while ensuring that the propagation loss remains relatively low.

• 원예과학기술지
• /
• 제32권1호
• /
• pp.84-90
• /
• 2014

우리나라에서 먹넌출은 안면도 지역에서만 소나무 숲에서 제한적으로 분포하는 덩굴성 식물이다. 본 연구는 먹넌출 집단의 분포형태와 특성, 유전다양성 및 공간분포에 따른 유전구조를 파악하는데 있다. 선발된 8개 I-SSR primer에서 총 50개의 I-SSR 증폭산물을 얻었으며 37개의 단형성 증폭산물을 제외한 13개의 다형적 증폭산물을 분석에 이용하였다. 공간적 자기상관 분석을 위한 조사구 $90m{\times}70m$내에 총 39개체의 먹넌출이 자생하고 있었으며, 군집지수(aggregation index)는 0.706으로 집중분포(clumped distribution)하는 공간분포를 나타냈다. I-SSR 표지자 분석 결과 39개체 중 유전자형이 서로 다른 21개의 유성생식체(genet)가 식별되었으며, 유전자형 비율(G/N)은 53.8%, 유전자형 다양성(D)은 0.966, 유전자형 균등도(E)는 0.946으로 각각 나타났다. Shannon의 다양성지수(I = 0.598)는 적은 개체수와 제한적 분포에도 불구하고 다른 수종들에 비해 비교적 높은 유전다양성을 나타냈다. Tanimoto distance를 이용한 공간적 자기상관 분석 결과 안면도 먹넌출의 현지외 보존을 위한 표본 추출 전략은 6m 이상의 간격을 두고 개체를 선발하는 것이 타당한 것으로 나타났다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제16권12호
• /
• pp.1705-1710
• /
• 2003

A small body size of Brown Tsaiya laying duck is desirable to reduce maintenance requirements, so the body weight at 40 weeks of age (BW40) has to be maintained at its current level. Egg weight has to be maintained at around 65 g to meet market requirements. Eggshell strength at 40 weeks of age (ES40) must to be increased in order to maintain a low incidence of broken eggs. Thus, number of eggs laid up to 52 weeks of age (EN52) has to be increased without negative correlated response on ES40. A new linear genetic selection index was used: $I_g=a_0{\times}GEW40\;(g)+a_1{\times}GBW40\;(g)+a_2{\times}GES40\;(kg/cm^2)+a_3{\times}GEN52\;(eggs)$ where GEW40, GBW40, GES40 and GEN52 were the multitrait best linear unbiased prediction (MT-BLUP) animal model predictors of the breeding values respectively of egg weight and body weight at 40 weeks of age (EW40, BW40), ES40 and EN52. The coefficients $a_0$, $a_1$, $a_2$ and $a_3$ were calculated with constraints of 0.0 g, 0.0 g and $0.013kg/cm^2$ for expected genetic gains in EW40, BW40 and ES40 respectively and maximum gain in EN52. Since 1997, the drakes and the ducks were selected according to their own indexes, with this new genetic selection index. From G0 to G4, the average per generation predicted genetic responses in female duck were +0.05 g for EW40, +0.92 g for BW40, $+0.035kg/cm^2$ for ES40 and +2.13 eggs for EN52. Which represented respectively 0.07%, 0.06%, 0.67% and 1.0% of the means of the EW40, BW40, ES40 and EN52. For ES40 and EN52, it represented also respectively 16.1% and 21.6% of the additive genetic standard deviation of these traits. Thevse results indicated that selection of laying Brown Tsaiya by a restricted genetic selection index and with MT-BLUP animal model could be an efficient tool for improving the efficiency of egg production, increasing egg shell strength and egg number while holding egg weight and body weight constants.