• Proceedings of the Korean Environmental Health Society Conference
• /
• 2004.12a
• /
• pp.87-87
• /
• 2004

• Journal of the Korean Institute of Educational Facilities
• /
• v.11 no.3
• /
• pp.57-64
• /
• 2004

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.11 no.3
• /
• pp.135-142
• /
• 2011

Unlike using the sequence-based representation for a chromosome in previous genetic algorithms for Bayesian structure learning, we proposed a matrix representation-based genetic algorithm. Since a good chromosome representation helps us to develop efficient genetic operators that maintain a functional link between parents and their offspring, we represent a chromosome as a matrix that is a general and intuitive data structure for a directed acyclic graph(DAG), Bayesian network structure. This matrix-based genetic algorithm enables us to develop genetic operators more efficient for structuring Bayesian network: a probability matrix and a transpose-based mutation operator to inherit a structure with the correct edge direction and enhance the diversity of the offspring. To show the outstanding performance of the proposed method, we analyzed the performance between two well-known genetic algorithms and the proposed method using two Bayesian network scoring measures.

• Korean Journal of Poultry Science
• /
• v.28 no.2
• /
• pp.155-163
• /
• 2001

Gene and cell transfer technique will serve as a powerful tool for the genetic improvement of the poultry and to yield useful products. For avian transgenesis, Japanese quail may serve as an excellent animal model because of its small body size and fast growth rate. Recent progress was described on the manipulation of quail embryos such as the introduction of foreign genes and cells, and the subsequent culturing of the manipulated embryos yielding hatchlings. Intraspecific donor-derived offspring have been available in quail, however, further investigation will be required to obtain interspecific offspring with the aim of rescuing endangered species. Trans genesis will also be useful for improving the profitability and quality of poultry stocks and for developing stocks with novel uses. Considerable progress should soon be made toward the production of transgenic poultry. The key feature of the procedure described here is that embryos are initially taken out from the shell for ease of manipulation and then placed back in culture in addition to various operations midway during culture.

• Asian-Australasian Journal of Animal Sciences
• /
• v.2 no.1
• /
• pp.23-26
• /
• 1989

Treatment of mice with 0.04% anthranilic acid (AnA) as drinking water resulted in an apparent stimulation of pup's growth and food intake of mothers in their first lactations associated with an increased rearing rate and no alteration in plasma prolactin level. AnA showed no significant effects on the day of vaginal opening, the pattern of estrous cycles, plasma growth hormone level and endocrine organ weights of the female and male offspring. The growth of male offspring was significantly retarded by AnA, however, their reproductivity was quite normal. The results indicate the AnA can simulate lactation of mice through little modulation of endocrine systems.

• Asian-Australasian Journal of Animal Sciences
• /
• v.4 no.2
• /
• pp.165-168
• /
• 1991

The maternal weigh-suckle-weigh (WSW) method for estimating milk production of sows was further evaluated by comparing this to the traditional WSW method. Twenty one estimates of hourly milk production were obtained by both methods. Total hourly milk production between the two methods was not significantly different (292.4 vs 303.3 g/h, p > 0.05). Hourly milk production determined by the maternal WSW method was highly correlated with hourly milk production estimates using the traditional WSW method ($R_2$ = 0.94, p < 0.001). When corrections for metabolic and salivary losses were made, the milk production figures for the maternal WSW method were approximately 27% less than those estimated by the traditional WSW method.

• The Korean Journal of Zoology
• /
• v.34 no.3
• /
• pp.389-393
• /
• 1991

To obtain monozygotic multiplets from 8-cell mouse embryos, we artificially constructed chimeric embryos by introducing one blastomere (donor) of 8-cell embryos of Fl hybrid (C57BL/6 X CBA) mice into 4-cell ICR mouse embryos (carrier) of which one blastomere had been previously removed with a micromanipulator. After 42 h of culture, the developmental frequency of chimeric embryos to normal morula and blastocyst was 95% (310/328). When chimeric embryos at morula or blastocvst stage were transferred to pseudopregnant mice,39%, (70/180) of them were born. Most of the offspring (56/70) were the carrier type in coat color, whereas only three of them were the donor type, of which ho were assumed to be derived from single 8-cell donor embryo. Because the two donor type mice Ivere the same sex and produced only the donor type offspring from a testcross, they are probably monozvgotic multiplets of 8-cell mouse embryos. However, since their internal chimerism was not able to be examined, it remains to be determined if their genetic constitutions are identical.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.81-84
• /
• 1998

Genetic Algorithms (GAs) are stochastic algorithms whose search methods model some natural phenomena. The procedure of GAs may be divided into two sub-procedures : Operation and Selection. Chromosomes can produce new offspring by means of operation, and the fitter chromosomes can produce more offspring than the less fit ones by means of selection. However, operation which is executed randomly and has some limits to its execution can not guarantee to produce fitter chromosomes. Thus, we propose a method which gives a directional information to the genetic operator by reinforcement learning. It can be achived by using neural networks to apply reinforcement learning to the genetic operator. We use the amount of fitness change which can be considered as reinforcement signal to calcualte the error terms for the output units. Then the weights are updated using backpropagtion algorithm. The performance improvement of GAs using reinforcement learning can be measured by applying the pr posed method to GA-hard problem.

• Journal of Animal Science and Technology
• /
• v.52 no.6
• /
• pp.459-466
• /
• 2010

In this study, we suggest an objective standard in selection of candidate horse mates. Korea Racing Authority provided racing records and pedigree information of 44 sires and 954 dams. The datasets were used to predict Racing Indices represented by the averages of earnings earned by offspring for each dam and sire that indicate the racing performance of its domestic progeny. Proportion of wins and second places to the number of taken races and the mean of distances for the won races of a sire were significant factors in linear model with minimum prediction errors. For dam, those factors were the average of earned money per race, number of outstanding broodmares in pedigree, and the comparable index which indicates the relative affinity with its mate. We can use the resultant model for a horse mate by choosing one of the candidates with the largest predicted value for hypothetical offspring.

• International Journal of Aeronautical and Space Sciences
• /
• v.3 no.1
• /
• pp.50-60
• /
• 2002

A new co-evolutionary algorithm, of which the convergence speed is accelerated by neural networks, is proposed and verified in this paper. To reduce computational load required for co-evolutionary optimization processes, the cost function and constraint information is stored in the neural networks, and the extra offspring group, whose cost is computed by the neural networks, is generated. It increases the offspring population size without overloading computational effort; therefore, the convergence speed is accelerated. The proposed algorithm is applied to attitude control design of flexible satellites, and it is verified by computer simulations and experiments using a torque-free air bearing system.