• Wind and Structures
• /
• v.27 no.1
• /
• pp.41-57
• /
• 2018

Concentrated Solar Photovoltaic (CPV) is a promising alternative to conventional solar structures. These solar tracking structures need to be optimized to be competitive against other types of energy production. In particular, the selection of the structural parameters needs to be optimized with regards to the dynamic wind response. This study aims to evaluate the effect of the main structural parameters, as selected in the preliminary design phase, on the wind response and then on the weight of the steel support structure. A parametric study has been performed where parameters influencing dynamic wind response are varied. The study is performed using a semi-deterministic time-domain wind analysis method. Unsteady aerodynamic model is applied for the shape of the CPV structure collector at different configurations in conjunction with a consistent mass-spring-damper model with the corresponding degrees of freedom to describe the dynamic response of the system. It is shown that, unlike the static response analysis, the variation of the peak wind response with many structural parameters is highly nonlinear because of the dynamic wind action. A steel structural optimization process reveals that close attention to structural and site wind parameters could lead to optimal design of CPV steel support structure.

• Journal of the Society of Naval Architects of Korea
• /
• v.51 no.1
• /
• pp.78-87
• /
• 2014

Recently the offshore wind turbine development is requested to be installed off south-west coast and Jeju island in Korea. Reliable and robust support structures are required to meet the demand on the offshore wind turbine in harsh and rapidly varying environmental conditions. Monopile is the most preferred substructure in shallow water with long term experiences from the offshore gas and oil industries. This paper presents an optimum design of a monopile connection with grouted transition piece (TP) for the reliable and cost-effective design purposes. First, design loads are simulated for a 5 MW offshore wind turbine in site conditions off the southwest coast of Korea. Second, sensitivity analysis is performed to investigate the design sensitivity of geometry and material parameters of monopile connection based on the ultimate and fatigue capacities according to DNV standards. Next, optimization is conducted to minimize the total mass and resulted in 30% weight reduction and the optimum geometry and material properties of the monopile substructure of the fixed offshore wind turbine.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.613-623
• /
• 2022

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1993.04a
• /
• pp.244-244
• /
• 1993

• Proceedings of the Korean Nuclear Society Conference
• /
• 2001.05a
• /
• pp.339.2-339
• /
• 2001

• ETRI Journal
• /
• v.32 no.1
• /
• pp.120-128
• /
• 2010

In this paper, we describe a modified fixed-threshold sequential minimal optimization (FSMO) for 1-slack structural support vector machine (SVM) problems. Because the modified FSMO uses the fact that the formulation of 1-slack structural SVMs has no bias, it breaks down the quadratic programming (QP) problems of 1-slack structural SVMs into a series of smallest QP problems, each involving only one variable. For various test sets, the modified FSMO is as accurate as existing structural SVM implementations (n-slack and 1-slack SVM-struct) but is faster on large data sets.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1999.10a
• /
• pp.127-132
• /
• 1999

A mobile IP is proposed to support host mobility over the current Internet. One of the most important issues on the host mobility is location and routing schemes that allow mobile hosts to move effectively from one site to another. In a Mobile IP environment, frequent handoffs are likely to degrade the performance by minimizing the loss of datagrams during handoffs. The handoff scheme is using routing optimization and binding extension to improve the performance by minimizing the average transfer delay of messages and packet loss. Simulation details show the improvement of transport delays and packet loss rate.

• Journal of Computing Science and Engineering
• /
• v.9 no.2
• /
• pp.39-50
• /
• 2015

Genetic algorithm (GA) and particle swarm optimization (PSO) are two excellent approaches to multimodal optimization problems. However, slow convergence or premature convergence readily occurs because of inappropriate and inflexible evolution. In this paper, a novel optimization algorithm with a flexible grid optimization (FGO) is suggested to provide adaptive trade-off between exploration and exploitation according to the specific objective function. Meanwhile, a uniform agents array with adaptive scale is distributed on the gird to speed up the calculation. In addition, a dominance centroid and a fitness center are proposed to efficiently determine the potential guides when the population size varies dynamically. Two types of subregion division strategies are designed to enhance evolutionary diversity and convergence, respectively. By examining the performance on four benchmark functions, FGO is found to be competitive with or even superior to several other popular algorithms in terms of both effectiveness and efficiency, tending to reach the global optimum earlier. Moreover, FGO is evaluated by applying it to a parameter decision in a least squares support vector machine (LS-SVM) to verify its practical competence.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2006.04a
• /
• pp.828-835
• /
• 2006

Spacer grid springs support the fuel rods in a nuclear fuel system. The spacer grid is a part of a fuel assembly. Since a spring has repeated contacts with the fuel rod, fretting wear occurs on the surface of the spring. Design is usually performed to reduce the wear. The conceptual design process for the spring is defined by using the Independence of axiomatic design and the design is carried out based on the direction that the design matrix indicates. For detailed design an optimization problem is formulated. In optimization, homologous design is employed to reduce fretting wear. The deformation of a structure is called homologous if a given geometrical relationship holds for a given number of structural points before, during, and after the deformation. In this case, the deformed shape of the spring should be the same as that of the fuel rod. 1bis condition is transformed to a function and considered as a constraint in the optimization process. The objective function is minimizing the maximum stress to allow a local plastic deformation. Optimization results show that the contact occurs in a wide range. Also, the results are verified by nonlinear finite element analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.5972-5989
• /
• 2019

With the onset of the big data age, data is growing exponentially, and the issue of how to optimize large-scale data processing is especially significant. Large-scale global optimization (LSGO) is a research topic with great interest in academia and industry. Spark is a popular cloud computing framework that can cluster large-scale data, and it can effectively support the functions of iterative calculation through resilient distributed datasets (RDD). In this paper, we propose a hybrid mechanism of particle swarm optimization (PSO) and differential evolution (DE) algorithms based on Spark (SparkPSODE). The SparkPSODE algorithm is a parallel algorithm, in which the RDD and island models are employed. The island model is used to divide the global population into several subpopulations, which are applied to reduce the computational time by corresponding to RDD's partitions. To preserve population diversity and avoid premature convergence, the evolutionary strategy of DE is integrated into SparkPSODE. Finally, SparkPSODE is conducted on a set of benchmark problems on LSGO and show that, in comparison with several algorithms, the proposed SparkPSODE algorithm obtains better optimization performance through experimental results.