Yoonseok Shin

Application of AdaBoost to the Retaining Wall Method Selection in Construction

The appropriate selection of construction methods is a critical factor in the successful completion of any construction project. Artificial intelligence techniques are widely used to assist in the selection of a construction method. This paper proposes the use of the adaptive boosting (AdaBoost) model to select an appropriate retaining wall method suitable for particular construction site conditions, in order to examine the applicability of AdaBoost in construction method selection. To verify its applicability, the proposed model was compared with a support vector machine (SVM) model, which have been attracting attention for their high performance in various classification problems. The AdaBoost model showed a slightly more accurate result than the SVM model in the selection of retaining wall methods, demonstrating that AdaBoost has advantages (e.g., robustness against defective data with missing values) in application to decision support systems. Moreover, the AdaBoost model can be used in future projects to assist engineers in determining the appropriate construction method, such as a retaining wall method, at an early stage of the project.

Application of boosting regression trees to preliminary cost estimation in building construction projects

Among the recent data mining techniques available, the boosting approach has attracted a great deal of attention because of its effective learning algorithm and strong boundaries in terms of its generalization performance. However, the boosting approach has yet to be used in regression problems within the construction domain, including cost estimations, but has been actively utilized in other domains. Therefore, a boosting regression tree (BRT) is applied to cost estimations at the early stage of a construction project to examine the applicability of the boosting approach to a regression problem within the construction domain. To evaluate the performance of the BRT model, its performance was compared with that of a neural network (NN) model, which has been proven to have a high performance in cost estimation domains. The BRT model has shown results similar to those of NN model using 234 actual cost datasets of a building construction project. In addition, the BRT model can provide additional information such as the importance plot and structure model, which can support estimators in comprehending the decision making process. Consequently, the boosting approach has potential applicability in preliminary cost estimations in a building construction project.

Life Comparative Analysis of Energy Consumption and CO2 Emissions of Different Building Structural Frame Types

The objective of this research is to quantitatively measure and compare the environmental load and construction cost of different structural frame types. Construction cost also accounts for the costs of CO2 emissions of input materials. The choice of structural frame type is a major consideration in construction, as this element represents about 33% of total building construction costs. In this research, four constructed buildings were analyzed, with these having either reinforced concrete (RC) or steel (S) structures. An input-output framework analysis was used to measure energy consumption and CO2 emissions of input materials for each structural frame type. In addition, the CO2 emissions cost was measured using the trading price of CO2 emissions on the International Commodity Exchange. This research revealed that both energy consumption and CO2 emissions were, on average, 26% lower with the RC structure than with the S structure, and the construction costs (including the CO2 emissions cost) of the RC structure were about 9.8% lower, compared to the S structure. This research provides insights through which the construction industry will be able to respond to the carbon market, which is expected to continue to grow in the future.

An Algorithm for Hoisting Time Calculation in Super-tall Building Construction

An installation of the construction lift has a few limitations by many constrains and these have influences on labor productivity, that can be changed by vertical-transportation management. In the super-tall building construction, a management of construction lift operation is one of the most important factor, but existing methodologies depend on skilled practitioners` experiences. And it is true that the expertise resulted by the experiences does not transfer to the next generation. This study is a part of lifting-management simulation development which aims at the optimal construction lift management. A proposed algorithm is focus on lifting time calculation considering an acceleration capability. This research evaluates the result accuracy using comparative analysis on simulation result and field measuring time.

Study on Improvement of Cost Calculation Method in Construction less than One Day Workload

Standard production unit system and historical cost data are the most typical data base for calculating budget price in construction. However, these construction cost estimation methods are difficult to calculate proper construction cost because definition, additional allowance or modification criteria is not clear in construction within one day. Therefore, this study identifies problems for standard production unit system and historical cost data and suggests the improvements for them. For the objectives, this study analyzes frequency after implementing survey for 44 specialty contractors in placing at kyeonggi-province. As the results of the study, labor costs in standard production unit system and equipment costs in historical cost data and in construction of pavement and maintenance by project type was exceeded at most high rate against construction cost estimation methods. Based on this result, standard production unit system and historical cost data need to be modified by three improvements such as classification by project scale. These will be baseline data for improvement of construction cost estimation methods for less than one day workload.표준품셈과 실적공사비 적산방식은 건설공사의 예정가격을 산정하는 가장 대표적인 기준자료이다. 하지만 이러한 공사비 산정방식은 1일 작업량 미만의 작업에서 정의, 할증 또는 보정기준 등이 명확하지 않아 적정 공사비의 산정이 어려운 실정이다. 따라서 본 연구는 1일 작업량 미만의 작업에서 표준품셈과 실적공사비의...

Analysis on the Characteristic of Living Noise in Residential Buildings

The purpose of this study is to analysis the noise characteristics about noise type, sound level, and noise occurrence frequency of living noise in residential buildings. The field measurement was conducted to classify the types of living noise and to examine the actual states of noise occurrence for each living noise source. Among the 24 types of living noise, 10 noise sources were selected based on the loudness and frequency of each living noise. The result indicated that 10 noise sources show the difference on each noise occurrence characteristic by time zones. Therefore, to reduce noise, a management plan should be introduced based on the actual state of the noise occurrence, considering the individual noise source and the time slot during noise frequently occurs. Moreover, the noise standard for each noise types of living noise should be specificated and the education for residents about characteristics of living noise types should be conducted to improve the consciousness of residents.

Optimizing the Mixing Proportion with Neural Networks Based on Genetic Algorithms for Recycled Aggregate Concrete

This research aims to optimize the mixing proportion of recycled aggregate concrete (RAC) using neural networks (NNs) based on genetic algorithms (GAs) for increasing the use of recycled aggregate (RA). NN and GA were used to predict the compressive strength of the concrete at 28 days. And sensitivity analysis of the NN based on GA was used to find the mixing ratio of RAC. The mixing criteria for RAC were determined and the replacement ratio of RAs was identified. This research reveal that the proposed method, which is NN based on GA, is proper for optimizing appropriate mixing proportion of RAC. Also, this method would help the construction engineers to utilize the recycled aggregate and reduce the concrete waste in construction process.

Formwork System Selection Model for Tall Building Construction Using the Adaboost Algorithm

In a tall building construction with reinforced concrete structures, the selection of an appropriate formwork system is a crucial factor for the success of the project. Thus, selecting an appropriate formwork system affects the entire construction duration and cost, as well as subsequent construction activities. However, in practice, the selection of an appropriate formwork system has depended mainly on the intuitive and subjective opinion of working level employees with restricted experience. Therefore, in this study, a formwork system selection model using the Adaboost algorithm is proposed to support the selection of a formwork system that is suitable for the construction site conditions. To validate the applicability of the proposed model, the selection models Adaboost and ANN were both applied to actual case data of tall building construction in Korea. The Adaboost model showed slightly better accuracy than that of the ANN model. The Adaboost model can assist engineers to determine the appropriate formwork system at the inception of future projects.

Web Design System Based on Neural Networks for Strength and Mixing Proportion Prediction of RAC

Recently, as construction wastes have increased and natural aggregates have lacked, it has largely studied about recycled aggregate which reuses of waste concrete. However, it is not enough to apply or practice recycled aggregate concrete for structural object. It is reason that the development of compressive strength is less than that of normal concrete in the concrete made with recycled aggregates due to the characteristic of recycled aggregate. Moreover, in spite of recognizing the difference between recycled aggregate and natural aggregate, the existing mix proportion for normal concrete has been applied to mix proportion of concrete made with recycled aggregate. The purpose of this research is to develop ”Web-Based Prediction System for Recycled Aggregate Concrete” that provides an accurate prediction values of compressive strength and mixing proportion on the recycled aggregate concrete under characteristic of recycled aggregate.

A Study on the Continuing Education Time according to the Basic Safety and Health Training Effect in Domestic Construction Industry

현재 본 연구는 국내 건설현장에서 매년 발생하는 산업재해자를 예방하기 위하여 정부에서 건설업 기초안전·보건교육을 입법 제정하였으며 일용근로자를 대상으로 교육을 실시 이수토록 하였다. 현재 일용근로자가 건설업에 작업하기 위하여 건설업 기초안전·보건교육을 이수하고 있으나 1회성 교육으로 끝나는 것으로 인식되어지고 있으며 그로 인하여 건설업 기초안전·보건교육을 최초 받은 후 시간이 경과함에 따라 일용근로자의 안전관련 지식 이해도 상태가 저하되는 등 건설업 기초안전·보건교육의 실효성에 대한 문제가 발생되어지고 있다. 따라서 건설업 기초안전·보건교육을 이수 받은 후 일정 기간에 따른 안전관련 지식 이해도를 평가분석하고, 그에 따른 건설업 일용근로자 안전관련 지식의 이해도 관련 평가 점수 차이가 가장 크게 나타나는 시점을 파악하여 건설업 기초안전보건교육 효과 평가에 관한 사항을 연구하고 개선사항을 제시하고자 한다. 건설업 기초안전·보건교육효과평가를 연구하기 위해 설문 조사(기본적 사항, 건설업 기초안전·보건교육 인식 조사) 및 기본평가를 실시하였으며, 기본평가의 문제는 총 20 문제로 구성되어 있으며, 기존 연구 및 산업안전보건공단에서 배포사용 중인 교재를 바탕으로 자체적으로 도출하여 출제하였으며, 설문 조사 결과에서 나온 기본평가 점수 값을 ‘SPSS(Statistical Package for the Social Sciences) 19 Program’을 이용하여 t-검정으로 분석하였다. 기본평가의 결과 값에 의하여 건설업 기초안전·보건교육을 최초 이수한 일용근로자의 안전관련 지식이해도 평가 평균 점수를 살펴보면 ‘1년 이상 ∼ 2년 미만’과 ‘2년 이상∼ 3년 미만’ 평균 점수 차이가 가장 크게 발생하여 t-검정 결과 값이 유의한 수준으로 나타났으며, 교육 효과가 2년 이후 부터 건설업 일용근로자의 안전관련 지식수준이 떨어져 불안전한 행동이유발 될 수 있다. 향후 본 연구를 바탕으로 건설업 일용근로자의 효과 평가를 분석하여 2차 교육 시기 등을 정하여 일용근로자의 안전관련 지식을 지속적으로 습득토록 하여 안전의식 수준을 일정하게 유지함으로써 불안전한 행동이 유발되지 않아 건설현장에서 발생될 수 있는 산업재해 예방에 기여 할 수 있기를 바란다.