• 한국방재학회 논문집
• /
• 제8권6호
• /
• pp.7-14
• /
• 2008

하수관거시스템 개량의 주된 목적은 불명수(Inflow/Infiltration, I/I)를 제거함으로써 그 성능을 향상시키는데 있다. 이때 전체 하수관거시스템 내에서 개개 관거별 I/I 발생량을 정량화할 수 있다면, 전체 하수관거시스템 내에서 소유역별 해당 정보의 추출이 보다 명확해질 수 있다. 그러나 실제 현장에서는 예산 및 시간의 제약 때문에 개개 관거의 I/I 발생 정보의 획득은 거의 불가능하다. 본 연구에서는 하수 관거별 I/I 발생량을 AHP(Analytic Hierarch Process)를 이용하여 정량화하였으며, 산정된 관거별 I/I 발생량을 이용하여 효율적인 하수과거 개량 사업 시행을 위한 개량 우선순위 결정 모형(Rehabiliation Priority Decision Model for sewer system, RPDM)을 개발하였다. 개개 관거별 I/I 발생량 산정 결과에 기반하여 RPDM은 개량이 시행되는 기간 동안 발생하는 I/I 발생량을 최소화하는 소유역별 최적 개량 우선순위(Optimal Rehabilitation Priority, ORP)를 유전자 알고리즘을 이용하여 결정한다. 이때 최적 개량 우선순위에 따른 소유역별 개량 시행 시 발생하는 이익은 개량 기간 동안 하수처리장으로 들어가는 I/I의 하수처리비용(Waste Water Treatment Cost, WWTC)에 대한 절감을 의미한다. 본 연구에서는 개발된 RPDM에 의한 최적 개량 우선순위의 결과는 일반적인 하수관거 개량사업의 우선순위 결정 방법인 점수가중평가법(Numerical Weighting Method, NWM)과 최악의 개량순서에 따른 결과들과 비교되었으며, 개량 기간 동안의 I/I 처리비용이 점수가중평가법에 비하여 22%, 최악의 개량순서에 비하여 40% 감소하는 것으로 나타났다.

• 대한안전경영과학회지
• /
• 제6권4호
• /
• pp.107-122
• /
• 2004

This study aims to examine the usefulness on the Evaluation Process for the Feasibility & Priority of A Certain Public Projects. and the Methodology used AHP(Analytic Hierarchy Process) which used pairwise comparisons of the alternatives and criteria for solving discrete alternative multicriteria decision problems. In this paper, we present a similar phenomenon, rank reversal problem, when we apply the AHP to group decision making process. The problem is identified by an example problem in that the previous rank order of Public Projects choices. we also present three different methods to prevent the undesirable characteristic of the original AHP in appling to Decision Making Process.

• 한국경영과학회지
• /
• 제29권3호
• /
• pp.41-61
• /
• 2004

The purpose of this paper is to construct $\ulcorner$CIDEAR(Cross Impact-DEA-AR)$\lrcorner$ model which evaluates proposed R&D projects considering cross impact among them and selects proper projects to utilize resources efficiently as well as to maximize efficacy of investments. For this purpose, $\ulcorner$CIDEAR$\lrcorner$ model is designed as the following six steps. $\ulcorner$Decision Theory Evaluation Model$\lrcorner$ is for setting and selecting the evaluation items according to the structured procedure of evaluation system. The priority of items is decided at $\ulcorner$AR Decision Model$\lrcorner$$\ulcorner$Cross Impact Estimation Model$\lrcorner$ is for computing the final probability of success and the result is used to revise the evaluation results of $\ulcorner$Decision Theory Evaluation Model$\lrcorner$. $\ulcorner$Resource Performance Analysis Model$\lrcorner$ classifies the proposed R&D projects on the basis of required resources and expected performance. Consequently, the possibility of bias of project selection can be prevented. $\ulcorner$Priority Oder Decision Model$\lrcorner$ is for computing the efficacy of proposed projects. Finally, $\ulcorner$Efficacy-Efficiency Cause Analysis Model$\lrcorner$ analyzes the structure of efficacy and efficiency of the projects. The major findings and significances of this study are summarized as follows: (1) $\ulcorner$CIDEAR$\lrcorner$ model can deal with the affairs of R&D projects having the characteristics of mutual independence as well as mutual dependence in the point of efficacy and efficiency. Hence, it is possible to evaluate and select R&D projects more accurately. (2) It can be possible to raise the possibility of projects success. R&D manager can use the information for project management because the efficacy-efficiency structure of selected projects can be analyzed. (3) We proved the usefulness of the constructed $\ulcorner$CIDEAR$\lrcorner$ model using an case about twenty-one R&D projects of a leading company of electronic industry in Korea.

• 산업경영시스템학회지
• /
• 제15권26호
• /
• pp.159-163
• /
• 1992

The assumption of reinvestment rate leads to the results conflicting with the priority order of investments determined by net present worth. It has been revealed through various studies that the priority order of projects determined by the criteria based on internal rate of return is different from that determined by present worth. This study is to find out how to define reinvestment rate of return influencing the decision-making of the priority order through examining the meanings of reinvestment rate of capital and true rate of return, and to present some examples with a simple mathematical model.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2003년도 추계학술대회 및 정기총회
• /
• pp.25-28
• /
• 2003

The $\ulcorner$CIDEAR$\lrcorner$ model proceeds the following six steps : $\ulcorner$Decision Theory ＆ Evaluation Model$\lrcorner$, $\ulcorner$AR Decision ＆ Evaluation Model$\lrcorner$, $\ulcorner$Resource ＆ Performance Analysis Model$\lrcorner$, $\ulcorner$Cross Impact Assumption Model$\lrcorner$, $\ulcorner$Priority Oder Decision Model$\lrcorner$, and $\ulcorner$Efficiency Cause Analysis Model$\lrcorner$ - In this study, twenty-one R＆D projects of a leading company in electronic industry are selected to examine the usefulness of the constructed $\ulcorner$CIDEAR$\lrcorner$ model. Simulation method, Excel, Lindo(Linear Interactive and Discrete Optimizer) and Team EC are used in this case study.

• 디지털산업정보학회논문지
• /
• 제19권1호
• /
• pp.109-118
• /
• 2023

Data-based analysis methods have become used more for estimating or predicting housing prices, and neural network models and decision trees in the field of big data are also widely used more and more. Neural network models are often evaluated to be superior to existing statistical models in terms of estimation or prediction accuracy. However, there is ambiguity in determining the input feature of the input layer of the neural network model, that is, the type and number of input features, and decision trees are sometimes used to overcome these disadvantages. In this paper, we evaluate the existing methods of using decision trees and propose the method of using decision trees to prioritize input feature selection in neural network models. This can be a complementary or combined analysis method of the neural network model and decision tree, and the validity was confirmed by applying the proposed method to house price estimation. Through several comparisons, it has been summarized that the selection of appropriate input characteristics according to priority can increase the estimation power of the model.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2000년도 추계학술대회 및 정기총회
• /
• pp.259-262
• /
• 2000

The Cross-impact Hierarchy Process (CHP), an extended model of the Analytic Hierarchy Process(AHP) which is linked to Cross Impact Analysis(CIA), is a powerful decision making tool to assist in the ranking of large number of dependent technological alternatives. In this paper, we will describe an application of the CHP to the aerospace industry. We here conducted a questionnaire survey for S company that is one of the representative aerospace companies in Korea. A questionnaire was designed to obtain both the priority with dependence (the CHP priority) and the priority with independence (the AHP priority) in order to compare the priority derived by each of two methods. The hierarchy in this case study is concerned with priority setting for R&D area to ensure dependent aerospace design technology of the company, The result shows that there exists the difference hard to neglect between the final priorities gained by two methods.

• 한국구조물진단유지관리공학회지
• /
• 제17권1호
• /
• pp.89-101
• /
• 2013

• 한국기술혁신학회:학술대회논문집
• /
• 한국기술혁신학회 2004년도 정기총회 및 추계학술대회 논문집
• /
• pp.187-202
• /
• 2004

• 경영과정보연구
• /
• 제4권
• /
• pp.67-88
• /
• 2000

The purpose of this study is to present models for evaluation and selection of DataBase Management Systems(DBMS) suppliers. The major concern of management is that most decision problems have multiple, usually conflicting, criteria. The fuzzified multiple-objective programming models are given to accomodate the aspiration level and satisfaction level of decision makers. The proposed models are classified into two types, that is, pre-emptive priority and interpolated non-membership function model. Numerical examples illustrating each type of model are presented and the implications of these models are discussed.