• Proceedings of the KOR-KST Conference
• /
• 2003.02a
• /
• pp.21-71
• /
• 2003

Previous alignment optimization models have not adequately considered intersections and other structures such as bridges, tunnels, grade separations and interchanges which can very strongly affect alignment decisions. This paper develops comprehensive cost functions for intersections and other structures and incorporates them in recently developed highway alignment optimization models connected with genetic algorithms and geographical information systems. The result is a fast and computerized process for extracting, analyzing spatial data, evaluating candidate alignments and optimizing them. A method for locally optimizing intersections is also developed. It improves search flexibility by saving good alignments whose unacceptable crossing angles with existing roads can be fixed, Through case studies, the developed model is found to produce feasible and efficient solutions.

• Journal of Information Processing Systems
• /
• v.18 no.2
• /
• pp.235-244
• /
• 2022

Many new techniques have been adopted in HEVC (High efficiency video coding) standard, such as quadtree-structured coding unit (CU), prediction unit (PU) partition, 35 intra-mode, and so on. To reduce computational complexity, the paper proposes two optimization algorithms which include fast CU depth range decision and fast PU partition mode decision. Firstly, depth range of CU is predicted according to spatial-temporal correlation. Secondly, we utilize the depth difference between the current CU and CU corresponding to the same position of adjacent frame for PU mode range selection. The number of traversal candidate modes is reduced. The experiment result shows the proposed algorithm obtains a lot of time reducing, and the loss of coding efficiency is inappreciable.

• Journal of Korean Society of Steel Construction
• /
• v.17 no.4 s.77
• /
• pp.385-394
• /
• 2005

In this paper, a discrete optimum design program was developed using the refined fuzzy-genetic algorithms based on the genetic algorithms and the fuzzy theory. The optimum design in this study can perform section and shape optimization simultaneously for planar and spatial steel structures. In this paper, the objective function is the weight of steel structures and the constraints are the design limits defined by the design and buckling strengths, displacements, and thicknesses of the member sections. The design variables are the dimensions and coordinates of the steel sections. Design examples are given to show the applicability of the discrete optimum design using the improved fuzzy-genetic algorithms in this study.

• Journal of Korean Association for Spatial Structures
• /
• v.1 no.1 s.1
• /
• pp.125-134
• /
• 2001

The objective of this study is the development of size discrete optimum design algorithm which is based on the GAs(genetic algorithms). The algorithm can perform size discrete optimum designs of space trusses. The developed algorithm was implemented in a computer program. For the optimum design, the objective function is the weight of space trusses and the constraints are limite state design codes(1998) and displacements. The basic search method for the optimum design is the GAs. The algorithm is known to be very efficient for the discrete optimization. This study solves the problem by introducing the GAs. The GAs consists of genetic process and evolutionary process. The genetic process selects the next design points based on the survivability of the current design points. The evolutionary process evaluates the survivability of the design points selected from the genetic process. In the genetic process of the simple GAs, there are three basic operators: reproduction, cross-over, and mutation operators. The efficiency and validity of the developed discrete optimum design algorithm was verified by applying GAs to optimum design examples.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.2
• /
• pp.83-90
• /
• 2024

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks and extreme gradient boosting algorithms present good prediction performance.

• Journal of Korean Association for Spatial Structures
• /
• v.5 no.4 s.18
• /
• pp.53-59
• /
• 2005

This paper provides the results of the investigation on the optimum thickness distribution of plate structures with different essential boundary conditions. In this study, the strain energy to be minimized is considered as the objective function and the initial volume of structures is used as the constraint function. The computer-aided geometric design (CAGD) such as Coon's patch representation is used to represent the thickness distribution of plates. A reliable degenerated shell finite element is adopted to calculate the accurate strain energy level of the plates. Robust optimization algorithms provided in the optimizer DOT are adopted to search the optimum thickness values during the optimization iteration. Finally, the square plate is used to find out the optimum thickness distribution of plates according to different essential boundary condition.

• Journal of Korean Association for Spatial Structures
• /
• v.12 no.4
• /
• pp.47-56
• /
• 2012

This paper describes the structural design and optimization of sinusoidally corrugated web girder by using EUROCODE (EN 1993-1-5). The optimum design methodology and characteristics of the optimal cross-section are discussed. We investigate a shear buckling and the concerned standards for corrugated web and explain the equations to obtain a critical stress according to buckling type. In order to perform optimization, we consider an objective function as minimum weight of the girder and use the constraint functions as slenderness ratio and stresses of flanges as well as corrugated web and deflection. Genetic Algorithm is adopted to search a global optimum solution for this mathematical model. For numerical example, the clamped girder under the concentrated load is considered, while the optimum cross-sectional area and design variables are analyzed. From the results of the adopted example, the optimum design program of the sinusoidally corrugated web girder is able to find the suitable solution which satisfied a condition subject to constraint functions. The optimum design shows the tendency to decrease the cross-sectional area with the yielding strength increase and increase the areas with load increase. Moreover, the corrugated web thickness shows a stable increase concerning the load.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.

• Journal of Mechanical Science and Technology
• /
• v.16 no.5
• /
• pp.619-632
• /
• 2002

In recent study on design of experiments, the complicate metamodeling has been studied because defining exact model using computer simulation is expensive and time consuming. Thus, some designers often use approximate models, which express the relation between some inputs and outputs. In this paper, we review and compare the complicate metamodels, which are expressed by the interaction of various data through trying many physical experiments and running a computer simulation. The prediction model in this paper employs interpolation schemes known as ordinary kriging developed in the fields of spatial statistics and kriging in Design and Analysis of Computer Experiments (DACE) model. We will focus on describing the definitions, the prediction functions and the algorithms of two kriging methods, and assess the error measures of those by using some validation methods.

• Proceeding of KASS Symposium
• /
• 2006.05a
• /
• pp.191-204
• /
• 2006

This paper investigate the optimum thickness distribution of plate structure with different essential boundary conditions in the fundamental natural frequency maximization problem. In this study, the fundamental natural frequency is considered as the objective function to be maximized and the initial volume of structures is used as the constraint function. The computer-aided geometric design (CAGD) such as Coon's patch representation is used to represent the thickness distribution of plates. A reliable degenerated shell finite element is adopted calculate the accurate fundamental natural frequency of the plates. Robust optimization algorithms implemented in the optimizer DoT are adopted to search optimum thickness values during the optimization iteration. Finally, the optimum thickness distribution with respect to different boundary condition