• 천문학회보
• /
• 제38권2호
• /
• pp.58.2-58.2
• /
• 2013

Both peculiar velocities and errors in the assumed redshift-distance relation ("Alcock-Paczynski effect") generate correlations between clustering amplitude and orientation with respect to the line-of-sight. In this talk we propose a novel technique to extract the Alcock-Paczynski, geometric, distortion information from the anisotropic clustering of galaxies in 3-dimensional redshift space while minimizing non-linear clustering and peculiar velocity effects. We capitalize on the recent, large dataset from the Sloan Digital Sky Survey III (SDSS-III), which provides a large comoving sample of the universe out to high redshift. We focus our analysis on the Baryon Oscillation Spectroscopic Survey (BOSS) constant mass (CMASS) sample of 549,005 bright galaxies in the redshift range 0.43

• Industrial Engineering and Management Systems
• /
• 제14권3호
• /
• pp.236-247
• /
• 2015

This study aims to examine the effects of industrial clustering and manufacturing flexibility on innovation capability and operational performance. This study follow a survey method to collect data pertaining to the phenomena of industrial clustering, manufacturing flexibility, innovation capability, and operational performance by utilizing a single respondent design. A total of 124 Indonesian manufacturing SMEs are taken to test the proposed theoretical model by utilizing covariance-based structural equations modeling approach. It was found that both industrial clustering and manufacturing flexibility was positively associated with operational performance and innovation capability as well. In addition, innovation capability may account for the effects of industrial clustering and manufacturing flexibility on operational performance. This implies that manufacturing SMEs have to reorient their production and operation perspectives, including agglomerate with other similar or related SMEs to develop and utilize their own resources. The SMEs also need to possess some degree of manufacturing flexibility in respond to the uncertain environment and market changes. In addition, the SMEs should put a greater emphasize to use industrial cluster and manufacturing flexibility benefits to generate innovation capability to achieve high performance.

• 한국음향학회지
• /
• 제25권7호
• /
• pp.319-324
• /
• 2006

본 논문에서는 화자독립 가변어휘 핵심어 검출기의 성능을 개선하기 위하여 두 가지의 새로운 비핵심어 모델링 방법을 제안한다. 첫째는 K-means 알고리즘 기반 monophone 군집화 방법을 개선하기 위해 monophone을 state단위로 결정트리를 기반으로 군집화하여 비핵심어를 모델링하는 방법이다. 둘째는 single state multiple mixture 방법을 개선하기 위해 음절단위 multi-state multiple mixture 방법으로 모델링하는 방법이다. 실험에서 ETRI 표준 한국어 공통음성 단어 DB를 이용하여 트라이폰 모델을 훈련하였고, 훈련에 사용하지 않은 음성데이터를 이용하여 핵심어 검출closed 테스트를 수행하였다. 그리고 사무실 환경에서 4명의 화자가 각각 100문장씩 발성한 400문장의 음성데이터를 이용하여 100단어 핵심어 검출 open 테스트를 수행하였다. 실험 결과 결정트리기반 상태 군집화 방법이 기존의 K-means 알고리듬 기반 monophone clustering 방법보다 핵심어 검출 성능이 28%/29%(closed/open test) 향상되었다 그리고 음절단위 multi-state multiple mixture 방법이 비핵심어 전체를 single state 모델로 구성하는 방법보다 핵심어 검출 성능이 22%/2%(closed/open test) 향상됨으로써 본 논문에서 제안한 두 가지 알고리듬이 우수한 결과를 나타내었다

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1994년도 추계학술대회 논문집
• /
• pp.371-376
• /
• 1994

This paper presents an on-line modeling method approach for the machine condition. the machine condition is continuously monitored with a sensor such as, a vibration, a current, an acoustic emission (AE) sensor. In this study, neural network modeling by radial basis function is designed for analysis a prediction error. An on-line learning algorithm is designed using the RLS(recursive least square) estimation and the existing clustering method of Kohonen neural network. Experimental results show that the proposed RBNN modeling is suitable for predicting simulated data.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.453-458
• /
• 1998

In this paper, a new approach to modeling of nonlinear systems using fuzzy theory is presented. So as to handle a variety of nonlinearity and reflect the degree of confidence in the informations about system, we combine multiple model method with hierarchical prioritized structure. The mountain clustering technique is used in partition of system, and TSK rule structure is adopted to form the fuzzy rules. Back propagation algorithm is used for learning parameters in the rules. Computer simulations are performed to verify the effectiveness of the proposed method. It is useful for the treatment fo the nonlinear system of which the quantitative math-approach is difficult.

• Journal of Electrical Engineering and Technology
• /
• 제8권6호
• /
• pp.1276-1282
• /
• 2013

This paper proposes a stochastic modeling of plug-in electric vehicles (PEVs) distribution in power systems, and analyzes the corresponding clustering characteristic. It is essential for power utilities to estimate the PEV charging demand as the penetration level of PEV is expected to increase rapidly in the near future. Although the distribution of PEVs in power systems is the primary factor for estimating the PEV charging demand, the data currently available are statistics related to fuel-driven vehicles and to existing electric demands in power systems. In this paper, we calculate the number of households using electricity at individual ending buses of a power system based on the electric demands. Then, we estimate the number of PEVs per household using the probability density function of PEVs derived from the given statistics about fuel-driven vehicles. Finally, we present the clustering characteristic of the PEV distribution via case studies employing the test systems.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2014년도 춘계 종합학술대회 논문집
• /
• pp.419-420
• /
• 2014

• 전기학회논문지P
• /
• 제65권2호
• /
• pp.108-113
• /
• 2016

The real-world problems usually show nonlinear and multi-variate characteristics, so it is difficult to establish concrete mathematical models for them. Thus, it is common to practice data-driven modeling techniques in these cases. Among them, most widely adopted techniques are regression model and intelligent model such as neural networks. Regression model has drawback showing lower performance when much non-linearity exists between input and output data. Intelligent model has been shown its superiority to the linear model due to ability capable of effectively estimate desired output in cases of both linear and nonlinear problem. This paper proposes modeling method of daily photovoltaic power systems using ELM(Extreme Learning Machine) based modular networks. The proposed method uses sub-model by fuzzy clustering rather than using a single model. Each sub-model is implemented by ELM. To show the effectiveness of the proposed method, we performed various experiments by dataset acquired during 2014 in real-plant.

• 전기학회논문지
• /
• 제62권4호
• /
• pp.554-561
• /
• 2013

In this paper, we introduce a modeling and a process simulator developed with the aid of pRBFNNs for activated sludge process in the sewage treatment system. Activated sludge process(ASP) of sewage treatment system facilities is a process that handles biological treatment reaction and is a very complex system with non-linear characteristics. In this paper, we carry out modeling by using essential ASP factors such as water effluent quality, the manipulated value of various pumps, and water inflow quality, and so on. Intelligent algorithms used for constructing process simulator are developed by considering multi-output polynomial radial basis function Neural Networks(pRBFNNs) as well as Fuzzy C-Means clustering and Particle Swarm Optimization. Here, the apexes of the antecedent gaussian functions of fuzzy rules are decided by C-means clustering algorithm and the apexes of the consequent part of fuzzy rules are learned by using back-propagation based on gradient decent method. Also, the parameters related to the fuzzy model are optimized by means of particle swarm optimization. The coefficients of the consequent polynomial of fuzzy rules and performance index are considered by the Least Square Estimation and Mean Squared Error. The descriptions of developed process simulator architecture and ensuing operation method are handled.

• 한국정보전자통신기술학회논문지
• /
• 제7권4호
• /
• pp.151-158
• /
• 2014

본 논문에서는 Hard 분산 분할 방법을 이용하는 추론 시스템을 소개하고 비선형 공정을 모델링한다. 이를 위해 입력 공간을 분산 형태로 분할하고 소속 정도가 0 또는 1을 갖는 Hard 분할 방법을 이용한다. 제안한 방법은 C-Means 클러스터링 알고리즘에 의해 구현되며, 초기 중심값에 민감한 단점을 보완하기 위해 LBG 알고리즘을 적용하여 이진 분할에 의한 초기 중심값을 이용한다. Hard 분산 분할된 입력 공간은 규칙 기반의 시스템 모델링에서 규칙을 형성한다. 규칙의 전반부 파라미터는 C-Means 클러스터링 알고리즘에 의한 소속행렬로 결정된다. 규칙의 후반부는 다항식 함수의 형태로 표현되며, 각 규칙의 후반부 파라미터들은 표준 최소자승법에 의해 동정된다. 비선형 공정으로는 널리 이용되는 데이터를 이용하여 비선형 공정을 모델링한 후 특성을 평가한다.