• The KIPS Transactions:PartD
• /
• v.11D no.1
• /
• pp.163-172
• /
• 2004

In the software development project applying object-oriented development methodology, the research on the UCP(Use Case Point) as a method to estimate development effort is being carried on. The existing research proposes the linear model calculating the development effort that multiplies an invariant on AUCP(Adjusted Use Case Point) which applied technical and environmental factors. However, the statistical model that estimates the development effort using AUCP and UUCP(Unadjusted Use Case Point) is not being studied. The irrelevant relationship of the linear regression model, whose development period is increasing tremendously as the software size increases, is confirmed. Moreover, during the UCP calculating process, there can be errors in FP by applying the TCF(Technical Complexity Factor) and EF(Environmental Factor). This paper presents a non-linear regression model, that does not consider the TCF and EF, and that estimate the development effort from UUCP directly by utilizing the exponential function. An exponential function is selected among the linear, logarithm, polynomial, power, and exponential model via statistical evaluations of the models mentioned above.

• Korean Journal of Construction Engineering and Management
• /
• v.7 no.5
• /
• pp.85-93
• /
• 2006

This study is started from a situation of korean construction which has been undergoing diversity. And risk of construction project has been increased recently. The purpose of this study is to propose the model which is able to estimate the proper manpower by eliciting the variable which is offered in the pre-design and construction phase. The existing method of estimate has a problem with calculating exact costs. For this model, it was analyzed the existing manpower estimating model and used historical data of 38 apartment houses, constructed from 2000 to now. Based on these, the regression model of the construction manpower was built. And then the regression model was verified. The result of verification was relatively adequate in the statistics exept for some cases. This regression model will help make it possible for constructor to estimate the deduction of retirement more accurate than existing method.

• Journal of Industrial Convergence
• /
• v.16 no.4
• /
• pp.33-46
• /
• 2018

Personal credit scoring is an effective tool for banks to properly guide decision profitably on granting loans. Recently, many classification algorithms and models are used in personal credit scoring. Personal credit scoring technology is usually divided into statistical method and non-statistical method. Statistical method includes linear regression, discriminate analysis, logistic regression, and decision tree, etc. Non-statistical method includes linear programming, neural network, genetic algorithm and support vector machine, etc. But for the development of the credit scoring model, there is no consistent conclusion to be drawn regarding which method is the best. In this paper, we will compare the performance of the most common scoring techniques such as logistic regression, neural network, and support vector machines using personal credit data of the financial institution in China. Specifically, we build three models respectively, classify the customers and compare analysis results. According to the results, support vector machine has better performance than logistic regression and neural networks.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.6
• /
• pp.857-870
• /
• 2017

The use of shield TBM is gradually increasing due to the urbanization of social infrastructures. Reliable estimation of advance rate is very important for accurate construction period and cost. For this purpose, it is required to develop the prediction model of advance rate that can consider the ground properties reasonably. Based on the database collected from field, statistical prediction procedure for field penetration index (FPI) was modularized in this study to calculate penetration rate of shield TBM. As output parameter, FPI was selected and various systems were included in this module such as, procedure of eliminating abnormal dataset, preprocessing of dataset and ridge regression with best subset selection. And it was finally validated by using field dataset.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.4
• /
• pp.1693-1705
• /
• 2013

To restore old aqueduct in Korea which is a irrigation bridge to supply water in paddy field area, it is needed to estimate approximate costs of restoration because the basic design for estimation of construction costs is often ruled out in current system. In this paper, estimating models of construction costs were developed on the basis of performance data for restoration of RC aqueduct bridges since 2003. The regression analysis (RA) model and case-based reasoning (CBR) model for the estimation of construction costs were developed respectively. Error rate of simple RA model was lower than that of multiple RA model. CBR model using genetic algorithm (GA) has been applied in the estimation of construction costs. In the model three factors like attribute weight, attribute deviation and rank of case similarity were optimized. Especially, error rate of estimated construction costs decreased since limit ranges of the attribute weights were applied. The results showed that error rates between RA model and CBR models were inconsiderable statistically. It is expected that the proposed estimating method of approximate costs of aqueduct restoration will be utilized to support quick decision making in phased rehabilitation project.

• Tunnel and Underground Space
• /
• v.29 no.5
• /
• pp.356-366
• /
• 2019

Various TBM performance prediction models have been developed and most of them were considered penetration rate only. Despite the fact that some models have suggested equations and charts for estimating the utilization factor, but there are a few studies to estimate the TBM utilization factor. Utilization factor is affected by the type of TBM machine, operation, maintenance of machine, geological conditions, contractor experience and other factors. In this study, more than 100 case studies are analyzed to determine the relationship between the utilization factor and RMR, geological conditions, TBM types, tunnel length, and TBM diameter. Simple and multiple linear regression analysis are performed to develop predictive models for the utilization factor. The predictive model with explanatory variables of geological conditions, TBM types, tunnel length, and TBM diameter does not give a good correlation. The predictive models with explanatory variable of RMR give higher values of the coefficient of determination.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07b
• /
• pp.1129-1133
• /
• 2004

반도체공정 최적화에 소요되는 시간과 경비를 줄이기 위해 신경망 모델이 개발되고 있다. 주로 역전파 신경망을 이용하여 모델이 개발되고 있으며, 본 연구에서는 Radial Basis Function Network (RBFN)을 이용하여 플라즈마 식각공정 모델을 개발한다. 실험데이터는 유도결합형 플라즈마를 이용한 Silicon Carbide 박막의 식각공정으로부터 수집되었다. 모델개발을 위해 $2^4$ 전인자 (full factorial) 실험계획법이 적용되었으며, 모델에 이용된 식각응답은 식각률과 atomic force microscopy로 측정한 식각표면 거칠기이다. 모델검증을 위해 추가적으로 16번의 실험을 수행하였다. RBFN의 예측성능은 세 학습인자, 즉 뉴런수, width, 초기 웨이트 분포 (initial weight distribution-IWD) 크기에 의해 결정된다. 본 연구에서는 각 학습인자의 영향을 최적화하였으며, IWD의 불규칙성을 고려하여 주어진 학습인자에 대해서 100개의 모델을 발생하고, 이중 최소의 IWD를 갖는 모델을 선택하였다. 최적화한 식각률과 표면거칠기 모델의 RMSE는 각기 26 nm/min과 0.103 nm이었다. 통계적인 회귀모델과 비교하여, 식각률과 표면거칠기 모델은 각기 52%와 24%의 향상된 예측정확도를 보였다. 이로써 RBFN이 플라즈마 공정을 효과적으로 모델링 할 수 있음을 확인하였다.

• Journal of KIISE:Software and Applications
• /
• v.29 no.12
• /
• pp.873-882
• /
• 2002

Estimation of development cost, effort and time is difficult and a key problem of software engineering in the early stage of software development. These are estimated by using the function point which is measured from a requirement specification. However, it is often a serious Question of the staffing level required for the software development. The purpose of this paper is to show us the model which can be used to estimate a size of development team. Three hundred one software projects have been analyzed and studied for the model. First, an analysis was conducted for statistical algorithmic model. After various data transformation and regression analysis, it was concluded that no good model was available. Therefore, non-algorithmic model was suggested for analysis, which has random distribution of residuals and makes good performance using RBF (Radial Basis Function) network. Since the model provides a standard to determine the required size of development team, it ran be used as management information.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.278-281
• /
• 1998

본 논문에서는 자연음성으로부터 통계적인 방법으로 일반적인 음성합성 규칙을 생성하기 위해, 남녀 각각 1명이 200문장에 대해 발성한 문음성 데이터를 음운 세그먼트, 음운 라벨링, 음운별 품사 태깅, 문법 정보 태깅하여 음성 데이터베이스를 구축하였다. 이 음성 데이터베이스로부터 휴지지속시간을 분석하여 긴 휴지와 짧은 휴지로 분류하였고, 이러한 휴지가 어느 경우에 나타나는가를 조사하였다. 음운지속시간을 보다 정교하게 예측하기 위하여, 각 음운의 고유 지속시간의 영향을 배제시킨 정규화 지속시간에 대해 2가지 class(장, 단)의 휴지시간을 고려한 회귀트리로 음운지속시간을 모델화하였다. 제안된 모델의 평가 결과 예측치와 관측치 간의 다중 상관 계수는 남성은 0.82, 여성은 0.84 정도로 평가되었다.

• 한국IT서비스학회:학술대회논문집
• /
• 2003.05a
• /
• pp.145-152
• /
• 2003

본 연구의 선행 연구에서는 증권시스템의 기능점수를 직접 구하여 기능점수와 운영비용과의 회귀분석을 실시하였다. 수집된 자료의 건수가 적었던 관계로 통계적 유의성을 충분하게 확보하지 못하였다. 따라서 본 연구에서는 증권시스템의 기능점수를 직접 측정하는 것이 현실적으로 많은 제약이 있음을 감안하여, 비교적 자료 수집이 용이한 프로그램 본 수를 측정하였다. 이러한 프로그램 본 수는 스텝 수로 1차 변환이 되었고, 스텝 수는 다시 기능점수로 2차 변환이 되었다. 이렇게 변환된 기능점수와 운영비용과의 회귀분석을 실시하였으며, 증권정보시스템 운영비용 추정 모델을 제시하였다.