• 전자공학회논문지CI
• /
• 제41권3호
• /
• pp.37-45
• /
• 2004

본 논문에서는 이동 에드-혹 네트워크에서 조합가중치 클러스터링 알고리즘을 적용하여 강건하고 신뢰성 있는 클러스터 기반의 그룹 멀티캐스트 방식을 제안한다. 에드-혹 네트워크는 고정된 통신 하부 구조의 도움 없이 이동 단말기로만 구성된 무선 네트워크이다. 제한된 대역폭과 높은 이동성으로 인하여 에드-혹 네트워크에서의 라우팅 프로토콜은 강건하고, 간단하면서 에너지 소비를 최소화하여야 한다. WCGM(Weighted Cluster Group Multicast)방식은 조합 가중치 다중 클러스터 기반 구조를 이용하고 기존의 FGMP(Forwarding Group Multicast Protocol)방식의 장점인 제한적인 플러딩에 의한 데이터 전달방식은 유지하면서 클러스터 헤드 선출 시 조합가중치를 적용한다. 이것은 안정적이며 강건한 데이터 전달 구조를 가지기 때문에 데이터 전달 구조를 유지하기 위한 오버헤드(Overhead)와 데이터 전달을 위한 오버헤드를 모두 줄이는 효과를 시뮬레이션을 통하여 검증하였다.

• 대한임베디드공학회논문지
• /
• 제15권4호
• /
• pp.197-204
• /
• 2020

The ImageNet dataset is a large scale dataset and contains various natural scene images. In this paper, we propose a convolutional neural network (CNN)-based weighted ensemble technique for the ImageNet classification task. First, in order to fuse several models, our technique uses weights for each model, unlike the existing average-based ensemble technique. Then we propose an algorithm that automatically finds the coefficients used in later ensemble process. Our algorithm sequentially selects the model with the best performance of the validation set, and then obtains a weight that improves performance when combined with existing selected models. We applied the proposed algorithm to a total of 13 heterogeneous models, and as a result, 5 models were selected. These selected models were combined with weights, and we achieved 3.297% Top-5 error rate on the ImageNet test dataset.

• Smart Structures and Systems
• /
• 제15권1호
• /
• pp.169-189
• /
• 2015

Convergence difficulty and available complete measurement information have been considered as two primary challenges for the identification of large-scale engineering structures. In this paper, a time domain substructural identification approach by combining a weighted adaptive iteration (WAI) algorithm and an extended Kalman filter method with a weighted global iteration (EFK-WGI) algorithm was proposed for simultaneous identification of physical parameters of concerned substructures and unknown external excitations applied on it with limited response measurements. In the proposed approach, according to the location of the unknown dynamic loadings and the partially available structural response measurements, part of structural parameters of the concerned substructure and the unknown loadings were first identified with the WAI approach. The remaining physical parameters of the concerned substructure were then determined by EFK-WGI basing on the previously identified loadings and substructural parameters. The efficiency and accuracy of the proposed approach was demonstrated via a 20-story shear building structure and 23 degrees of freedom (DOFs) planar truss model with unknown external excitation and limited observations. Results show that the proposed approach is capable of satisfactorily identifying both the substructural parameters and unknown loading within limited iterations when both the excitation and dynamic response are partially unknown.

• 제어로봇시스템학회논문지
• /
• 제6권3호
• /
• pp.273-283
• /
• 2000

In this paper we suggest an optimal design method of Fuzzy-Neural Networks(FNN) model for complex and nonlinear systems. The FNNs use the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. And we use a HCM(Hard C-Means) Clustering Algorithm to find initial parameters of the membership function. The parameters such as parameters of membership functions learning rates and momentum weighted value is proposed to achieve a sound balance between approximation and generalization abilities of the model. According to selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity (distribution of I/O data we show that it is available and effective to design and optimal FNN model structure with a mutual balance and dependency between approximation and generalization abilities. This methodology sheds light on the role and impact of different parameters of the model on its performance (especially the mapping and predicting capabilities of the rule based computing). To evaluate the performance of the proposed model we use the time series data for gas furnace the data of sewage treatment process and traffic route choice process.

• 정보처리학회논문지A
• /
• 제8A권4호
• /
• pp.299-310
• /
• 2001

본 연구에서는 리눅스 가상 서버(LVS：Linux Virtual Server) 클러스터 시스템에서 실제 서버의 상태에 기초한 사용자의 요청을 분배하는 방법론을 연구하고자 한다. LVS 클러스터 시스템에서 사용자의 요청을 분배하는데 적용되는 기존 WLC(Weighted Least Connection) 방법론이 검토되었고, 실제 서버의 부하를 고려하여 각 서버에 요청을 할당하는 부하 분산 방법론을 제안하고자 한다. 부하 측정을 위한 실험은 가상의 부하를 생성하는 툴을 사용하여 서버에 부하를 부과하여 실행되었다. 본 연구에서 제시된 부하 분산 방법론이 기존의 WLC 방법론보다 실제 서버의 메모리 사용측면에서 효율을 기대할 수 있어 제안하고자 하며, 또한 서버 자원을 균형적으로 분배시키고 가중치의 변화에 대한 교정력(correction potentiality)이 어느 정도 개선됨을 확인할 수 있었다.

• 대한산업공학회지
• /
• 제26권2호
• /
• pp.183-192
• /
• 2000

This paper considers the problem of scheduling a set of n jobs on m parallel machines to minimize total weighted tardiness. For the problem a genetic algorithm is proposed, in which solutions are encoded using the random key method suggested by Bean and new crossover operators are employed to increase performance of the algorithm. The algorithm is compared with the Modified Due-Date (MDD) algorithm after series of tests to find appropriate values for genetic parameters. Results of computational tests on randomly generated test problems show that the suggested algorithm performs better than the MDD algorithm and gives good solutions in a reasonable amount of computation time.

• 제어로봇시스템학회논문지
• /
• 제7권12호
• /
• pp.985-992
• /
• 2001

This paper proposes a self-organizing fuzzy modeling(SOFUM)which an create a new hyperplane shaped cluster and adjust parameters of the fuzzy model in repetition. The suggested algorithm SOFUM is composed of four steps: coarse tuning. fine tuning cluster creation and optimization of learning rates. In the coarse tuning fuzzy C-regression model(FCRM) clustering and weighted recursive least squared (WRLS) algorithm are used and in the fine tuning gradient descent algorithm is used to adjust parameters of the fuzzy model precisely. In the cluster creation, a new hyperplane shaped cluster is created by applying multiple regression to input/output data with relatively large fuzzy entropy based on parameter tunings of fuzzy model. And learning rates are optimized by utilizing meiosis-genetic algorithm in the optimization of learning rates To check the effectiveness of the suggested algorithm two examples are examined and the performance of the identified fuzzy model is demonstrated via computer simulation.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2911-2913
• /
• 1999

This paper suggest an optimal identification method to complex and nonlinear system modeling that is based on Fuzzy-Neural Network(FNN). The FNN modeling implements parameter identification using HCM algorithm and optimal identification algorithm structure combined with two types of optimization theories for nonlinear systems, we use a HCM Clustering Algorithm to find initial parameters of membership function. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using optimal identification algorithm. The proposed optimal identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregate objective function(performance index) with weighted value is proposed to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model, we use the time series data for gas furnace, the data of sewage treatment process and traffic route choice process.

• 정보처리학회논문지B
• /
• 제10B권7호
• /
• pp.757-768
• /
• 2003

본 논문에서는 가중 퍼지 Pr/T 네트에 기반을 둔 규칙기반시스템을 위한 가중 퍼지 추론알고리즘을 제안한다. 이때 퍼지 생성규칙의 확신도, 규칙에 나타나는 술어의 진리값과 술어의 중요도를 나타내는 가중값을 퍼지 숫자로 표현한다. 제안한 추론알고리즘은 퍼지 생성규칙에 있는 술어의 중요도에 따라 부여한 가중값을 이용하여 추론하기 때문에 $\circled1$ 술어의 가중값 없이 퍼지 생성규칙의 확신도만을 기반으로 단순하게 min과 max 연산을 하거나[10], $\circled2$ 술어의 가중값 없이 퍼지 생성규칙에 있는 퍼지 개념에 따라 믿음값 평가함수로 퍼지 생성규칙의 믿음값을 평가하는[12] 방법보다 더 유연하고 사람의 직관과 추론에 가깝다.

• Journal of information and communication convergence engineering
• /
• 제11권4호
• /
• pp.258-267
• /
• 2013

New incremental learning algorithm using extended data expression, based on probabilistic compounding, is presented in this paper. Incremental learning algorithm generates an ensemble of weak classifiers and compounds these classifiers to a strong classifier, using a weighted majority voting, to improve classification performance. We introduce new probabilistic weighted majority voting founded on extended data expression. In this case class distribution of the output is used to compound classifiers. UChoo, a decision tree classifier for extended data expression, is used as a base classifier, as it allows obtaining extended output expression that defines class distribution of the output. Extended data expression and UChoo classifier are powerful techniques in classification and rule refinement problem. In this paper extended data expression is applied to obtain probabilistic results with probabilistic majority voting. To show performance advantages, new algorithm is compared with Learn++, an incremental ensemble-based algorithm.