• Communications for Statistical Applications and Methods
• /
• v.29 no.1
• /
• pp.65-83
• /
• 2022

Although various statistical methods have been developed to map time-dependent genetic factors, most identified genetic variants can explain only a small portion of the estimated genetic variation in longitudinal traits. Gene-gene and gene-time/environment interactions are known to be important putative sources of the missing heritability. However, mapping epistatic gene-gene interactions is extremely difficult due to the very large parameter spaces for models containing such interactions. In this paper, we develop a Gaussian process (GP) based nonparametric Bayesian variable selection method for longitudinal data. It maps multiple genetic markers without restricting to pairwise interactions. Rather than modeling each main and interaction term explicitly, the GP model measures the importance of each marker, regardless of whether it is mostly due to a main effect or some interaction effect(s), via an unspecified function. To improve the flexibility of the GP model, we propose a novel grid-based method for the within-subject dependence structure. The proposed method can accurately approximate complex covariance structures. The dimension of the covariance matrix depends only on the number of fixed grid points although each subject may have different numbers of measurements at different time points. The deviance information criterion (DIC) and the Bayesian predictive information criterion (BPIC) are proposed for selecting an optimal number of grid points. To efficiently draw posterior samples, we combine a hybrid Monte Carlo method with a partially collapsed Gibbs (PCG) sampler. We apply the proposed GP model to a mouse dataset on age-related body weight.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.2
• /
• pp.66-73
• /
• 1997

In many optimal methods for the structural design, the structural analysis is performed with the given design parameters. Then the design sensitivity is calculated based on its structural anaysis results. There-after, the design parameters are changed iteratively. But genetic algorithm is a optimal searching technique which is not depend on design sensitivity. This method uses for many design para- meter groups which are generated by a designer. The generated design parameter groups are become initial population, and then the fitness of the all design parameters are calculated. According to the fitness of each parameter, the design parameters are optimized through the calculation of reproduction process, degradation and interchange, and mutation. Those are the basic operation of the genetic algorithm. The changing process of population is called a generation. The basic calculation process of genetic algorithm is repeatly accepted to every generation. Then the fitness value of the element of a generation becomes maximum. Therefore, the design parameters converge to the optimal. In this study, the optimal design pro- cess of a machine tool structure for static loading is presented to determine the optimal base supporting points and structure thickness using a genetic algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.621-626
• /
• 2003

In this paper, we modeled a virtual life (VL) that reacts to the user s action according to its own behavioral characteristics and grows itself. We established some conditions with which such a VL is designed. Genetic Algorithm is used for the growth process that changes the VL s properties. In this process, the parameter values of the VL s properties are encoded as one chromosome, and the GA operations change this chromosome. The VL s reaction to the user s action is determined by these properties as well as the general expectation of each reaction. These properties are evaluated through 5 fitness measures so as to deal with multi-objective criteria. Here, we present the simulation of the growth Process, and show some experimental results.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.1 s.94
• /
• pp.49-60
• /
• 1999

This paper addresses a welding task sequencing for robot arc welding process planning. Although welding task sequencing is an essential step in the welding process planning, it has not been considered through a systematic approach, but it depends rather on empirical knowledge. Thus, an effective task sequencing for robot arc welding is required. Welding perations can be classified by the number of welding robots. Genetic algorithms are applied to tackle those welding task sequencing problems. A genetic algorithm for traveling salesman problem (TSP) is utilized to determine welding task sequencing for a MultiWeldline-SingleLayer problem. Further, welding task sequencing for multiWeldline-MultiLayer welding is investigated and appropriate genetic algorithms are introduced. A random key genetic algorithm is also proposed to solve multi-robot welding sequencing : MultiWeldline with multi robots. Finally, the genetic algorithm are implemented for the welding task sequencing of three dimensional weld plate assemblies. Robot welding operations conforming to the algorithms are simulated in graphic detail using a robot simulation software IGRIP.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.1
• /
• pp.121-126
• /
• 2009

Korean ginseng (Panax ginseng C. A. Meyer) has been used as an important medicinal plant in the Orient for a long time. It has been claimed that ginseng has many beneficial bioactive effects on human health, such as antitumor, antistress, antiaging and enhancing immune functions. Red ginseng possibly have new ingredients converted during steaming and dry process from fresh ginseng. In this study, pharmacological efficacy and ingredient conversion of ginseng by 9 repetitive steaming and drying process were investigated measuring conversion efficiency of acidic-polysaccharide, phenolic compounds and inhibition of peroxide lipides. It was found that acidic-polysaccarides were increased by heat treatment. In addition, maltol of phenolic compounds, strong antioxidant, produced during the process of red ginseng by Maillard reaction. Acidic-polysaccarides and maltol were increased after the 1st and 3rd steaming and drying treatments, but they were decreased gradually after 5th, 7th, and 9th treatments. Antioxidant activity was increased as increasing treatment times of steaming and drying without significance. Effect of red ginseng extract on inhibition of peroxide was increased gradually until after the 7th treatment, but remarkably decreased after the 9th treatment.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.5
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.152-154
• /
• 2005

In this paper, we propose a new architecture of Fuzzy Polynomial Neural Networks(FPNN) by means of genetically optimized Fuzzy Polynomial Neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially Genetic Algorithms(GAs). The design of the network exploits the extended Group Method of Data Handling(GMDH) with some essential parameters of the network being provided by the designer and kept fixed throughout the overall development process. This restriction may hamper a possibility of producing an optimal architecture of the model. The proposed FPNN gives rise to a structurally optimized network and comes with a substantial level of flexibility in comparison to the one we encounter in conventional FPNNs. It is shown that the proposed genetic algorithms-based Fuzzy Polynomial Neural Networks is more useful and effective than the existing models for nonlinear process. We experimented with Medical Imaging System(MIS) dataset to evaluate the performance of the proposed model.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.3
• /
• pp.55-65
• /
• 2005

In recent manufacturing systems, most jobs may have several process plans, such as alternative sequence of operations, alternative machine etc. A few researches have addressed the necessity for the integration of process planning and scheduling function for efficient use of manufacturing resources. But the integration problem is very difficult and complex. Many prior researches considered them separately or sequentially. It introduces overlapping or partial duplications in solution efforts. In this paper, Integration problem of jobs with multiple process plans in a job shop environment Is addressed. In order to achieve an efficient integration between process planning and scheduling by taking advantage of the flexibility that alternative process plans offer, we designed GA(Genetic Algorithm)-based scheduling method. The performance of proposed GA is evaluated through comparing integrated scheduling with separated scheduling in real world company with alternative machines and sequences of operations. Also, a couple of benchmark problems are used to evaluate performance. The integrated scheduling method in this research can be effectively epplied to the real case.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07a
• /
• pp.33-36
• /
• 2004

The process modeling for the growth rate in pulsed laser deposition(PLD)-grown ZnO thin films is investigated using neural networks(NNets) and the process recipes is optimized via genetic algorithms(GAs). D-optimal design is carried out and the growth rate is characterized by NNets based on the back-propagation(BP) algorithm. GAs is then used to search the desired recipes for the desired growth rate. The statistical analysis is used to verify the fitness of the nonlinear process model. This process modeling and optimization algorithms can explain the characteristics of the desired responses varying with process conditions.

• Journal of Genetic Medicine
• /
• v.6 no.1
• /
• pp.38-55
• /
• 2009

Purpose: This study was undertaken to provide the framework for development of a genetic counseling training program, and an accreditation and certification process suitable for non-M.D. genetic counselors in Korea. Materials and Methods: Global standards of genetic counseling curriculums, training program accreditation (TPA), and the certification process for genetic counselors (CPGC) in the U.S.A and Japan were reviewed, and a questionnaire survey was performed to elicit opinions among health-care providers including physicians, nurses, technicians, researchers, and educators. In addition, input from professional communities, including the Korean Society of Medical Genetics (KSMG) and Institute for Genetic Testing Evaluation, was sought in formulating the framework of this study. Results: Comparison of U.S.A. and Japan educational systems showed similarities in curriculum, accreditation, and certification programs. Analysis of 117 respondents opinions showed a high level of agreement in the area of global standards; 88% indicated that KSMG should be in charge of TPA and CPGC, while 77% favored a certification exam composed of both written exam and interview components. Conclusion: Based upon this study we propose that the KSMG should be in charge of providing the TPA and CPGC for non-MD genetic counselors. Requirements for the entrance to a Master's degree genetic counseling program should be open to successful four year undergraduate students in all areas, provided the candidates demonstrate the abilities to master the graduate level of study in human genetics, clinical genetics, statistics, psychology, and other required subjects. Eligibility for certification should include qualified candidates of genetic counseling with no formally approved education, but a sufficient amount of clinical experience, in addition to accredited program graduates. Certification examinations should be carried out every two years and the certification should be good for five years, as is the case in Japan.