• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2021년도 가을 학술논문 발표대회
• /
• pp.228-229
• /
• 2021

Planning/planning stage Construction cost prediction is very important. In particular, flexible thinking is required to predict the construction cost by reflecting rapid market changes and current conditions. Therefore, in this study, we tried to consider the process for calculating the construction cost of an apartment house in a more accurate planning/planning stage. First, cases were collected based on the classification system by construction type. Second, the construction cost was predicted using the case-based reasoning technique. Third, the composition ratio by construction type of the most similar case was applied to the derived construction cost. Finally, the construction cost was predicted based on practical corrections reflecting the market and field conditions.

• Advances in aircraft and spacecraft science
• /
• 제11권1호
• /
• pp.1-21
• /
• 2024

The stiffness reduction of cross-ply composite laminates featuring a transverse cracking and delamination within the mid-layer is predicted through utilization of a modified shear-lag model, incorporating a stress perturbation function. Good agreement is obtained by comparing the prediction models and experimental data. The material characteristics of the composite are affected by fluctuations in temperature and transient moisture concentration distribution in desorption case, based on a micro-mechanical model of laminates. The transient and non-uniform moisture concentration distribution induces a stiffness reduction. The obtained results demonstrate the stiffness degradation dependence on factors such as cracks density, thickness ratio and environmental conditions. The present study underscores the significance of comprehending the degradation of material properties in the failure progression of laminates, particularly in instances of extensive delamination growth.

• Communications for Statistical Applications and Methods
• /
• 제31권4호
• /
• pp.365-375
• /
• 2024

Diverse methods to evaluate the prediction model of a time to event have been proposed in the context of right censored data where all subjects are subject to be susceptible. A time-dependent AUC (area under curve) measures the predictive ability of a marker based on case group and control one which are varying over time. When a substantial portion of subjects are event-free, a population consists of a susceptible group and a cured one. An uncertain curability of censored subjects makes it difficult to define both case group and control one. In this paper, our goal is to propose a time-dependent AUC for a cure rate model when a censoring distribution is related with covariates. A class of inverse probability of censoring weighted (IPCW) AUC estimators is proposed to adjust the possible sampling bias. We evaluate the finite sample performance of the suggested methods with diverse simulation schemes and the application to the melanoma dataset is presented to compare with other methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.631-634
• /
• 2004

In this paper, the Bayesian recurrent neural network (BRNN) is proposed to predict time series data. Among the various traditional prediction methodologies, a neural network method is considered to be more effective in case of non-linear and non-stationary time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one need to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, we sets the weight vector as a state vector of state space method, and estimates its probability distributions in accordance with the Bayesian inference. This approach makes it possible to obtain more exact estimation of the weights. Moreover, in the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent network with Bayesian inference, what we call BRNN, is expected to show higher performance than the normal neural network. To verify the performance of the proposed method, the time series data are numerically generated and a neural network predictor is applied on it. As a result, BRNN is proved to show better prediction result than common feedforward Bayesian neural network.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.199-202
• /
• 1996

Although numerous studies demonstrate that one technique outperforms the others for a given data set, there is often no way to tell a priori which of these techniques will be most effective to solve a specific problem. Alternatively, it has been suggested that a better approach to classification problem might be to integrate several different forecasting techniques by combining their results. The issues of interest are how to integrate different modeling techniques to increase the prediction performance. This paper proposes the post-model integration method, which means integration is performed after individual techniques produce their own outputs, by finding the best combination of the results of each method. To get the optimal or near optimal combination of different prediction techniques. Genetic Algorithms (GAs) are applied, which are particularly suitable for multi-parameter optimization problems with an objective function subject to numerous hard and soft constraints. This study applied three individual classification techniques (Discriminant analysis, Logit and Neural Networks) as base models to the corporate failure prediction context. Results of composite prediction were compared to the individual models. Preliminary results suggests that the use of integrated methods will offer improved performance in business classification problems.

• 한국콘텐츠학회논문지
• /
• 제10권6호
• /
• pp.134-143
• /
• 2010

본 논문에서는 위험도라는 품질 인자를 예로 들어 메트릭 기반 소프트웨어 품질 예측 모델들을 네가지 타입으로 분류하는 프레임워크를 제안한다. 모델들은 다음과 같은 두가지 기준에 의해 분류된다: 모델 입력 메트릭 형태, 과거 프로젝트 데이터의 필요 유무. 분류된 타입들은 각각의 특성을 가지며 새롭게 정의된 몇가지 기준들에 의해 타 타입들과 장단점이 비교되었다. 이러한 정성적인 평가를 거쳐 품질 예측 모델을 이용하고자하는 개발 집단은 어떤 품질 예측 모델이 자신들에게 적합한지를 판단할 수 있게 된다. 또한 각 타입에 속하는 위험도 예측 모델들을 구현해 예측 성능을 측정한 선행 연구 데이터를 분석하여 예측 성능에 못지않게 모델이 속한 타입의 특성이 모델 선정의 중요한 관건이 됨을 보였다.

• 한국측량학회지
• /
• 제30권6_2호
• /
• pp.623-629
• /
• 2012

During the construction of crossing engineering one of the important measures to ensure the safety of subway operation is the implementation of deformation surveying to the existing subway tunnel. Guangzhou new subway line 2 engineering which crosses the existing tunnel is taken as the background. How to achieve intelligent and automatic deformation surveying forecast during the subway tunnel construction process is studied. Because large amount of surveying data exists in the subway construction, deformation analysis is difficult and prediction has low accuracy, a subway intelligent deformation prediction model based on the PBIL and support vector machine is proposed. The PBIL algorithm is used to optimize the exact key parameters combination of support vector machine though probability analysis and thereby the predictive ability of the model deformation is greatly improved. Through applications on the Guangzhou subway across deformation surveying deformation engineering the prediction method's predictive ability has high accuracy and the method has high practicality. It can support effective solution to the implementation of the comprehensive and accurate surveying and early warning under subway operation conditions with the environmental interference and complex deformation.

• 한국구조물진단유지관리공학회 논문집
• /
• 제5권1호
• /
• pp.237-246
• /
• 2001

This study is to measure the creep coefficient by 3 days, 7 days and 28 days in the age when loading for the quality assessment of $350kgf/cm^2$ in the high-strength concrete. And it is to analyze the behavior of creep coefficient by applying the experimental data though the compressive strength test, the elastic modulus test and the dry shrinkage test to the ACI-209, AASHTO-94 and CEB/FIP-90, the prediction mode, and the basis of concrete structural design. Also it is to analyze the behavior of short-term creep coefficient during 91 days in the age when loading through the experiment by using the regression analysis, the statistical theory. As applying it to the long-term behavior during 365 days and comparing with the creep prediction mode and examining it, the result from the analysis of the quality of the concrete is as follows. As the result of comparison and analysis about the ACI-209, AASHTO-94 and CEB/FIP-90, the prediction mode, and the basis of concrete structural design, the normal Portland cement class 1 shows the approximate value with the prediction of GEE/PIP-90 and the basis of concrete structural design, but in case of the prediction of ACI-209 and AASHTO-94, there would be worry of underestimation in the application.

• Journal of electromagnetic engineering and science
• /
• 제11권3호
• /
• pp.220-226
• /
• 2011

We have proposed a new method to accurately predict the resonance of Fabry-Perot Cavity (FPC) antennas enclosed with conducting side walls. When lateral directions of an FPC antenna are not blocked with metallic walls, the conventional technique is accurate enough to predict the resonance of the FPC antenna. However, when the FPC antenna has side walls, especially for case with only a short distance between the walls, the conventional prediction method yields an inaccurate result, inevitably requiring a tedious, time-consuming tuning process to determine the correct resonant height to provide the maximum antenna gain in a target frequency band using three-dimensional full-wave computer simulations. To solve that problem, we have proposed a new resonance prediction method to provide a more accurate resonant height calculation of FPC antennas by using the well-known resonance behavior of a rectangular resonant cavity. For a more physically insightful explanation of the new prediction formula, we have reinvestigated our proposal using a wave propagation characteristic in a hollow rectangular waveguide, which clearly confirms our approach. By applying the proposed technique to an FPC antenna covered with a partially reflecting superstrate consisting of continuously tapered meander loops, we have proved that our method is very accurate and readily applicable to various types of FPC antennas with lateral walls. Experimental result confirms the validness of our approach.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제17권2호
• /
• pp.92-102
• /
• 2017

Purpose: Reliability prediction standards consider environmental conditions, such as temperature, humidity and vibration in order to predict the reliability of the electronics components. There are many types of standards, and each standard has a different failure rate prediction model, and requires different environmental conditions. The purpose of this study is to make a sensitivity analysis by changing the temperature which is one of the environmental conditions. By observing the relation between the temperature and the failure rate, we perform the sensitivity analysis for standards including MIL-HDBK-217F, RiAC-HDBK-217Plus and FIDES. Methods: we establish environmental conditions in accordance with maneuver weapon systems's OMS/MP and mission scenarios then predict the reliability using MIL-HDBK-217F, RiAC-HDBK-217Plus and FIDES through the case of DC-DC Converter. Conclusion: Reliability prediction standards show different sensitivities of their failure rates with respect to the changing temperatures.