• 반도체디스플레이기술학회지
• /
• 제4권2호
• /
• pp.25-32
• /
• 2005

This paper proposes a method for the intelligent load distribution of two cooperating robots(TCRs) using fuzzy logic. The proposed scheme requires the knowledge of the robots' dynamics, which in turn depend upon the characteristics of large flat panel displays(LFPDs) carried by the TCRs. However, the dynamic properties of the LFPD are not known exactly, so that the dynamics of the robots, and hence the required Joint torque, must be calculated for nominal set of the LFPD characteristics. The force of the TCRs is an important factor in carrying the LFPD. It is divided into external force and internal force. In general, the effects of the internal force of the TCRs are not considered in performing the load distribution in terms of optimal time, but they are essential in optimal trajectory planning; if they are not taken into consideration, the optimal scheme is no longer fitting. To alleviate this deficiency, we present an algorithm for finding the internal-force (actors for the TCRs in terms of optimal time. The effectiveness of the proposed system is demonstrated by computer simulations using two three-joint planner robot manipulators.

• 대한의용생체공학회:의공학회지
• /
• 제18권3호
• /
• pp.315-323
• /
• 1997

Driving is a complex vigilance task that includes improper lookout, excessive speed and inattention. The primary objective of this research is to detect driver drowsiness so that the driver can be alerted to an impending traffic accident in performance. We developed the automatic detection and warning system during drowsy driving. A drowsiness detection system must be able to monitor driver status and detect the detrimental changes of a driver performance. Eyeblink has been found to be a reliable factor of drowsiness detection in earlier studies. As an additional parameter, we also considered the yawning which often occurs in a low vigilance state and predicts the drowsy state. We used a computer vision method to extract the eyeblink and yawning in the face image sequences. When the drowsy state was detected, the driver was refreshed by alarming device and menthol scent generator after deciding the warning level by fuzzy logic. For the evaluation of our system, we measured the physiological parameters such as EOG and EEG. The results indicated that it is possible to detect and alert the driver drowsiness temporarily or continuously by using our system.

• 한국반도체및디스플레이장비학회:학술대회논문집
• /
• 한국반도체및디스플레이장비학회 2005년도 추계 학술대회
• /
• pp.110-123
• /
• 2005

This paper proposes an intelligent method for the optimal load distribution of two cooperating robots(TCRs) using fuzzy logic. The proposed scheme requires the knowledge of the robots' dynamics, which in turn depend upon the characteristics of large flat panel displays(LFPDs) carried by the TCRs. However, the dynamic properties of the LFPD are not known exactly, so that the dynamics of the robots, and hence the required joint torque, must be calculated for nominal set of the LFPD characteristics. The force of the TCRs is an important factor in carrying the LFPD. It is divided into external force and internal force. In general , the effects of the internal force of the TCRs are not considered in performing the load distribution in terms of optimal time, but they are essential in optimal trajectory planning: if they are not taken into consideration, the optimal scheme is no longer fitting. To alleviate this deficiency, we present an algorithm for finding the internal-force factors for the TCRs in terms of optimal time. The effectiveness of the proposed system is demonstrated by computer simulations using two three-joint planner robot manipulators.

• Advances in Computational Design
• /
• 제8권2호
• /
• pp.147-177
• /
• 2023

Elliptical concrete-filled steel tubular (CFST) column is widely used in modern structures for both aesthetical appeal and structural performance benefits. The ultimate axial load is a critical factor for designing the elliptical CFST short columns. However, there are complications of geometric and material interactions, which make a difficulty in determining a simple model for predicting the ultimate axial load of elliptical CFST short columns. This study aims to propose an efficient adaptive neuro-fuzzy inference system (ANFIS) model for predicting the ultimate axial load of elliptical CFST short columns. In the proposed method, the ANFIS model is used to establish a relationship between the ultimate axial load and geometric and material properties of elliptical CFST short columns. Accordingly, a total of 188 experimental and simulation datasets of elliptical CFST short columns are used to develop the ANFIS models. The performance of the proposed ANFIS model is compared with that of existing design formulas. The results show that the proposed ANFIS model is more accurate than existing empirical and theoretical formulas. Finally, an explicit formula and a Graphical User Interface (GUI) tool are developed to apply the proposed ANFIS model for practical use.

• 한국지능시스템학회논문지
• /
• 제10권5호
• /
• pp.487-496
• /
• 2000

본 논문에서는, HCM 클러스러팅 방법과 유전자 알고리즘을 이용하여 다중 FNN 모델을 동정하고 최적화 한다. 제안된 다중 FNN은 Yamakawa의 FNN을 기본으로 하며, 퍼지 추론 방법으로 간략 추론을, 학습으로는 오류 역전파 알고리즘을 사용한다. 다중 FNN 모델의 구조와 파라미터를 동정하기 위해 HCM 클러스터링과 유전자 알고리즘을 사용한다. 여기서, 시스템 모델링을 위해 데이터 전처리 기능을 수행하는 HCM클러스터링 방법은 I/O 프로세서 공정 데이터를 이용하여 입출력 공간분할에 의한 다중 FNN 구조를 결정하기 위해 사용된다. 또한 유전자 알고리즘을 사용하여 멤버쉽함수의 정점, 학습율, 모멘텀 계수와 같은 다중 FNN 모델의 파라미터들을 동조한다. 모델의 근사화와 일반화 능력 사이에 합히적 균형을 얻기 위해 하중계수를 가진 합성 성능지수를 사용한다. 이 합성 성능지수는 근사화 및 예측 능력사이의 상호 균형과 의존성을 고려한 하중계수를 가진 합성 목적함수를 의미한다. 데이터 개수, 비선형성의 정도에 의존하는 이 합성 목적함수의 하중계수의 선택, 조절을 통하여 최적의 다중 FNN 모델을 설계하는 것이 유용하고 효과적임을 보인다. 제안된 모델의 성능 평가를 위하여 가스로 공정의 시계열 데이터와 비선형 함수의 수치 데이터를 사용한다.

• 한국수자원학회논문집
• /
• 제41권5호
• /
• pp.517-525
• /
• 2008

지역빈도해석을 통한 확률강우량 산정 결과는 수문학적으로 동질한 지역의 구분 결과에 따라 달라진다. 지역을 구분할 때에는 강우에 영향을 미치는 다양한 변수들이 사용될 수 있다. 변수의 유형과 개수가 지역 구분의 효율성을 좌우하기 때문에 활용 가능한 모든 변수들의 정보를 요약할 수 있는 변수들을 선택하는 것이 지역 구분의 효율성 면에서 유리하다고 할 수 있다. 이런 면에서 지역 구분의 효율성을 증대시킬 목적으로 다변량 분석 기법이 활용될 수 있다. 본 연구에서는 변수들 간의 상관관계를 바탕으로 모든 변수가 표현하는 정보를 대표할 수 있는 더 적은 수의 변수를 선정하는 기법으로 Procrustes analysis를 활용하였다. 이 기법을 활용하여 42개의 강우 관련 변수들을 21개로 줄일 수 있었다. 선정된 변수들을 바탕으로 요인분석을 수행하여 5개의 요인을 추출하였고, 이를 근거로 군집해석 기법인 fuzzy-c means 기법을 활용하여 지역을 구분하였다. 68개 강우 관측 지점을 대상으로 지역을 구분한 결과 6개의 지역으로 구분되었다. 6개의 지역에서 GEV 분포가 적합한 것으로 나타났고, 3변수 대수정규 분포와 generalized logistic 분포가 5개 지역에서 적합한 것으로 나타났다. 기존 연구 결과와의 비교를 위해 generalized logistic 분포를 바탕으로 지점빈도해석, 홍수지수법, 지역형상추정법을 적용하여 확률강우량을 산정하였다.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2000년도 추계 학술발표회 논문집 Proceedings of EESK Conference-Fall 2000
• /
• pp.251-260
• /
• 2000

Seismic performance evaluation systems require rational classification of structure systems, proper evaluation criteria, and their scoring index for synthesis. Current seismic performance systems need expert judgments based on collection of available data, approximate analysis of important items, and various scoring system. This study presents a three-step seismic performance evaluation system for building structures in Korea. Each evaluation step determines the seismic performance and the method depends on the degree of refinement of analysis. The preliminary step evaluation involves the global attributes of structures such as vertical irregularity, asymmetric plan, redundancy, and age of structures. The second step requires an elastic analysis for estimation of forces acting on critical sections and checks the strength and ductility. The final step requires inelastic capacity of structures. Each stephas own evaluation scheme with proper weighing factor dependent on the importance and consequence. This study applies the fuzzy theory to a scoring method that synthesizes the individual quantity to a representative value.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2004년도 춘계학술대회 논문집
• /
• pp.1155-1162
• /
• 2004

This research proposes a new risk analysis method in order to guarantee successful performance of construction projects. The proposed risk analysis methods consists of four phases. First step, AHP model can help contractors decide whether or not they bid for a project by analysing risks involved in the project. Second step, the influence diagraming, decision tree and Monte Carlo simulation are used as tools to analyze and evaluate project risks quantitatively. Third step, Monte Carlo simulation is used to assess risk for groups of activities with probabilistic branching and calendars. Finally, Fuzzy theory suggests a risk management method for construction projects, which is using subjective knowledge of an expert and linguistic value, to analyze and quantify risk. The result of study is expected to improve the accuracy of risk analysis because three factors, such as probability, impact and exposure, for estimating membership function are introduced to quantify each risk factor. Consequently, it will help contractors identify risk elements in their projects and quantify the impact of risk on project time and cost.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권1호
• /
• pp.1-5
• /
• 2012

Data reduction has been used widely in data mining for convenient analysis. Principal component analysis (PCA) and factor analysis (FA) methods are popular techniques. The PCA and FA reduce the number of variables to avoid the curse of dimensionality. The curse of dimensionality is to increase the computing time exponentially in proportion to the number of variables. So, many methods have been published for dimension reduction. Also, data augmentation is another approach to analyze data efficiently. Support vector machine (SVM) algorithm is a representative technique for dimension augmentation. The SVM maps original data to a feature space with high dimension to get the optimal decision plane. Both data reduction and augmentation have been used to solve diverse problems in data analysis. In this paper, we compare the strengths and weaknesses of dimension reduction and augmentation for classification and propose a classification method using data reduction for classification. We will carry out experiments for comparative studies to verify the performance of this research.

• 디지털콘텐츠학회 논문지
• /
• 제2권2호
• /
• pp.103-115
• /
• 2001

본 논문은 퍼지지식베이스에서 러프 집합과 요인공간이론을 적용하여 최소 결정규칙 생성과 근사추론 연산을 수행하는 두 개의 알고리듬을 제안한다. 최소 결정규칙의 생성은 속성요인에 관련한 상관분석과 베이지안 정리를 응용한 데이터의 분류기법과 리덕트에 의해 수행된다. 이 결정규칙으로 이루어진 최소지식 베이스의 탐색공간에서 소속함수와 t-norm의 합성 연산을 정의한 근사추론 방식에 의해 특정 객체를 검색한다. 본 연구의 러프와 퍼지연산 모듈을 수행하는 제안 알고리듬 기법을 객체및 속성수를 증가시키는 시뮬레이션을 통해 다른 검색이론 및 합성연산 방식과 비교하였다. 그 결과 다른 제 방법보다 본 연구에서 제안하는 기법이 특정 객체를 추출하기 위한 검색연산 시간에 있어 보다 빠르게 검색됨을 입증하였다.