• 한국멀티미디어학회논문지
• /
• 제17권10호
• /
• pp.1160-1170
• /
• 2014

Clustering methods are very useful in many fields such as data mining, classification, and object recognition. Both the supervised and unsupervised grouping approaches can classify a series of sample data with a predefined or automatically assigned cluster number. However, there is no constraint on the number of elements for each cluster. Numbers of cluster members for each cluster obtained from clustering schemes are usually random. Thus, some clusters possess a large number of elements whereas others only have a few members. In some areas such as logistics management, a fixed number of members are preferred for each cluster or logistic center. Consequently, it is necessary to design a clustering method that can automatically adjust the number of group elements. In this paper, a k-means based clustering method with a fixed number of cluster members is proposed. In the proposed method, first, the data samples are clustered using the k-means algorithm. Then, the number of group elements is adjusted by employing a greedy strategy. Experimental results demonstrate that the proposed clustering scheme can classify data samples efficiently for a fixed number of cluster members.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 추계학술대회
• /
• pp.831-834
• /
• 2011

WSN 분야의 대표적인 알고리즘의 하나인 LEACH는 시스템 수명동안 모든 노드들이 균일한 횟수로 클러스터 헤더가 되는 것을 보장한다. 하지만 각 라운드별로 일정한 클러스터 헤더 수를 보장하지 못하여 클러스터 헤더가 선출되지 못하는 경우가 발생하거나 적은 수로 선출되는 경우가 발생한다. 클러스터 헤더가 적게 선출될 경우 클러스터 헤더에 높은 부하가 걸린다. 또한 선출된 클러스터 헤더의 위치에 따라 센서 노드가 소속되지 않은 클러스터가 발생할 경우도 있다. 이에 본 논문에서는 관심 영역을 일정한 섹터로 나누어 각 섹터마다 클러스터 헤더를 무작위로 하나씩 선출하는 알고리즘을 제안한다. 클러스터 구성 시 각 센서 노드는 가장 가까운 클러스터 헤더에 소속되어 클러스터 구성은 섹터와는 무관하게 진행된다. 이 알고리즘은 매 라운드마다 일정한 수의 클러스터 헤더를 보장하며 소속된 센서 노드가 없는 헤더가 발생하지 않도록 한다.

• 디지털산업정보학회논문지
• /
• 제12권2호
• /
• pp.7-14
• /
• 2016

In this paper presents a low power algorithm using a feasible cluster generation method considered glitch. The proposed algorithm is a method for reducing power consumption of a given circuit. The algorithm consists of a feasible cluster generation process and glitches removal process. So that glitches are not generated for the node to which the switching operation occurs most frequently in order to reduce the power consumption is a method for generating a feasible cluster. A feasible cluster generation process consisted of a node value set, dividing the node, the node aligned with the feasible cluster generation. A feasible cluster generation procedure is produced from the highest number of nodes in the output. When exceeding the number of OR-terms of the inputs of the selected node CLB prevents the signal path is varied by the evenly divided. If there are nodes with the same number of outputs selected by the first highest number of nodes in the input produces a feasible cluster. Glitch removal process removes glitches through the path balancing in the same manner as [5]. Experimental results were compared with the proposed algorithm [5]. Number of blocks has been increased by 5%, the power consumption was reduced by 3%.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2009년도 춘계 종합학술대회 논문집
• /
• pp.792-796
• /
• 2009

데이터 클러스터링 분야에서 최적의 클러스터 개수를 추정하는 것은 매우 중요한 일이다. 그것은 클러스터링의 적합성을 판단할 기준을 정하고 그 적합성을 극대화 하는 최적의 클러스터의 개수를 찾는 것이다. 본 논문에서는 클러스터의 적합성을 판단할 기준으로써 클러스터링 균형을 사용하여 최적의 클러스터 개수를 찾기 위한 효율적인 휴리스틱 방법을 제안하였다. k-means 사용하여 가상 및 실제 데이터 셋에 적용한 결과, 제안한 알고리즘이 계산효율 측면에서 우수함을 확인할 수 있었다.

• Communications for Statistical Applications and Methods
• /
• 제23권1호
• /
• pp.47-55
• /
• 2016

Stratified cluster sampling has been widely used for effective parameter estimations due to reductions in time and cost. The probability proportional to size (PPS) sampling method is used when the number of cluster element are significantly different. However, simple random sampling (SRS) is commonly used for simplicity if the number of cluster elements are almost the same. Also it is known that the ratio estimator produces a good performance when the total number of population elements is known. However, the two stage cluster estimator should be used if the total number of elements in population is neither known nor accurate. In this study we suggest a composite estimator by combining the ratio estimator and the two stage cluster estimator to obtain a better estimate under a certain population circumstance. Simulation studies are conducted to compare the superiority of the suggested estimator with two other estimators.

• 한국지능시스템학회논문지
• /
• 제9권6호
• /
• pp.621-626
• /
• 1999

In this paper a new cluster validation index which is heuristic but able to eliminate the monotonically decreasing tendency occurring in which the number of cluster c gets very large and close to the number of data points n is proposed. We review the FCM algorithm and some conventional cluster validity criteria discuss on the limiting behavior of the proposed validity index and provide some numerical examples showing the effectiveness of the proposed cluster validity index.

• 한국멀티미디어학회논문지
• /
• 제8권12호
• /
• pp.1623-1630
• /
• 2005

Adaptive modulation and coding (AMC), which has a number of variation levels in accordance with the fading channel variation, is a promising technique for communication systems. In this paper, we present an AMC method using the cluster in OFDM system for bandwidth efficiency and performance improvement. The AMC schemes applied into each cluster or some clusters are determined by the minimum or the average SNR value among all the sub carriers within the corresponding cluster. It is important to find the optimal information on cluster because AMC performance can be varied according to the number and position of cluster. It is shown by computer simulation that the AMC method outperforms the fixed modulation in terms of bandwidth efficiency and its performance can be determined by the position and number of clusters.

• 한국콘텐츠학회논문지
• /
• 제9권9호
• /
• pp.80-89
• /
• 2009

클러스터링 알고리즘에서 최적의 클러스터 수를 결정하기 위한 효율적인 고속 탐색 알고리즘을 소개한다. 제안하는 방법은 클러스터링 적합도의 척도로 사용되는 클러스터 타당성 평가기준을 토대로 한다. 데이터 집합에 클러스터링 프로세스를 진행하여 최적의 클러스터 형상에 도달하게 되면 클러스터 타당성 평가기준은 최대 혹은 최소값을 가질 것으로 기대한다. 본 논문에서는 최적의 클러스터 개수를 찾기 위한 고속의 비소모적 탐색 방법을 설계하고 실제 클러스터링과 접목한다. 제안하는 알고리즘은 k-means++ 클러스터링 알고리즘에 적용하였고, 클러스터 타당성 평가기준으로써 CB 및 PBM 타당성 평가기준 방법을 사용하였다. 몇몇의 가상 데이터 집합과 실제 데이터 집합에 실험한 결과, 제안하는 방법은 정확도의 손실 없이 계산 효율을 획기적으로 증가시킴을 보여주었다.

• 한국멀티미디어학회논문지
• /
• 제21권6호
• /
• pp.667-677
• /
• 2018

Since sensor networks consist of sensor nodes with limited energy resources, so efficient energy use of sensor nodes is very important in the design of sensor networks. Sensor nodes consume a lot of energy for data transmission. Clustering technique is used to efficiently use energy in data transmission. Recently, mobile sink techniques have been proposed to reduce the energy load concentrated on the cluster header near a sink node. The CMS(Cluster-based Mobile sink) technique minimizes the generation of control messages by creating a data transmission path while creating clusters, and supports the inter-cluster one-hop transmission. But, there is a case where there is no connectivity between neighbor clusters, it causes a problem of having a long hop data transmission path regardless of local distance. In this paper, we propose a SCBC(Strong connection balancing cluster) to support the path of the minimum number of hops. The proposed scheme minimizes the number of hops in the data transmission path and supports efficient use of energy in the cluster header. This also minimizes a number of hops in data transmission paths even when the sink moves and establishes a new path, and it supports the effect of extending the life cycle of the entire sensor network.

• ETRI Journal
• /
• 제41권5호
• /
• pp.648-657
• /
• 2019

A cluster topology was proposed with the assumption of zero noise to improve the performance of wireless body area networks (WBANs). However, in WBANs, the transmission power should be reduced as low as possible to avoid the effect of electromagnetic waves on the human body and to extend the lifetime of a battery. Therefore, in this work, we consider a bit error rate for a cluster-based WBAN and analyze the performance of the system while the transmission of sensors and cluster headers (CHs) is controlled. Moreover, a hierarchical topology is proposed for the cluster-based WBAN to further improve the throughput of the system; this proposed system is called as the hierarchical cluster WBAN. The hierarchical cluster WBAN is combined with a transmission control scheme, that is, complete control, spatial reuse superframe, to increase the throughput. The proposed system is analyzed and evaluated based on several factors of the system model, such as signal-to-noise ratio, number of clusters, and number of sensors. The calculation result indicates that the proposed hierarchical cluster WBAN outperforms the cluster-based WBAN in all analyzed scenarios.