• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.270-272
• /
• 2006

In this paper, we discuss optimal design of Fuzzy Polynomial Neural Networks by means of Genetic Algorithms(GAs) using symbolic coding for non-linear data. One of the major subject of genetic algorithms is representation of chromosomes. The proposed model optimized by the means genetic algorithms which used symbolic code to represent chromosomes. The proposed gFPNN used a triangle and a Gaussian-like membership function in premise part of rules and design the consequent structure by constant and regression polynomial (linear, quadratic and modified quadratic) function between input and output variables. The performance of the proposed model is quantified through experimentation that exploits standard data already used in fuzzy modeling. These results reveal superiority of the proposed networks over the existing fuzzy and neural models.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.5 no.1
• /
• pp.108-115
• /
• 2005

Inherited metabolic diseases (IMD) comprise a large class of genetic diseases involving disorders of metabolism. The majorities are due to defects of single genes that code for enzymes that facilitate conversion of various substances into others. Because of the multiplicity of conditions, many different diagnostic tests are used for screening of IMD. Molecular genetic diagnosis is the detection of pathogenic mutations in DNA and/or RNA samples and is becoming a much more common practice in medicine today. The purpose of molecular genetic testing in IMD includes diagnostic testing, pre-symptomatic testing, carrier screening, prenatal diagnosis, preimplantation testing, and population screening. However, because of the complexity, difficulty in interpreting the result, and the ethical considerations, an understanding of technical, conceptual, and practical aspects of molecular genetic diagnosis is mandatory.

• ETRI Journal
• /
• v.30 no.6
• /
• pp.799-806
• /
• 2008

In this paper, a new design for an error correcting code (ECC) is proposed. The design is aimed to build an ECC circuitry with minimal power consumption. The genetic algorithm equipped with the symbiotic mechanism is used to design a power-efficient ECC which provides single-error correction and double-error detection (SEC-DED). We formulate the selection of the parity check matrix into a collection of individual and specialized optimization problems and propose a symbiotic evolution method to search for an ECC with minimal power consumption. Finally, we conduct simulations to demonstrate the effectiveness of the proposed method.

• Journal of Electrical Engineering and Technology
• /
• v.6 no.4
• /
• pp.493-504
• /
• 2011

The present paper presents a genetic algorithm (GA) to maximize social welfare and perform congestion management by optimally placing and sizing one Thyristor-Controlled Series Capacitor (TCSC) device in a double-sided auction market. Simulation results, with line flow constraints before and after the compensation, are compared through the Sequential Quadratic Programming SQP method, and are used to analyze the effect of TCSC on the congestion levels of modified IEEE 14-bus and 30-bus test systems. Quadratic, smooth and nonsmooth (with sine components due to valve point loading effect) generator cost curves, and quadratic smooth consumer benefit functions are considered. The main aims of the present study are the inclusion of customer benefit in the social welfare maximization and congestion management objective function, the consideration of nonsmooth generator characteristics, and the optimal locating and sizing of the TCSC using real code-based GA to guarantee fast convergence to the best solution.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.6
• /
• pp.1481-1494
• /
• 1997

In hard real-time systems, a timing fault may yield catastrophic results. Dynamic scheduling provides the flexibility to compensate for unexpected events at runtime; however, scheduling overhead at runtime is relatively large, constraining both the accuracy of the timing and the complexity of the scheduling analysis. In contrast, static scheduling need not have any runtime overhead. Thus, it has the potential to guarantee the precise time at which each instruction implementing a control action will execute. This paper presents a new approach to the problem of analyzing high-level language code, augmented by arbitrary before and after timing constraints, to provide a valid static schedule. Our technique is based on instruction-level complier code scheduling and timing analysis, and can ensure the timing of control operations to within a single instruction clock cycle. Because the search space for a valid static schedule is very large, a novel adaptive genetic search algorithm was developed.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.26 no.6
• /
• pp.795-804
• /
• 2002

The optimal design code of an axial flow pump has been developed to determine geometric and fluid dynamic variables under hydrodynamic as well as mechanical design constraints. The design code includes the optimization of the complete radial distribution of the geometry by determining the coefficients of 2$^{nd}$ order polynomials to represent the three-dimensional geometry. The optimization problem has been formulated with a nonlinear multivariable objective function, maximizing the efficiency and stall margin, while minimizing the net positive suction head required. Calculation of the objective function is based on the mean streamline analysis and through-flow analysis using the present state-of-the-art model. The optimal solution is calculated using the penalty function method in which the genetic optimizer is employed. The optimized efficiency and design variables are presented in this paper as a function of non-dimensional specific speed in the range, 2$\leq$ $n_{s}$ $\leq$10. The results can be used in preliminary design of axial flow pumps.

• Nuclear Engineering and Technology
• /
• v.49 no.6
• /
• pp.1250-1258
• /
• 2017

The multigroup transport theory is the basis for many neutronics modules. A significant point of the cross-section (XS) generation procedure is the choice of the energy groups' boundaries in the XS libraries, which must be carefully selected as an unsuitable energy meshing can easily lead to inaccurate results. This decision can require considerable effort and is particularly difficult for the common user, especially if not well-versed in reactor physics. This work investigates a genetic algorithm-based tool which selects an appropriate XS energy structure (ES) specific for the considered problem, to be used for the condensation of a fine multigroup library. The procedure is accelerated by results storage and fitness calculation speedup and can be easily parallelized. The extension is applied to the coupled code SIMMER and tested on the European Sustainable Nuclear Industrial Initiative (ESNII+) Advanced Sodium Technological Reactor for Industrial Demonstration (ASTRID)-like reactor system with different fitness functions. The results show that, when the libraries are condensed based on the ESs suggested by the algorithm, the code actually returns the correct multiplication factor, in both reference and voided conditions. The computational effort reduction obtained by using the condensed library rather than the fine one is assessed and is much higher than the time required for the ES search.

• Earthquakes and Structures
• /
• v.13 no.4
• /
• pp.397-407
• /
• 2017

With the growing demand for metallic dampers in engineering practice, it is urgent to establish a reasonable approach to evaluating the mechanical performance of metallic dampers under seismic excitations. This paper introduces an effective method for parameter identification of the modified Bouc-Wen model and its application to evaluating the fatigue performance of metallic dampers (MDs). The modified Bouc-Wen model which eliminates the redundant parameter is used to describe the hysteresis behavior of MDs. Relations between the parameters of the modified Bouc-Wen model and the mechanical performance parameters of MDs are studied first. A modified Genetic Algorithm using real-integer hybrid coding with relative fitness as well as adaptive crossover and mutation rates (called RFAGA) is then proposed to identify the parameters of the modified Bouc-Wen model. A reliable approach to evaluating the fatigue performance of the MDs with respect to the Chinese Code for Seismic Design of Buildings (GB 50011-2010) is finally proposed based on the research results. Experimental data are employed to demonstrate the process and verify the effectiveness of the proposed approach. It is shown that the RFAGA is able to converge quickly in the identification process, and the simulation curves based on the identification results fit well with the experimental hysteresis curves. Furthermore, the proposed approach is shown to be a useful tool for evaluating the fatigue performance of MDs with respect to the Chinese Code for Seismic Design of Buildings (GB 50011-2010).

• Steel and Composite Structures
• /
• v.30 no.3
• /
• pp.293-304
• /
• 2019

The optimum cost of a reinforced concrete plane and space frames have been found by using the Genetic Algorithm (GA) method. The design procedure is subjected to many constraints controlling the designed sections (beams and columns) based on the standard specifications of the American Concrete Institute ACI Code 2011. The design variables have contained the dimensions of designed sections, reinforced steel and topology through the section. It is obtained from a predetermined database containing all the single reinforced design sections for beam and columns subjected to axial load, uniaxial or biaxial moments. The designed optimum beam sections by using GAs have been unified through MATLAB to satisfy axial, flexural, shear and torsion requirements based on the designed code. The frames' functional cost has contained the cost of concrete and reinforcement of steel in addition to the cost of the frames' formwork. The results have found that limiting the dimensions of the frame's beams with the frame's columns have increased the optimum cost of the structure by 2%, declining the re-analysis of the optimum designed structures through GA.

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.834-841
• /
• 2022

System thermal-hydraulic (STH) code is adopted for nuclear safety analysis. The critical flow model (CFM) is significant for the accuracy of STH simulation. To overcome the defects of current CFMs (low precision or long calculation time), a CFM based on a genetic neural network (GNN) has been developed in this work. To build a powerful model, besides the critical mass flux, the critical pressure and critical quality were also considered in this model, which was seldom considered before. Comparing with the traditional homogeneous equilibrium model (HEM) and the Moody model, the GNN model can predict the critical mass flux with a higher accuracy (approximately 80% of results are within the ±20% error limit); comparing with the Leung model and the Shannak model for critical pressure prediction, the GNN model achieved the best results (more than 80% prediction results within the ±20% error limit). For the critical quality, similar precision is achieved. The GNN-based CFM in this work is meaningful for the STH code CFM development.