• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2012.11a
• /
• pp.153-154
• /
• 2012

The accuracy of cost estimation at an early stage in school building project is one of the critical factors for successful completion. So many method and techniques have developed that can estimate construction cost using limited information available in the early stage. Among the techniques, Support Vector Machine(SVM) has received attention in various field due to its excellent capacity for self-learning and generalization performance. Therefore, the purpose of this study is to verify the applicability of cost prediction model based on SVM in school building project at the early stage. Data used in this study are 139 school building cost constructed from 2004 to 2007 in Gyeonggi-Do. And prediction error rate of 7.48% in support vector machine is obtained. So the results showed applicability of using SVM model for predicting construction cost of school building projects.

• Journal of the Korea Safety Management & Science
• /
• v.8 no.5
• /
• pp.17-25
• /
• 2006

Nowadays most colleges are confronting with a serious problem because many students have left their majors at the colleges. In order to make a countermeasure for reducing major separation rate, many universities are trying to find a proper solution. As a similar endeavor, the objective of this paper Is to find a predicting model of students leaving their majors. The sample for this study was chosen from a university in Kangwon-Do during seven years(2000.3.1 $\sim$ 2006. 6.30). In this study, the ratio of training sample versus testing sample among partition data was controlled as 50% : 50% for a validation test of data division. Also, this study provides values about accuracy, sensitivity, specificity about three kinds of algorithms including CHAID, CART and C4.5. In addition, ROC chart and gains chart were used for classification of students leaving their majors. The analysis results were very informative since those enable us to know the most important factors such as semester taking a course, grade on cultural subjects, scholarship, grade on majors, and total completion of courses which can affect students leaving their majors.

• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.281-291
• /
• 2022

Surmounting complexities in analyzing the mechanical parameters of concrete entails selecting an appropriate methodology. This study integrates a novel metaheuristic technique, namely satin bowerbird optimizer (SBO) with artificial neural network (ANN) for predicting uniaxial compressive strength (UCS) of concrete. For this purpose, the created hybrid is trained and tested using a relatively large dataset collected from the published literature. Three other new algorithms, namely Henry gas solubility optimization (HGSO), sunflower optimization (SFO), and vortex search algorithm (VSA) are also used as benchmarks. After attaining a proper population size for all algorithms, the Utilizing various accuracy indicators, it was shown that the proposed ANN-SBO not only can excellently analyze the UCS behavior, but also outperforms all three benchmark hybrids (i.e., ANN-HGSO, ANN-SFO, and ANN-VSA). In the prediction phase, the correlation indices of 0.87394, 0.87936, 0.95329, and 0.95663, as well as mean absolute percentage errors of 15.9719, 15.3845, 9.4970, and 8.0629%, calculated for the ANN-HGSO, ANN-SFO, ANN-VSA, and ANN-SBO, respectively, manifested the best prediction performance for the proposed model. Also, the ANN-VSA achieved reliable results as well. In short, the ANN-SBO can be used by engineers as an efficient non-destructive method for predicting the UCS of concrete.

• Wind and Structures
• /
• v.18 no.3
• /
• pp.235-252
• /
• 2014

An effective numerical technique to calculate the reactions of a multi-spanned transmission line conductor system, under arbitrary loads varying along the spans, is developed. Such variable loads are generated by High Intensity Wind (HIW) events in the form of tornadoes and downburst. First, a semi-closed form solution is derived to obtain the displacements and the reactions at the ends of each conductor span. The solution accounts for the nonlinearity of the system and the flexibility of the insulators. Second, a numerical scheme to solve the derived closed-form solution is proposed. Two conductor systems are analyzed under loads resulting from HIW events for validation of the proposed technique. Non-linear Finite Element Analyses (FEA) are also conducted for the same two systems. The responses resulting from the technique are shown to be in a very good agreement with those resulting from the FEA, which confirms the technique accuracy. Meanwhile, the semi-closed form technique shows superior efficiency in terms of the required computational time. The saving in computational time has a great advantage in predicting the response of the conductors under HIW events, since this requires a large number of analyses to cover different potential locations and sizes of those localized events.

• 한국전산유체공학회:학술대회논문집
• /
• 2000.05a
• /
• pp.33-38
• /
• 2000

A Numerical study of laminar vortex-shedding past a circular cylinder has been performed widely by many researchers. Many factors, such as numerical technique and domain size, number and shape of grid, affected predicting vortex shedding and Strouhal number. In the present study, the effect of convection scheme, time discretization methods and grid dependence were investigated. The present paper presents the finite volume solution of unsteady flow past circular cylinder at Re=200, 400. The Strouhal number was predicted using UDS, CDS, Hybrid, Power-law, LUDS, QUICK scheme for convection term, implicit and crank-nicolson methods for time discretization. The grid dependence was investigated using H-type mesh and O-type mesh. It also studied that the effect of mesh size of the nearest adjacent grid of circular cylinder. The effect of convection scheme is greater than the effect of time discretization on predicting Strouhal. It has been found that the predicted Strouhal number changed with mesh size and shape.

• Ocean and Polar Research
• /
• v.35 no.1
• /
• pp.63-68
• /
• 2013

The European Common Barnacle Balanus perforatus Brugiere (Crustacea, Cirripedia) has been introduced into the east coast of Korea, presumably via the ballast water of ships. The species has since been spreading along both the northern and southern coast to the east, most likely due to alongshore currents. We predicted the potential range expansion of Balanus perforatus in Korean waters using Genetic Algorithm for Rule-set Prediction (GARP), an environmental niche modeling technique. The results show that much of the southern coastal waters of Korea could be colonized by the spread of the nonindigenous species, but that the west coast is unlikely to be invaded. More sampling on the west coast would enhance the predictability of the model. To our knowledge, this is the first report of its kind for predicting marine nonindigenous species in Korean waters using GARP modeling.

• Journal of the korean Society of Automotive Engineers
• /
• v.8 no.1
• /
• pp.52-61
• /
• 1986

An iterative viscous-potential flow procedure has been developed and used to predict aerodynamic characteristics of automobiles in ground proximity. The method is capable of predicting the effects of separated flows. The viscous-potential flow iteration procedure provides the connection between potential flow, boundary layer and wake modules. The separated wake is modeled in the potential flow analysis by thin sheets across which exists a jump in velocity potential. The ground effect is properly accounted for by placing a body image in the potential flow calculation. The agreement between theory and experiment is good and, thus, demonstrates that the method can be used in the preliminary design stage.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2003.09a
• /
• pp.311-316
• /
• 2003

The compressive strength of concrete is a criterion to produce concrete. However, the tests on the compressive strength are complicated and time-consuming. More importantly, it is too late to make improvement even if the test result does not satisfy the required strength, since the test is usually performed at the 28th day after the placement of Concrete at the Construction site. Therefore, strength prediction before the placement of concrete is highly desirable. This study presents the probabilistic technique for predicting the compressive strength of concrete on the basis of concrete mix proportions. The estimation of the strength is based on the probabilistic neural network, and show that the present methods are very efficient and reasonable in predicting the compressive strength of concrete probabilistically.

• Journal of Aerospace System Engineering
• /
• v.15 no.6
• /
• pp.10-18
• /
• 2021

A flame deflector prevents a launch system from thermal damage by deflecting the exhaust flame of the launch vehicle. During the deflection of the flame, the flame deflector is subjected to a high-temperature and high-pressure flow, which results in thermal ablation damage at the surface. Predicting this ablation damage is an essential requirement to ensure a reliable design. This paper introduces a numerical method for predicting the ablation damage phenomena based on a one-way fluid-structure interaction (FSI) analysis. In the proposed procedure, the temperature and convective heat transfer coefficient of the exhaust flame are calculated using a fluid dynamics analysis, and then the ablation is calculated using a finite element analysis (FEA) based on the user-subroutine UMESHMOTION and Arbitrary Lagrangian-Eulerian (ALE) adaptive mesh technique in ABAQUS. The result of such an analysis was verified by comparison to the ablation test result for a flame deflector.

• Computers and Concrete
• /
• v.33 no.3
• /
• pp.325-340
• /
• 2024

The growing demands for sustainable and high-performance construction materials necessitate a deep understanding of their physicochemical properties by that of these heterogeneities. This paper presents a comprehensive review of the state-of-the-art hierarchical multiscale modeling approach aimed at predicting the intricate physicochemical characteristics of construction materials. Emphasizing the heterogeneity inherent in these materials, the review briefly introduces single-scale analyses, including the ab initio method, molecular dynamics, and micromechanics, through a scale-bridging technique. Herein, the limitations of these models are also overviewed by that of effectively scale-bridging methods of length or time scales. The hierarchical multiscale model demonstrates these physicochemical properties considering chemical reactions, material defects from nano to macro scale, microscopic properties, and their influence on macroscopic events. Thereby, hierarchical multiscale modeling can facilitate the efficient design and development of next-generation construction.