• 자원ㆍ환경경제연구
• /
• 제17권1호
• /
• pp.147-164
• /
• 2008

주택에 포함된 여러 가지 환경적 요인에 대한 가치추정을 시도할 경우 전형적인 헤도닉 가격기법에서는 시장균형을 가정한다. 이때 개별 요인들의 추정가치는 시장가격에 근거한 암묵적 가치가 된다. 따라서 이 접근법의 논리는 기본적으로 현시선호이론을 배경으로 한다. 그런데 주택시장의 참여자들이 주택과 관련된 요인들에 대해 완전한 정보를 갖지 못하거나 판단이 애매할 경우에는 전형적인 헤도닉 접근법이 제공하는 추정치의 적절성에 대해 의문이 제기될 수 있다. 이 문제의 해결방안으로 퍼지 헤도닉 기법이 제안된 바 있다. 본 논문은 우리나라 주요 공항주변의 비행기 소음이 주택가격에 미치는 영향을 추정하기 위해 퍼지 헤도닉 기법을 응용함으로써 추정치에 포함된 불확실성 또는 모호성 부분을 파악하고자 하였다.

• 한국조경학회지
• /
• 제37권3호
• /
• pp.1-10
• /
• 2009

학교숲은 도시숲의 유형중 하나이다. 도시학교는 적당한 거리에 적당한 면적을 유지하고 있어 학교숲의 조성은 도시에 많은 숲이 조성되는 효과를 준다. 또한, 학교는 학생들이 오랜 시간 머무르는 장소로 학생들의 환경교육의 장으로써의 역할을 수행할 수 있다. 그러나 현재 조성된 학교숲은 학생들의 요구나 참여가 배제된 채 결과 중심의 사업이 되고 있어 학생들의 환경교육에 큰 영향을 미치고 있지 못한 실정이다. 또한 설문조사를 바탕으로 분석하는 기존연구의 경우, 리커트척도를 활용하여 주관적 판단인 정성적 자료를 정량화 하였다는데 의의가 있으나, 인간의 주관적 판단은 모호한 경우가 많아 일반적으로 정량화하는데 문제가 있다. 이에 본 연구에서는 경상북도에 위치한 초등학교 학생들을 대상으로 학교숲에 대한 객관적인 만족도 평가를 위해 퍼지이론을 활용하여, 학교숲 만족도에 미치는 항목들을 알아보고자 하였다. 연구 결과, '학교 특색'과 '정서 함양' 항목의 산술평균값의 순위와 퍼지이론을 도입한 무게중심값의 순위가 변화됨을 알 수 있었다. 이는 퍼지이론이 인간의 사고와 같은 정성적 자료를 합리적으로 객관화 할 수 있다는 증거가 된다. 또한 학교숲 전체 만족도에 영향을 주는 요인은 '학교 특색' 항목의 회귀계수값이 0.159로 가장 높았으며, 다음으로 '수량 많음(0.142)', '자연 소중(0.136)', '정서 함양(0.120)'순으로 나타났다. 이 연구는 설문의 객관적 분석방법과 학교숲 조성을 위한 기초자료로 활용이 가능하리라 판단된다.

• 지능정보연구
• /
• 제20권4호
• /
• pp.43-58
• /
• 2014

최근 정보기술의 발전으로 복잡하고 방대한 양의 주가 데이터에 대한 실시간 분석이 가능해지면서 인공지능 기법을 활용해 주식 시장의 등락을 예측하고, 이를 기반으로 매매 거래를 수행하는 트레이딩 시스템에 대한 세간의 관심이 높아지고 있다. 본 연구는 이러한 트레이딩 시스템의 시장 예측 알고리즘으로 활용될 수 있는 새로운 주식 시장 등락 예측 모형을 제시한다. 본 연구의 제안 모형은 ${\pi}$-퍼지 논리를 이용해 모든 입력변수의 차원을 low, medium, high로 퍼지변환한 입력값을 대상으로 Support Vector Machine(SVM)을 적용하여 익일 시장의 등락을 예측하도록 설계되었다. 그런데 이 경우 입력변수의 수가 3배로 늘어나기 때문에, 적절한 입력변수의 선택이 요구된다. 이에 본 연구에서는 유전자 알고리즘을 활용하여 입력변수 선택 집합을 최적화하도록 하였으며, 동시에 ${\pi}$-퍼지 논리 및 SVM에 적용되는 조절 파라미터들의 값도 함께 최적화 하도록 하였다. 모형의 성능을 검증하기 위해, 본 연구에서는 지난 2004년부터 2013년까지의 10년치 국내 주식시장 데이터를 기반으로 한 KOSPI 200 지수의 등락 예측에 제안모형을 적용해 보았다. 이 때, 비교모형으로 로지스틱 회귀모형, 다중판별분석, 의사결정나무, 인공신경망, SVM, 퍼지SVM 등도 함께 적용시켜 성과를 정밀하게 검증해 보고자 하였다. 그 결과, 제안모형이 예측 정확도는 물론 투자수익률(Return on Investment) 측면에서도 다른 모든 비교모형들에 비해 월등히 우수한 성능을 보임을 확인할 수 있었다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권8호
• /
• pp.561-570
• /
• 2004

In this paper, new architectures and comprehensive design methodologies of Genetic Algorithms(GAs) based Genetically optimized Neurofuzzy Networks(GoNFN) are introduced, and a series of numeric experiments are carried out. The proposed GoNFN is based on the rule-based Neurofuzzy Networks(NFN) with the extended structure of the premise and the consequence parts of fuzzy rules being formed within the networks. The premise part of the fuzzy rules are designed by using space partitioning in terms of fuzzy sets defined in individual variables. In the consequence part of the fuzzy rules, three different forms of the regression polynomials such as constant, linear and quadratic are taken into consideration. The structure and parameters of the proposed GoNFN are optimized by GAs. GAs being a global optimization technique determines optimal parameters in a vast search space. But it cannot effectively avoid a large amount of time-consuming iteration because GAs finds optimal parameters by using a given space. To alleviate the problems, the dynamic search-based GAs is introduced to lead to rapidly optimal convergence over a limited region or a boundary condition. In a nutshell, the objective of this study is to develop a general design methodology o GAs-based GoNFN modeling, come up a logic-based structure of such model and propose a comprehensive evolutionary development environment in which the optimization of the model can be efficiently carried out both at the structural as well as parametric level for overall optimization by utilizing the separate or consecutive tuning technology. To evaluate the performance of the proposed GoNFN, the models are experimented with the use of several representative numerical examples.

• 대한건축학회논문집:계획계
• /
• 제34권5호
• /
• pp.3-10
• /
• 2018

The purpose of this study is to estimate the attractiveness value according to the preference level on architectural aesthetic. This research starts from the concept that aesthetic is phenomenon and from the viewpoint of 'attraction value' which affects goods. Interactive internet surveys were conducted for 500 citizens of Seoul metropolitan city who are potential users of the Nodle Islet Cultural Center. Based on the scenarios and questionnaires with fuzzy models, we have examined the evaluation of architectural aesthetic and monetary willing-to-payment, and estimated the economic value by preference level of architectural aesthetic through linear regression analysis. The main results of the study are as follows: First, the economic value of the Nodle Islet Cultural Center was estimated at ?15,683.43/person. Residents of Seoul metropolitan city were willing to accept the increase in the above-mentioned amount of the facility fares when their preferred works (average 86.81 points) were constructed. (P <0/05) Second, it is confirmed that the economic value increases dramatically as the preference level of architectural aesthetic increases. Third, it is presumed that the infinite valuation of architectural aesthetic and the problem of free riding coexist in the estimation of economic valuation of architectural aesthetic for public buildings. Fourth, by mixing the fuzzy logic with contingent valuation method, starting point bias and no response biases that happened in contingent valuation could be disappeared. bias elimination must be considered seriously because another bias could be happened in full process of the research. The results of this study will serve as a basis for spreading architectural aesthetic value-oriented research from the vague and obscure aesthetic-centered discussion on the existing architectural aesthetic. In addition, it will be an opportunity to draw institutional application and utilization strategy of architectural aesthetic through architectural aesthetic value research.

• Journal of the Korean Data and Information Science Society
• /
• 제19권3호
• /
• pp.801-809
• /
• 2008

Nowadays almost all universities are endeavoring to improve the quality of education offered. The quality of education that is provided should be measured beforehand. This study examined three methods, SERVQUAL, SERVPERF and Lee and Yun(2004)'s method of measuring service quality: SERVQUAL, SERVPERF are well known and the most commonly used measurement of the quality of education offered and the Lee and Yun(2004)'s method measures service quality using fuzzy numbers. As a result of this research, SERVQUAL was proven to be the most efficient method to measure the quality of education offered. Even though, more actual analysis related to this study should be followed, the research is meaningful in a way that it provided clues and reasons for the study.

• Industrial Engineering and Management Systems
• /
• 제9권2호
• /
• pp.88-96
• /
• 2010

This paper presents a two-phase quantitative framework to aid the decision making process for effective selection of an efficient freight logistics hub from 8 alternatives in Thailand on the North-South economic corridor. Phase 1 employs both multiple regression and Pearson Feature selection to find the important criteria, as defined by logistics hub score, and to reduce number of criteria by eliminating the less important criteria. The result of Pearson Feature selection indicated that only 5 of 15 criteria affected the logistics hub score. Moreover, Genetic Algorithm (GA) was constructed from original 15 criteria data set to find the relationship between logistics criteria and freight logistics hub score. As a result, the statistical tools are provided the same 5 important criteria, affecting logistics hub score from GA, and data mining tool. Phase 2 performs the fuzzy stochastic AHP analysis with the five important criteria. This approach could help to gain insight into how the imprecision in judgment ratios may affect their alternatives toward the best solution and how the best alternative may be identified with certain confidence. The main objective of the paper is to find the best alternative for selecting freight logistics hub under proper criteria. The experimental results show that by using this approach, Chiang Mai province is the best place with the confidence interval 95%.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2008년 영문 학술대회
• /
• pp.84-88
• /
• 2008

The UAV propulsion system that will be operated for long time at more than 40,000ft altitude should have not only fuel flow minimization but also high reliability and durability. If this UAV propulsion system may have faults, it is not easy to recover the system from the abnormal, and hence an accurate diagnostic technology must be needed to keep the operational reliability. For this purpose, the development of the health monitoring system which can monitor remotely the engine condition should be required. In this study, a fuzzy trend monitoring method for detecting the engine faults including mechanical faults was proposed through analyzing performance trends of measurement data. The trend monitoring is an engine conditioning method which can find engine faults by monitoring important measuring parameters such as fuel flow, exhaust gas temperatures, rotational speeds, vibration and etc. Using engine condition database as an input to be generated by linear regression analysis of real engine instrument data, an application of the fuzzy logic in diagnostics estimated the cause of fault in each component. According to study results, it was confirmed that the proposed trend monitoring method can improve reliability and durability of the propulsion system for a long endurance UAV to be operated at medium altitude.

• International Journal of Korean Welding Society
• /
• 제1권1호
• /
• pp.17-22
• /
• 2001

Because the quantitative relationships between welding parameters and welding result are not yet blown, optimal values of welding parameters for $CO_2$ robotic arc welding is a difficult task. Using the various artificial data processing methods may solve this difficulty. This research aims to develop an expert system for $CO_2$ robotic arc welding to recommend the optimal values of welding parameters. This system has three main functions. First is the recommendation of reasonable values of welding parameters. For such work, the relationships in between the welding parameters are investigated by the use of regression analysis and fuzzy system. The second is the estimation of bead shape by a neural network system. In this study the welding current voltage, speed, weaving width, and root gap are considered as the main parameters influencing a bead shape. The neural network system uses the 3-layer back-propagation model and a generalized delta rule as teaming algorithm. The last is the optimization of the parameters for the correction of undesirable weld bead. The causalities of undesirable weld bead are represented in the form of rules. The inference engine derives conclusions from these rules. The conclusions give the corrected values of the welding parameters. This expert system was developed as a PC-based system of which can be used for the automatic or semi-automatic $CO_2$ fillet welding with 1.2, 1.4, and 1.6mm diameter the solid wires or flux-cored wires.

• Structural Engineering and Mechanics
• /
• 제89권3호
• /
• pp.301-308
• /
• 2024

Concrete carbonation is a continuous and slow process from the outside to the inside, in which its penetration slows down with the increased depth of carbonation. In this paper, the results of the evaluation of the measurement of concrete carbonation depth using a non-destructive ultrasonic testing method are presented. According to the results, the relative nonlinear parameter caused more sensitivity in carbonation changes compared to Rayleigh's fuzzy velocity. Thus, the acoustic nonlinear parameter is expected to be applied as a quantitative index to recognize carbonation effects. In this research, combo diagrams were developed based on the results of ultrasonic testing and the experiment to determine carbonation depth using a phenolphthalein solution, which could be considered as instructions in the projects involving non-destructive ultrasonic test methods. The minimum and maximum accuracy of this method were 89% and 97%, respectively, which is a reasonable range for operational projects. From the analysis performed, some useful expressions are found by applying the regression analysis for the nonlinearity index and the carbonation penetration depth values as a guideline.