• 한국건축시공학회지
• /
• 제12권5호
• /
• pp.518-527
• /
• 2012

This study uses a hybrid estimation tool for effective cost data management of building projects, and develops a realistic cost estimation model. The method makes use of newly available information as the project progresses, and project cost and percentage progress are analyzed and used as inputs for the developed system. For model development, case-based reasoning (CBR) is proposed, as it enables complex nonlinear mapping. This study also investigates analytic hierarchy process (AHP) for weight generation and applies them to a real project case. Real case studies are used to demonstrate and validate the benefits of the proposed approach. By using this method, an evaluation of actual project performance can be developed that appropriately considers the natural variability of construction costs.

• 지능정보연구
• /
• 제1권1호
• /
• pp.91-109
• /
• 1995

This paper compared four knowledge acquisition methods (namely, neural network, case-based reasoning, discriminant analysis, and covariance structure modeling) for allergic rhinitis. The data were collected from 444 patients with suspected allergic rhinitis who visited the Otorlaryngology Deduring 1991-1993. Among four knowledge acquisition methods, the discriminant model had the best overall diagnostic capability (78%) and the neural network had slightly lower rate(76%). This may be explained by the fact that neural network is essentially non-linear discriminant model. The discriminant model was also most accurate in predicting allergic rhinitis (88%). On the other hand, the CSM had the lowest overall accuracy rate (44%) perhaps due to smaller input data set. However, it was most accuate in predicting non-allergic rhinitis (82%).

• 국제학술발표논문집
• /
• The 1th International Conference on Construction Engineering and Project Management
• /
• pp.1065-1069
• /
• 2005

The construction failures can be decreased through continuous improvement of construction process based upon the information of construction failures. Herein, the information of construction failures can be utilized as the key factor for identifying and enhancing various ineffective construction processes that can prevent failures. This research proposes a process model for the continuous improvement of construction processes by using construction failure information. Extensive reviews and analyses of literatures related to construction failures are performed to investigate its definition, type, cause, and lessons learned. This research adapts process modeling methodology and case-based reasoning for the development of the proposed CIMCP(continuous improvement model of construction process), and then suggests its framework that contains modules of case retrieval, case index, and case adaptation.

• 대한간호학회지
• /
• 제53권1호
• /
• pp.87-100
• /
• 2023

Purpose: This study aimed to develop a nursing simulation learning module for coronavirus disease 2019 (COVID-19) patient-care and examine its effects on clinical reasoning competence, clinical competence, performance confidence, and anxiety in COVID-19 patient care for nursing students. Methods: A non-equivalent control group pre- and post-test design was employed. The study participants included 47 nursing students (23 in the experimental group and 24 in the control group) from G City. A simulation learning module for COVID-19 patient-care was developed based on the Jeffries simulation model. The module consisted of a briefing, simulation practice, and debriefing. The effects of the simulation module were measured using clinical reasoning competence, clinical competence, performance confidence, and anxiety in COVID-19 patient-care. Data were analyzed using χ²-test, Fisher's exact test, t-test, Wilcoxon signed-rank test, and Mann-Whitney U test. Results: The levels of clinical reasoning competence, clinical competence, and performance confidence of the experimental group were significantly higher than that of the control group, and the level of anxiety was significantly low after simulation learning. Conclusion: The nursing simulation learning module for COVID-19 patient-care is more effective than the traditional method in terms of improving students' clinical reasoning competence, clinical competence, and performance confidence, and reducing their anxiety. The module is expected to be useful for educational and clinical environments as an effective teaching and learning strategy to empower nursing competency and contribute to nursing education and clinical changes.

• 지능정보연구
• /
• 제25권3호
• /
• pp.239-251
• /
• 2019

본 논문은 학습데이터의 크기에 따른 사례기반추론기법이 주가예측력에 어떻게 영향을 미치는지 살펴본다. 삼성전자 주가를 대상을 학습데이터를 2000년부터 2017년까지 이용한 경우와 2015년부터 2017년까지 이용한 경우를 비교하였다. 테스트데이터는 두 경우 모두 2018년 1월 1일부터 2018년 8월 31일까지 이용하였다. 시계 열데이터의 경우 과거데이터가 얼마나 유용한지 살펴보는 측면과 유사사례개수의 중요성을 살펴보는 측면에서 연구를 진행하였다. 실험결과 학습데이터가 많은 경우가 그렇지 않은 경우보다 예측력이 높았다. MAPE을 기준으로 비교할 때, 학습데이터가 적은 경우, 유사사례 개수와 상관없이 k-NN이 랜덤워크모델에 비해 좋은 결과를 보여주지 못했다. 그러나 학습데이터가 많은 경우, 일반적으로 k-NN의 예측력이 랜덤워크모델에 비해 좋은 결과를 보여주었다. k-NN을 비롯한 다른 데이터마이닝 방법론들이 주가 예측력 제고를 위해 학습데이터의 크기를 증가시키는 것 이외에, 거시경제변수를 고려한 기간유사사례를 찾아 적용하는 것을 제안한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.635-639
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the modeling of chaotic nonlinear systems. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the modeling performance for chaotic nonlinear systems and compare it with those of the FNN and the WFM.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권1호
• /
• pp.111-118
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• 한국융합학회논문지
• /
• 제10권9호
• /
• pp.11-16
• /
• 2019

사람들은 바쁜 현대사회 속에서 시간적 제재를 받고 있다. 이에 따라 사람들은 건강에 나쁜 영향을 미치는 간편한 인스턴트 식품을 섭취하고 간단한 운동조차하기 어려운 상황에 놓여있다. 또한 불필요한 정보과부화 현상으로 인해 개인의 특성에 적합하고 정확한 추론을 하는 것에 대한 중요성이 커지고 있다. 따라서 본 논문에서는 다중상황의 군집분석과 연관규칙을 이용한 지식추론 모델을 제안한다. 제안하는 방법은 상황정보에 따른 군집을 기반으로 연관규칙을 생성함으로써 사용자들에게 개인화된 헬스케어 방법을 제공한다. 이를 통해 각 질병에 대한 위험도를 추론함으로써 해당 질병에 대한 발병률을 낮출 수 있다. 또한 성능 평가를 통해 제안하는 모델이 비교 모델보다 수치상으로 F-measure 값이 0.027 더 높게 나타나며, 비교 모델 보다 우수하게 평가된다.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.1183-1188
• /
• 2009

Estimating project costs during the early stage of conceptual planning is very important when deciding whether to approve the project and allocate an appropriate budget. However, due to greater uncertainties involved in a project, it is challenging to estimate costs during this initial stage within a reasonable tolerance. This paper attempts to develop a cost-estimate model for public road projects under these circumstances and limitations. In the conceptual planning stage of a road project, there is only limited information for cost estimation, for example, such input data as total length of the route, origin and destination, number of lanes, general geographic characteristics of the route, and other basic attributes. This implies that the model should individuate suitable but restricted information without considering detailed features such as quantity of earthwork and a detailed route of a given condition. With these limited facts, this paper applies a case-based reasoning (CBR) method to solve a new problem by deriving similar past problems, which in turn is used to estimate the cost of a given project based on best-fitted previous cases. To develop a CBR cost-estimate model, the authors classified 8 representative variables, including project type, the number of lanes, total length, road design grades, etc. Then, we developed the CBR model, primarily by using 180 actual cases of public road projects, procured over the last decade. With the CBR model, it was found that the degree of error in estimation can be reasonably reduced, to below approximately 30% compared to the final costs estimated upon the completion of detailed design.

• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.283-286
• /
• 2007

This paper proposes a genetic algorithm (GA) approach to instance selection in case-based reasoning (CBR) for the prediction of Korea Stock Price Index (KOSPI). CBR has been widely used in various areas because of its convenience and strength in complex problem solving. Nonetheless, compared to other machine learning techniques, CBR has been criticized because of its low prediction accuracy. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. In this paper, the GA optimizes simultaneously feature weights and a selection task for relevant instances for achieving good matching and retrieval in a CBR system. This study applies the proposed model to stock market analysis. Experimental results show that the GA approach is a promising method for instance selection in CBR.