• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.17-24
• /
• 2023

Based on the problem of 'Tatanic - Machine Learning from Disaster', a representative competition of Kaggle that presents challenges related to data science and solves them, we want to see how data preprocessing and model construction affect prediction accuracy and score. We compare and analyze the features by selecting seven top-ranked solutions with high scores, except when using redundant models or ensemble techniques. It was confirmed that most of the pretreatment has unique and differentiated characteristics, and although the pretreatment process was almost the same, there were differences in scores depending on the type of model. The comparative analysis study in this paper is expected to help participants in the kaggle competition and data science beginners by understanding the characteristics and analysis flow of the preprocessing methods of the top score participants.

• Korean Journal of Construction Engineering and Management
• /
• v.19 no.6
• /
• pp.46-54
• /
• 2018

In the 21st century, the Earth has continued its efforts to reduce carbon emissions to overcome the crisis caused by climate change. The construction industry, which is a representative industry that produces large amounts of the environmental load during construction, should actively reduce the amount of the environmental load. From the planning stage of the construction facility, it is necessary to consider the environmental load such as route selection and structure type selection to reduce the environmental load. However, the environmental load can be estimated based on the input resource amount. However, in the planning stage, it is difficult to accurately calculate the environmental load due to lack of information on the construction amount. The purpose of this study is to select the environmental load factors for IPC girder bridges to be used in the environmental load estimation model in the planning stage. Specific information related to the environmental load was selected from a list of information available in the planning stage, reflecting the Life Cycle Assessment(LCA), correlation, principal components analysis and expert opinion. The list of selected planning stage information is 10 such as span length and bridge extension, and it is expected to be used as a basic data for the future development of environmental load estimation model.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.2
• /
• pp.183-194
• /
• 2005

In this study, we introduce an advanced architecture of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) and develop a comprehensive design methodology supporting their construction. A series of numeric experiments is included to illustrate the performance of the networks. The construction of gHFNN exploits fundamental technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms (GAs). The architecture of the gHFNNs results from a synergistic usage of the genetic optimization-driven hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). In this tandem, a FNN supports the formation of the premise part of the rule-based structure of the gHFNN. The consequence part of the gHFNN is designed using PNNs. We distinguish between two types of the linear fuzzy inference rule-based FNN structures showing how this taxonomy depends upon the type of a fuzzy partition of input variables. As to the consequence part of the gHFNN, the development of the PNN dwells on two general optimization mechanisms: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gHFNN, the models are experimented with a representative numerical example. A comparative analysis demonstrates that the proposed gHFNN come with higher accuracy as well as superb predictive capabilities when comparing with other neurofuzzy models.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2008.11a
• /
• pp.245-249
• /
• 2008

The purpose of this study is to test performances of 14 types of root barrier materials by applying testing plants and soils suitable for weather and natural features of Korea. For testing plants, Plioblastus pygmaed Mitford A. and Pyracantha angustifolia have been selected. For testing soil, mixture of pearlite and peat moss in 3:1 ratio(volume). Testing container has been fabricated with duplicated structure having inner and outer containers. And the outer container has 2 hinges on its side wall to allow opening and closing. Wet rock wool with 50mm in thickness has been inserted between inner and outer containers to allow root to penetrate through root barrier material and continue to grow. We planted 12 Plioblastus pygmaed Mitford A. and 4 Pyracantha angustifolia per one testing container. Three testing samples have been made for 1 type of root barrier material, which become a total 42 specimens. Planted testing samples have been installed within the greenhouse, which will be observed regularly for 2 years from now on. We started test from July 11, 2008 and had performed intermediate observations every month for initial 3 months. From the 3rd intermediate observation on Sept. 18, we confirmed that 6 types of root barrier materials have penetrated roots. Even though two types of them(EDPM Sheet, Polyethylene Sheet) have been generally used as root barrier materials for roof planting system, all of three testing samples have a lot of penetrated roots. This result proves that it is not reasonable to introduce testing methods of root barrier from Europe or Japan.

• Journal of Korean Society of Steel Construction
• /
• v.22 no.4
• /
• pp.377-388
• /
• 2010

The flexural behavior of composite HSB600 and HSB800 I-girders under a positive moment was investigated using the material non-linear moment-curvature analysis method. Three representative composite sections with different ductility properties were selected as the baseline sections in this study. Using these baseline sections, the moment-curvature program was verified by comparing the flexural strength and the moment-curvature curve obtained from the program with those obtained using the non-linear FE analysis of ABAQUS. In the FE analysis, the composite girders were modeled three-dimensionally with flanges, the web, and the concrete slab as thin shell elements, and initial imperfections and residual stresses were imposed on the FE model. In the moment-curvature and FE analyses, the 28-day compressive strength of the concrete slab was assumed to be 30-50 MPa, and the HSB600 and HSB800 steels were modeled as elasto-plastic strain-hardening materials, with the concrete as the CEB-FIP model. The effects of the ductility ratio of the composite girder, the type of steel, the compressive strength of the concrete deck, and the location of the plastic neutral axis on the flexural characteristics were analyzed.

• Korean Journal of Construction Engineering and Management
• /
• v.19 no.5
• /
• pp.53-60
• /
• 2018

In particular, the investigation of tendons in PSC Box Girder Bridge should be done in a systematic way. It is important to identify preventative maintenance activities that should be carried out in order to analyze the risk factors by type of representative tensions and to reduce risks in the long term. However, in the current maintenance system, various methodologies for investigating and repairing tensions have been studied, but it is difficult to investigate precisely tensions. Therefore, to apply the risk assessment for screening of tensions to the domestic PSC Box Bridge, we presented a risk matrix evaluation index that is consistent with the state assessment and maintenance system.

• Journal of the Korean GEO-environmental Society
• /
• v.20 no.1
• /
• pp.19-25
• /
• 2019

In this present study, to evaluate the applicability of the monitoring system of the entire reservoir dam facility using the wireless sensor network system and a section representative of the domestic reservoir dam was selected as the test bed site and to operated a system that can evaluate the condition of the facility at the real time with monitoring. In order to set up a wireless sensor network system, the system assessment of present state was carried out for confirmation the risk factors and the limit values of the risk factors in limit state were calculated. The type and position of the sensor to be measured in the field were determined by setting the measurement items suitable for the hazardous area and the risk factor. In this paper, we evaluated the feasibility of the system by monitoring and constructing a wireless sensor network system in a field for a fill dam that can represent a domestic reservoir dam. Applicability evaluation was verified by comparing directly with the measurement of partial concentration method which is the measurement management technology of the dam.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.1183-1188
• /
• 2009

Estimating project costs during the early stage of conceptual planning is very important when deciding whether to approve the project and allocate an appropriate budget. However, due to greater uncertainties involved in a project, it is challenging to estimate costs during this initial stage within a reasonable tolerance. This paper attempts to develop a cost-estimate model for public road projects under these circumstances and limitations. In the conceptual planning stage of a road project, there is only limited information for cost estimation, for example, such input data as total length of the route, origin and destination, number of lanes, general geographic characteristics of the route, and other basic attributes. This implies that the model should individuate suitable but restricted information without considering detailed features such as quantity of earthwork and a detailed route of a given condition. With these limited facts, this paper applies a case-based reasoning (CBR) method to solve a new problem by deriving similar past problems, which in turn is used to estimate the cost of a given project based on best-fitted previous cases. To develop a CBR cost-estimate model, the authors classified 8 representative variables, including project type, the number of lanes, total length, road design grades, etc. Then, we developed the CBR model, primarily by using 180 actual cases of public road projects, procured over the last decade. With the CBR model, it was found that the degree of error in estimation can be reasonably reduced, to below approximately 30% compared to the final costs estimated upon the completion of detailed design.

• Korean Journal of Construction Engineering and Management
• /
• v.13 no.4
• /
• pp.132-140
• /
• 2012

Along with the increasing interest in environmental problems such as global warming, the South Korean government has established policies and regulations to reduce the amount of greenhouse gases, targeting a 30% reduction of $CO_2$ compared to business-as-usual levels by 2020. Thus, there have been many studies in construction field to control and reduce the amount of $CO_2$ emitted from buildings. $CO_2$ emission from the building construction could be obtained by using the life cycle assessment(LCA) methodology. In LCA, it is essential to have life cycle inventory(LCI) data of construction materials consisting of $CO_2$ emission data that have been defined and examined in a detailed way in order to obtain more accurate and detailed $CO_2$ emission of buildings. To date, however, the LCI data have been acquired only for the representative materials. Accordingly this study aimed to propose detailed $CO_2$ emission data for steel rebar and H-beam, which are the essential structural steel materials, by strength and type. To accomplish the objective, this study used Input-Output LCA methodology which is based on the Input-Output table. It is believed that the $CO_2$ emission data of steel materials acquired from this study would allow a more accurate assessment of $CO_2$ emission for diverse structural design alternatives.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.507-512
• /
• 2022

The subjects of the study are the sedimentary rock slope of the Mesozoic Gyeongsang Supergroup, which has a high risk of failure. The rocks of the slope shall be sandstone, siltstone and dacite, and discontinuities shall develop beddings, shear joints, extension joints, and dacite dyke boundary planes. The type and scale of failure varies depending on the type of rock and the strike/dip of the discontinuities, but the planar failure prevails. Based on the face-mapping data, SMR, physical and mechanical testing of rocks, the critical equilibrium analysis, all representative sections required a countermeasure method because the acceptable safety factor during dry and rainy seasons were far below Fs=1.5 and Fs=1.2. After applying the countermeasure method, both the dry and wet conditions of the slope exceeded the allowable safety factor. In particular, the face-mapping data of the slope-face, the geological cross-sections of several representative sections perpendicular to the slope-face, and the critical equilibrium analysis and the presentation of countermeasure methods that have been reviewed based on them are expected to be reasonable tools for the slope stability.