• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.46-51
• /
• 2014

The most important process of engineering system optimal design is to identify the relationship between the design variables and system response. In case of the system optimization, Response Surface Method (RSM) is widely used. The optimization process of RSM generates the design space using the typical alternative candidates and finds the optimal design point in the generated design space. By changing the optimal point depending on the configuration of the design space, it is important to generate the design space. Therefor in this study, the design space is generated by using the relationship between design variables and system response based on Neuro-Response Surface Method (NRSM). And I try to construct the framework for optimal shape design based on NRSM that the optimum shape can be predicted using the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) within the generated design space. In order to verify the usefulness of the constructed framework, we applied the nonlinear mathematical function problem. In this study, we can solve the constraints of time in the optimization process for the engineering problem and effective to determine the optimal design was possible. by using the generated framework for optimal shape design based on NRSM. In the future research, we try to apply the optimization problem for Naval Architectural & Ocean Engineering based on the results of this study.

• Journal of the Korean Magnetics Society
• /
• v.17 no.4
• /
• pp.147-151
• /
• 2007

We have investigated the half-metallicity and magnetism for the Heusler ferromagnet $Co_2$ZrSi interfaced with semiconductor ZnTe along the (001) plane by using the full-potential linearized augmented plane wave (FLAPW) method. We considered low types of possible interfaces: ZrSi/Zn, ZrSi/Te, Co/Zn, and Co/Te, respectively. From the calculated density of states, it was found that the half-metallicity was lost at all the interfaces, however for the Co/Te system the value of minority spin density of states was close to zero at the Fermi level. These facts are due to the interface states, appeared in the minority spin gap in bulk $Co_2$ZrSi, caused by the changes of the coordination and symmetry and the hybridizations between the interface atoms. At the Co/Te interface, the magnetic moments of Co atoms are 0.68 and $0.78{\mu}_B$ for the "bridge" and "antibridge" sites, respectively, which are much reduced with respect to that ($1.15{\mu}_B$) of the bulk $Co_2$ZrSi. In the case of Co/Zn, Co atoms at the "bridge" and "antibridge" sites have magnetic moments of 1.16 and $0.93{\mu}_B$, respectively, which are almost same or slightly decreased compared to that of the bulk $Co_2$ZrSi. On the other hand, for the ZrSi/Zn and ZrSi/Te systems, the magnetic moments of Co atoms at the sub-interface layers are in the range of $1.13{\sim}1.30\;{\mu}_B$, which are almost same or slightly increased than that of the bulk $Co_2$ZrSi.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.9-18
• /
• 2023

Predicting the compressive strength of high-performance concrete (HPC) is challenging because of the use of additional cementitious materials; thus, the development of improved predictive models is essential. The purpose of this study was to develop an HPC compressive-strength prediction model using an ensemble machine-learning method of combined bagging and stacking techniques. The result is a new ensemble technique that integrates the existing ensemble methods of bagging and stacking to solve the problems of a single machine-learning model and improve the prediction performance of the model. The nonlinear regression, support vector machine, artificial neural network, and Gaussian process regression approaches were used as single machine-learning methods and bagging and stacking techniques as ensemble machine-learning methods. As a result, the model of the proposed method showed improved accuracy results compared with single machine-learning models, an individual bagging technique model, and a stacking technique model. This was confirmed through a comparison of four representative performance indicators, verifying the effectiveness of the method.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.6
• /
• pp.17-29
• /
• 2009

There has been an increase in the investigation of deep sea sediments with a consequent increase in the amount of energy required to undertake these investigations. The geotechnical characteristics of Ulleung Basin sediment are explored by using depressurized specimens following methane production tests carried out on pressured core samples obtained at 2,100 m water depth and 110 m below sea floor. Geotechnical index tests, X-ray diffraction, and scanning electron microscope are conducted to identify the geotechnical index parameters, clay mineralogy, chemical composition, and microstructure of the sediments. Compressibility, and elastic and electromagnetic wave parameters are investigated for two samples by using a multi sensing instrumented oedometer cell. The strength chatracteristics are obtained by the direct shear tests. The dominant clay minerals are mostly kaolinite, illite, chlorite, and calcite. The SEM shows a well-developed flocculated structure of the microfossil. Void ratio, electrical resistivity, real permittivity, conductivity, and shear wave velocity show bi-linear behavior with the effective vertical stress: as the vertical effective stress increases. The friction angle obtained by the direct shear test is about $21^{\circ}$, which is similar to the value observed in the Ulleung Basin sediments. This study shows that the understanding of the behavior acting on the diatomaceous marine sediment is important because it often maintains the useful energy resources such as gas hydrate and so will be the new engineering field in the next generation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.12 no.3
• /
• pp.65-79
• /
• 1992

This study is concerned with the optimal design of two hinged steel arches with I cross sectional type and aimed at the exact analysis of the arches and the safe and economic design of structure. The analyzing method of arches which introduces the finite difference method considering the displacements of structure in analyzing process is used to eliminate the error of analysis and to determine the sectional force of structure. The optimizing problems of arches formulate with the objective functions and the constraints which take the sectional dimensions(B, D, $t_f$, $t_w$) as the design variables. The object functions are formulated as the total weight of arch and the constraints are derived by using the criteria with respect to the working stress, the minimum dimension of flange and web based on the part of steel bridge in the Korea standard code of road bridge and including the economic depth constraint of the I sectional type, the upper limit dimension of the depth of web and the lower limit dimension of the breadth of flange. The SUMT method using the modified Newton Raphson direction method is introduced to solve the formulated nonlinear programming problems which developed in this study and tested out throught the numerical examples. The developed optimal design programming of arch is tested out and examined throught the numerical examples for the various arches. And their results are compared and analyzed to examine the possibility of optimization, the applicablity, the convergency of this algorithm and with the results of numerical examples using the reference(30). The correlative equations between the optimal sectional areas and inertia moments are introduced from the various numerical optimal design results in this study.

• Journal of Soil and Groundwater Environment
• /
• v.13 no.1
• /
• pp.13-23
• /
• 2008

The triaxial compression tests and consolidation tests using NaCl solution and leachates as substitute pore (or saturated) water in samples were carried out to find out the behavior characteristics of strength, deformation and permeability coefficient of contaminated clay. Also, the chemical property analysis on the clay samples using scanning electron microscope and energy dispersive x-ray spectrometer were involved. The magnitudes of composition ratio were shown in the order of O, C, Si, Al, and Fe as a result of chemical composition analysis for clay samples. Besides, as the results of triaxial compression tests and consolidation tests, the shear strength, compression and permeability properties were increased with increasing in the concentration of contaminant (NaCl). It may be considered that these circumstances be caused by the changes of soil structure to flocculent structure due to the decrease in the thickness of diffuse double layer with increasing in the concentration of electrolyte. MT3D model was also using to grasp the procedures that the groundwater may be contaminated by the leachates permeated through the clay liner. The results of contaminant transport analysis showed a tendency that the predicted concentration of groundwater was higher with increasing in the initial concentration of $Cl^-$ ion and increased as a nonlinear curves with time. The transportation distance calculated by the use of regression equation between the distance from contaminant source and the concentration of $Cl^-$ ion was increased with increasing the initial concentration.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.4
• /
• pp.34-44
• /
• 2006

Simulation models allow researchers to model large hydrological catchment for comprehensive management of the water resources and explication of the diffuse pollution processes, such as land-use changes by development plan of the region. Recently, there have been reported many researches that examine water body quality using Geographic Information System (GIS) and dynamic watershed models such as AGNPS, HSPF, SWAT that necessitate handling large amounts of data. The aim of this study is to develop a watershed based water quality estimation system for the impact assessment on stream water quality. KBASIN-HSPF, proposed in this study, provides easy data compiling for HSPF by facilitating the setup and simulation process. It also assists the spatial interpretation of point and non-point pollutant information and thiessen rainfall creation and pre and post processing for large environmental data An integration methodology of GIS and water quality model for the preprocessing geo-morphologic data was designed by coupling the data model KBASIN-HSPF interface comprises four modules: registration and modification of basic environmental information, watershed delineation generator, watershed geo-morphologic index calculator and model input file processor. KBASIN-HSPF was applied to simulate the water quality impact by variation of subbasin pollution discharge structure.

• Journal of the Society of Naval Architects of Korea
• /
• v.32 no.1
• /
• pp.42-57
• /
• 1995

An efficient and accurate scheme has been constructed by taking advantages of the hi-quadratic spline scheme and the higher-order boundary element method selectively depending on computation domains. Boundary surfaces are represented by 8-node boundary elements to describe curved surfaces of a ship and its neighboring free surface more accurately. The variation of the velocity potential complies with the characteristics of the 8-node element on the body surface. But on the free surface, it is assumed to follow that of the hi-quadratic spline scheme. By which, the free surface solution is free from numerical damping and has better numerical dispersion property. As numerical examples, steady and unsteady Neumann-Kelvin problems are considered. Numerical results for a submerged spheroid, Series 60($C_B=0.6$) and a modified support the proposed method. Finally, a new upstream radiation condition is derived using a wave equation operator in order to deal with problems for subcritical reduced frequency. The relevance of this operator has been confirmed in the case of unsteady Kelvin source potential.

• Journal of the Korea Concrete Institute
• /
• v.21 no.6
• /
• pp.797-804
• /
• 2009

The structural designs of RC flat plates that have insufficient flexural stiffness due to lack of support from boundary beams may be governed by serviceability as well as a strength criteira. Specially, since over-loading and tensile cracking in early-aged slabs significantly increase the deflection of a flat plate system under construction, a construction sequence and its impact on the slab deflections may be decisive factors in designs of flat plate systems. In this study, the procedure of calculating slab deflections considering construction sequences and concrete cracking effects is proposed. The construction steps and the construction loads are defined by the simplified method, and then the slab moments, elastic deflections, and the effective moment of inertia are calculated in each construction step. The elastic deflections in column and middle strips are magnified to inelastic deflections by the effective moment of inertia, and the center deflection of slab are calculated by the crossing beam method. The proposed method is verified by comparisons with the existing test result and the nonlinear analysis result. Also, by applications of the proposed method, the effects of the slab construction cycle and the number of shored floors on the deflections of flat plates under construction are analyzed.