• Asia pacific journal of information systems
• /
• 제16권2호
• /
• pp.69-84
• /
• 2006

Importance of Today's diffusion of integrated hospital information systems is that various and huge amount of data is being accumulated in their database systems. Many researchers have studied utilizing such hospital data. While most researches were conducted mainly for medical diagnosis, there have been insufficient studies to develop medical care cost prediction model, especially using machine learning techniques. In this research, therefore, we built a medical care cost prediction model for cancer patients using CBR (Case-Based Reasoning), one of the machine learning techniques. Its performance was compared with those of Neural Networks and Decision Tree models. As a result of the experiment, the CBR prediction model was shown to be the best in general with respect to error rate and linearity between real values and predicted values. It is believed that the medical care cost prediction model can be utilized for the effective management of limited resources in hospitals.

• 한국안전학회지
• /
• 제27권6호
• /
• pp.1-6
• /
• 2012

This study focuses on the benefit-cost analysis of certification of more than eight hundred devices and equipments used primarily in farm work. Specifically, EPA-suggested averting behavior approach was used for the analysis. Cost-benefit analysis indicates that there will be a net cost of 30 billion won for the first year since the introduction of the certification system. It is expected, however, that net benefit of 568 billion won after 11 years and the accumulated net benefit will reach to 3,867 billion won. These results validate the introduction of safety certification systems for devices and equipments used in farm work sites.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2023년도 봄 학술논문 발표대회
• /
• pp.329-330
• /
• 2023

The performance of the construction project is to be evaluated within 60 days of completion, according to relevant laws. It evaluates cost, construction period, design change, re-construction, safety, etc. for each project stage. And the project owners are inputting the evaluation results of the construction work into the construction project information system(CALS). The post-evaluation result information entered in this way can be referred to in the basic design of the construction project by referring to the related contents if there is a similar construction in the future. And It can also be used to predict and respond to the required period and cost by analyzing the accumulated data. In this study, in order to provide reference data that can be used in similar projects in the future, the latest analysis methods are reviewed and the possibility of future application is considered. Accordingly, this study intends to focus on the construction cost part among the indicators such as construction cost, construction period, design change, and re-construction that are currently being dealt with in post evaluation.

• 대한토목학회논문집
• /
• 제28권3D호
• /
• pp.371-381
• /
• 2008

국내 하천시설물 건설공사는 도로 등의 다른 토목시설공사에 비해서 사업의 금액규모가 상대적으로 작다는 등의 특성으로 인해 사업의 기획 및 계획단계에서의 개략적인 공사비용을 예측하는 기준 단가가 정립되어 있지 않으며, 시설물의 특성을 고려한 합리적이고 체계적인 견적 방법론 또한 존재하지 않는다는 문제점을 가지고 있다. 본 연구는 하천시설물 건설공사의 실적자료를 수집하고 분석하여, 4단계로 이루어진 하천 제방공사 실적정보 구성 체계를 제시하고, 공사비에 영향을 끼치는 인자들을 주요 공종별로 도출하여, 하천시설물 공사의 기획단계에서 적정한 개략공사비를 산정하는 체계적인 방법론을 제시한다.

• KIEAE Journal
• /
• 제16권4호
• /
• pp.79-86
• /
• 2016

Purpose: Frequently, the apartment management offices have difficulties in effective repair works due to their insufficient technological capability to operate long-term repair program. There also have been many cases of failure in executing urgent repairs mainly because the repair allowance has not accumulated enough for the repair works on time. This study aimed to determine core items in apartment maintenance in order to reduce the confusion and unnecessary efforts for the management office by suggesting simple list of repair items. Method: Core items are defined using several indicators. The degrees of necessity for repair work(NRW) are calculated combining the impacts to living, safety, and aesthetics. Then the degrees of burden of repair cost(BRC) are estimated by analyzing actual long-term repair program of three apartment complexes. Lastly the degrees of accumulation demand for repair allowance(AD) are calculated with NRW and BRC. Result: The core items and essential items are suggested for three apartment types as case studies based on the indicators of NRW, BRC, and AD. Then, the required accumulated allowance per $m^2$ was calculated to effectively implement repair works.

• Journal of the Korean Data and Information Science Society
• /
• 제8권1호
• /
• pp.85-89
• /
• 1997

In this paper, we consider a random replacement model with minimal repair, which is a generalization of the random replacement model introduced Lee and Lee(1994). It is assumed that a system is minimally repaired when it fails and replaced only when the accumulated operating time of the system exceeds a threshold time by a supervisor who arrives at the system for inspection according to Poisson process. Assigning the corresponding cost to the system, we obtain the expected long-run average cost per unit time and find the optimum values of the threshold time and the supervisor's inspection rate which minimize the average cost.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2019년도 춘계 학술논문 발표대회
• /
• pp.230-231
• /
• 2019

The nuclear power plant construction project is large-scale, has various stakeholders and computer system, and is produced and managed a large amount of information. The domestic nuclear power plant construction project has accumulated data based on many years of experience in the system. It has the competitiveness to suggeest alternatives that meet the requirement of the client in the overseas nuclear power plant project. Earned value management, which integrates schedule and cost, is possible to risk management. It was developed the earned value management system considering the the actual data properties and types of the preceding nuclear power plant construction projects. It will be able to increase the nuclaer power plant export competieiveness. Therefore, it was palned to carry out future stuies so that it be able to complement the measure to integrate cost and schedule in consideration of actual data(quantity of activity, etc.).

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2015년도 춘계 학술논문 발표대회
• /
• pp.251-252
• /
• 2015

Enough school facility maintenance data should be accumulated in a database or data warehouse in order to supply information about school facility correct maintenance budget plan, budget assignment, and cycle and rate of maintenance or replacement. For those, this research analyze the present school facility maintenance practice and budget and construction cost structure. In order to solve the problems, this study analyze the present practice of maintenance and replacement and obtain LCC(Life cycle cost) data, perform expert interview and then establish construction work breakdown structure of maintenance of educational facility by combining work breakdown structure(WBS) and cost breakdown structure(CBS).

• 센서학회지
• /
• 제32권3호
• /
• pp.174-179
• /
• 2023

Bulk trailers, used for the transportation of powdered materials, such as cement and fly ash, are crucial in the construction industry. The speedy exhaustion of powdered materials stored in the tank of bulk trailers is relevant to improving transportation efficiency and reducing transportation costs. The exhaust time can be reduced by developing an automatic control system to replace the manual exhaust operation. The instantaneous or accumulated exhausts of powdered materials must be measured for automatic control of the bulk trailer exhaust system. Accordingly, we previously proposed a recurrent neural network (RNN) model that estimated the instantaneous exhaust based on low-cost pressure sensor signals without an expensive flowmeter for powders. Although our previous study utilized only an RNN model, models such as multilayer perceptron (MLP) and convolutional neural network (CNN) are also widely utilized for time-series estimation. This study compares the performance of three neural network models (MLP, CNN, and RNN) in estimating instantaneous and accumulated exhausts. In terms of the instantaneous exhaust estimation, the difference in the performance of neural network models was insignificant (that is, 8.64, 8.62, and 8.56% for the MLP, CNN, and RNN, respectively, in terms of the normalized root mean squared error). However, in the case of the accumulated exhaust, the performance was excellent in the order of CNN (1.67%), MLP (2.03%), and RNN (2.20%).

• KIEAE Journal
• /
• 제6권1호
• /
• pp.3-10
• /
• 2006

As has been expected, economic factors are a major consideration in almost every decision in building design process. Assuming that improving a lighting system, existing or proposed, will reduce operating cost, what preliminary economic guidelines can be established to determine whether any proposed investment appears cost effective? In such a case a reasonable technique to compare system costs is by life-cycle costing. Stated simply, a life-cycle cost represents the total cost of a system over its entire life cycle, that is, the sum of first cost and all future costs. This paper aims to exemplify the benefit of daylighting in term of economic consideration. Four different electric lighting system designs are proposed and a lighting control system that is continuously operating according to the level of daylight in the space has been adapted. The accumulated performance of electric and daylighting is figured out to declare the effective depth of daylight in the space. The analysis on the saving amount of lighting energy due to daylight has been undertaken in answer to the question, that is, several projects are being considered, which is the most desirable from the cost-effectiveness viewpoint. The result shows clearly that although denser layout of lighting fixtures might be more effective to interface to the level of daylight ceaselessly changeable, its economic benefit may not meet the expected criterion the reason of increased initial investment and maintenance cost for the fixtures and control hardware.